Fast Feature Pyramids for Object Detection

Multi-resolution image features may be approximated via extrapolation from nearby scales, rather than being computed explicitly. This fundamental insight allows us to design object detection algorithms that are as accurate, and considerably faster, than the state-of-the-art. The computational bottle...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on pattern analysis and machine intelligence Vol. 36; no. 8; pp. 1532 - 1545
Main Authors:	Dollar, Piotr, Appel, Ron, Belongie, Serge, Perona, Pietro
Format:	Journal Article
Language:	English
Published:	Los Alamitos, CA IEEE 01.08.2014 IEEE Computer Society The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Accuracy Algorithmics. Computability. Computer arithmetics Algorithms Applied sciences Approximation Approximation methods Artificial intelligence Computation Computer science; control theory; systems Detectors Exact sciences and technology Feature extraction Histograms image pyramids Mathematical analysis natural image statistics Object detection Pattern recognition. Digital image processing. Computational geometry pedestrian detection Pyramids real-time systems Spectra Texture Theoretical computing Visual features Visual task performance Visualization Bottleneck Computer vision Image recognition Image resolution Statistical analysis Image processing Visual features pedestrian detection Pedestrian Real time image pyramids Narrow band Texture Multiresolution analysis Multiple image Visual system Extrapolation Surveillance natural image statistics real-time systems Object detection Fine grain structure Natural scenes Passband
ISSN:	0162-8828, 2160-9292, 1939-3539
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Multi-resolution image features may be approximated via extrapolation from nearby scales, rather than being computed explicitly. This fundamental insight allows us to design object detection algorithms that are as accurate, and considerably faster, than the state-of-the-art. The computational bottleneck of many modern detectors is the computation of features at every scale of a finely-sampled image pyramid. Our key insight is that one may compute finely sampled feature pyramids at a fraction of the cost, without sacrificing performance: for a broad family of features we find that features computed at octave-spaced scale intervals are sufficient to approximate features on a finely-sampled pyramid. Extrapolation is inexpensive as compared to direct feature computation. As a result, our approximation yields considerable speedups with negligible loss in detection accuracy. We modify three diverse visual recognition systems to use fast feature pyramids and show results on both pedestrian detection (measured on the Caltech, INRIA, TUD-Brussels and ETH data sets) and general object detection (measured on the PASCAL VOC). The approach is general and is widely applicable to vision algorithms requiring fine-grained multi-scale analysis. Our approximation is valid for images with broad spectra (most natural images) and fails for images with narrow band-pass spectra (e.g., periodic textures).
AbstractList	Multi-resolution image features may be approximated via extrapolation from nearby scales, rather than being computed explicitly. This fundamental insight allows us to design object detection algorithms that are as accurate, and considerably faster, than the state-of-the-art. The computational bottleneck of many modern detectors is the computation of features at every scale of a finely-sampled image pyramid. Our key insight is that one may compute finely sampled feature pyramids at a fraction of the cost, without sacrificing performance: for a broad family of features we find that features computed at octave-spaced scale intervals are sufficient to approximate features on a finely-sampled pyramid. Extrapolation is inexpensive as compared to direct feature computation. As a result, our approximation yields considerable speedups with negligible loss in detection accuracy. We modify three diverse visual recognition systems to use fast feature pyramids and show results on both pedestrian detection (measured on the Caltech, INRIA, TUD-Brussels and ETH data sets) and general object detection (measured on the PASCAL VOC). The approach is general and is widely applicable to vision algorithms requiring fine-grained multi-scale analysis. Our approximation is valid for images with broad spectra (most natural images) and fails for images with narrow band-pass spectra (e.g., periodic textures).
Author	Belongie, Serge Dollar, Piotr Appel, Ron Perona, Pietro
Author_xml	– sequence: 1 givenname: Piotr surname: Dollar fullname: Dollar, Piotr email: pdollar@microsoft.com organization: Interactive Visual Media Group, Microsoft Res., Redmond, WA, USA – sequence: 2 givenname: Ron surname: Appel fullname: Appel, Ron email: appel@caltech.edu organization: Dept. of Electr. Eng., California Inst. of Technol., Pasadena, CA, USA – sequence: 3 givenname: Serge surname: Belongie fullname: Belongie, Serge organization: Cornell Comput. Sci. Dept., Cornell NYC Tech, Cornell, NY, USA – sequence: 4 givenname: Pietro surname: Perona fullname: Perona, Pietro email: perona@caltech.edu organization: Dept. of Electr. Eng., California Inst. of Technol., Pasadena, CA, USA
BackLink	http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=28720933$$DView record in Pascal Francis https://www.ncbi.nlm.nih.gov/pubmed/26353336$$D View this record in MEDLINE/PubMed
BookMark	eNqFkU9r20AQxZeSUjtuv0ADQRAKISB39r_2GNK6CbjYh_S8rKRZkJGlZFc6-NtnXbsO5JCe5vJ7M_PeOydnXd8hIV8pzCkF8_1xffv7Yc6AijnjAEKbD2TKqILcMMPOyBSoYnlRsGJCzmPcQCIl8E9kwhSXnHM1JTcLF4dsgW4YA2brXXDbpo6Z70O2KjdYDdkPHNJo-u4z-ehdG_HLcc7In8XPx7v7fLn69XB3u8wrQcWQo1RMmIIbjaVwoIu6rGvtBS-1qL2nmnvJhIBCoa8Yl6VTUkouE6ag1jWfkevD3qfQP48YB7ttYoVt6zrsx2ipplRyncz9H1WaShBG84RevUE3_Ri6ZMRSKRQYSB8l6vJIjeUWa_sUmq0LO_svsAR8OwIuVq71wXVVE1-5QjMwfH-OHbgq9DEG9CeEgt23Z_-2Z_ft2WN7SVS8EVXN4PbZD8E17fvSi4O0QcTTrWRfiPT4Cz5Aots
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_1016_j_image_2017_02_008 crossref_primary_10_3390_electronics12173640 crossref_primary_10_1007_s00530_019_00614_y crossref_primary_10_1016_j_patrec_2018_07_035 crossref_primary_10_1109_TCYB_2016_2601438 crossref_primary_10_1109_TIM_2018_2871353 crossref_primary_10_1109_LSP_2017_2731952 crossref_primary_10_1016_j_eswa_2015_01_032 crossref_primary_10_9717_kmms_2016_19_12_1909 crossref_primary_10_1016_j_heliyon_2022_e12086 crossref_primary_10_1109_TITS_2018_2869087 crossref_primary_10_1109_TITS_2015_2496795 crossref_primary_10_3390_app10051866 crossref_primary_10_1007_s00371_020_01880_y crossref_primary_10_1109_TCSVT_2018_2873185 crossref_primary_10_1109_TITS_2017_2769719 crossref_primary_10_1177_1550147718763550 crossref_primary_10_1049_iet_cvi_2016_0303 crossref_primary_10_1007_s13177_024_00401_8 crossref_primary_10_1016_j_patrec_2016_11_020 crossref_primary_10_3390_ani14010159 crossref_primary_10_1038_s41598_024_64677_2 crossref_primary_10_1109_TII_2021_3056554 crossref_primary_10_1109_TPAMI_2022_3218569 crossref_primary_10_1587_transfun_E100_A_1601 crossref_primary_10_1016_j_dt_2020_10_006 crossref_primary_10_3389_fnbot_2019_00010 crossref_primary_10_1016_j_imavis_2018_06_009 crossref_primary_10_1016_j_jvcir_2022_103715 crossref_primary_10_1016_j_displa_2022_102354 crossref_primary_10_1109_TIP_2023_3297408 crossref_primary_10_3390_app13074210 crossref_primary_10_1109_TPAMI_2017_2738645 crossref_primary_10_1109_TCSVT_2020_3036467 crossref_primary_10_3390_app9040752 crossref_primary_10_1109_TCSVT_2018_2886476 crossref_primary_10_1109_TITS_2017_2784093 crossref_primary_10_3390_s24123739 crossref_primary_10_1109_ACCESS_2019_2932749 crossref_primary_10_1088_2631_8695_ad507d crossref_primary_10_1109_TCSVT_2020_3000223 crossref_primary_10_1016_j_patcog_2021_108063 crossref_primary_10_1016_j_compeleceng_2023_108695 crossref_primary_10_1016_j_imavis_2022_104394 crossref_primary_10_1051_matecconf_201710003010 crossref_primary_10_1109_TSM_2019_2931328 crossref_primary_10_1109_TCSI_2024_3425751 crossref_primary_10_1016_j_cosrev_2018_03_001 crossref_primary_10_1007_s10044_022_01076_1 crossref_primary_10_1016_j_compbiomed_2022_105989 crossref_primary_10_1109_ACCESS_2019_2909992 crossref_primary_10_1109_TMM_2015_2508146 crossref_primary_10_3389_fphy_2023_1121311 crossref_primary_10_1016_j_displa_2023_102454 crossref_primary_10_1109_TCSVT_2017_2653187 crossref_primary_10_1587_transinf_2018EDL8112 crossref_primary_10_1007_s11227_025_07208_8 crossref_primary_10_1016_j_asoc_2019_106014 crossref_primary_10_1007_s11263_020_01415_x crossref_primary_10_1007_s00521_020_05314_7 crossref_primary_10_1109_TPAMI_2015_2470658 crossref_primary_10_1007_s11042_022_13515_6 crossref_primary_10_1016_j_imavis_2020_103986 crossref_primary_10_1109_TCSVT_2017_2648850 crossref_primary_10_1016_j_inffus_2018_09_015 crossref_primary_10_1007_s11554_021_01131_w crossref_primary_10_1016_j_neucom_2019_12_110 crossref_primary_10_1007_s11554_023_01287_7 crossref_primary_10_1109_ACCESS_2021_3100369 crossref_primary_10_1016_j_neucom_2018_06_088 crossref_primary_10_1016_j_knosys_2023_110719 crossref_primary_10_1145_3626754 crossref_primary_10_1038_s44333_025_00037_5 crossref_primary_10_1109_TGRS_2019_2957251 crossref_primary_10_1109_TCSVT_2021_3096237 crossref_primary_10_1109_TCSVT_2016_2630731 crossref_primary_10_1109_TIV_2019_2904389 crossref_primary_10_1007_s11063_019_10182_x crossref_primary_10_3390_sym12122012 crossref_primary_10_1109_TSP_2019_2931170 crossref_primary_10_1016_j_neucom_2021_10_006 crossref_primary_10_1109_ACCESS_2018_2879473 crossref_primary_10_1016_j_infrared_2018_11_007 crossref_primary_10_1109_TITS_2017_2750058 crossref_primary_10_1016_j_imavis_2019_02_009 crossref_primary_10_1007_s11277_017_5211_2 crossref_primary_10_1109_TCSVT_2015_2492838 crossref_primary_10_1155_2019_3651529 crossref_primary_10_1016_j_bspc_2024_106056 crossref_primary_10_3390_s22093568 crossref_primary_10_1587_transinf_2019EDL8027 crossref_primary_10_1155_2019_9060797 crossref_primary_10_1299_jbse_24_00367 crossref_primary_10_1007_s11554_022_01233_z crossref_primary_10_1109_ACCESS_2020_2994000 crossref_primary_10_1051_smdo_2019016 crossref_primary_10_1007_s11042_023_16604_2 crossref_primary_10_1109_TPAMI_2015_2474388 crossref_primary_10_1109_TPAMI_2017_2756936 crossref_primary_10_1007_s11042_018_6995_0 crossref_primary_10_1109_TCYB_2014_2330853 crossref_primary_10_1109_TIP_2015_2507942 crossref_primary_10_1109_JSEN_2020_2966034 crossref_primary_10_1109_TITS_2022_3145467 crossref_primary_10_1016_j_neucom_2021_11_091 crossref_primary_10_1109_TMM_2015_2505089 crossref_primary_10_1109_TITS_2017_2749971 crossref_primary_10_3390_s21196358 crossref_primary_10_1109_ACCESS_2018_2836921 crossref_primary_10_1109_TCYB_2019_2894261 crossref_primary_10_1007_s12559_015_9373_5 crossref_primary_10_1109_ACCESS_2020_2995321 crossref_primary_10_1007_s11042_020_08744_6 crossref_primary_10_1016_j_eswa_2025_128529 crossref_primary_10_1162_neco_a_01156 crossref_primary_10_1109_TPAMI_2020_3009758 crossref_primary_10_1007_s13177_025_00507_7 crossref_primary_10_1016_j_jvcir_2018_02_001 crossref_primary_10_1109_TPAMI_2016_2537325 crossref_primary_10_1109_TSP_2018_2821650 crossref_primary_10_1061__ASCE_CP_1943_5487_0000813 crossref_primary_10_1016_j_image_2016_06_002 crossref_primary_10_1007_s13042_022_01771_9 crossref_primary_10_1007_s11042_018_5846_3 crossref_primary_10_1016_j_neucom_2017_06_009 crossref_primary_10_1016_j_patcog_2018_08_005 crossref_primary_10_1016_j_image_2018_09_002 crossref_primary_10_1109_TPAMI_2017_2706685 crossref_primary_10_1016_j_patcog_2016_05_027 crossref_primary_10_1007_s11063_018_9837_1 crossref_primary_10_3390_electronics14071291 crossref_primary_10_1109_ACCESS_2021_3066538 crossref_primary_10_1007_s11042_024_20335_3 crossref_primary_10_1109_ACCESS_2021_3063028 crossref_primary_10_1016_j_procs_2016_07_472 crossref_primary_10_1016_j_patcog_2020_107512 crossref_primary_10_1109_TASE_2018_2830655 crossref_primary_10_1016_j_patcog_2018_08_018 crossref_primary_10_1049_ipr2_12378 crossref_primary_10_1109_ACCESS_2017_2698164 crossref_primary_10_1186_s12544_020_00425_7 crossref_primary_10_1109_TCSVT_2018_2817609 crossref_primary_10_1002_tee_23737 crossref_primary_10_1109_TCSVT_2014_2360030 crossref_primary_10_1109_TPAMI_2018_2876253 crossref_primary_10_1016_j_neucom_2023_126558 crossref_primary_10_1007_s11042_025_20785_3 crossref_primary_10_1017_S1751731115001342 crossref_primary_10_1007_s11263_015_0823_z crossref_primary_10_1016_j_image_2016_05_020 crossref_primary_10_1109_ACCESS_2021_3063030 crossref_primary_10_3390_s25133854 crossref_primary_10_1109_ACCESS_2019_2941892 crossref_primary_10_1109_TNNLS_2018_2876865 crossref_primary_10_1007_s12369_018_0507_2 crossref_primary_10_1049_iet_its_2018_5618 crossref_primary_10_1088_1742_6596_1883_1_012075 crossref_primary_10_1109_ACCESS_2020_3021508 crossref_primary_10_1007_s10489_021_02293_7 crossref_primary_10_1109_TVT_2018_2843394 crossref_primary_10_1007_s40815_019_00645_7 crossref_primary_10_1109_TITS_2018_2838128 crossref_primary_10_1016_j_neucom_2016_10_018 crossref_primary_10_1109_TIP_2017_2705426 crossref_primary_10_3390_s19040866 crossref_primary_10_1109_ACCESS_2019_2962100 crossref_primary_10_1109_ACCESS_2022_3165821 crossref_primary_10_1007_s11063_022_10910_w crossref_primary_10_1109_TITS_2017_2686871 crossref_primary_10_3390_s20164363 crossref_primary_10_1109_TIP_2022_3189803 crossref_primary_10_1016_j_imavis_2019_04_003 crossref_primary_10_1007_s10851_018_0834_9 crossref_primary_10_3390_jimaging10010012 crossref_primary_10_1109_ACCESS_2024_3388889 crossref_primary_10_1155_2017_9830641 crossref_primary_10_1177_00202940221089237 crossref_primary_10_5507_tots_2019_002 crossref_primary_10_1109_ACCESS_2021_3057616 crossref_primary_10_1016_j_image_2016_05_007 crossref_primary_10_1587_transinf_2018EDL8170 crossref_primary_10_1007_s11042_019_07939_w crossref_primary_10_1007_s11263_016_0890_9 crossref_primary_10_1016_j_smhl_2018_07_024 crossref_primary_10_1007_s11263_021_01512_5 crossref_primary_10_1186_s13640_016_0143_4 crossref_primary_10_1109_TNSE_2022_3227119 crossref_primary_10_1016_j_csi_2022_103702 crossref_primary_10_3233_MGS_200330 crossref_primary_10_1088_1742_6596_1865_4_042019 crossref_primary_10_1371_journal_pone_0208385 crossref_primary_10_1016_j_patcog_2019_04_018 crossref_primary_10_1109_TCSVT_2018_2883558 crossref_primary_10_1109_TITS_2017_2714691 crossref_primary_10_1109_TMM_2016_2638622 crossref_primary_10_1109_TMM_2023_3272471 crossref_primary_10_1002_ecj_12268 crossref_primary_10_1016_j_compag_2024_108963 crossref_primary_10_1186_s13638_022_02157_9 crossref_primary_10_1109_JSTSP_2022_3211198 crossref_primary_10_3390_s19040780 crossref_primary_10_1016_j_rcim_2019_101887 crossref_primary_10_1007_s11760_020_01742_z crossref_primary_10_1109_TITS_2022_3171250 crossref_primary_10_1016_j_cviu_2016_05_003 crossref_primary_10_1049_cvi2_70010 crossref_primary_10_3390_inventions6040079 crossref_primary_10_1109_ACCESS_2018_2855703 crossref_primary_10_1145_3565886 crossref_primary_10_1088_1742_6596_1187_4_042100 crossref_primary_10_1109_ACCESS_2020_3012557 crossref_primary_10_3390_electronics9091478 crossref_primary_10_1016_j_patcog_2016_06_002 crossref_primary_10_1016_j_patcog_2018_10_008 crossref_primary_10_1587_transinf_2016EDL8164 crossref_primary_10_1016_j_future_2022_07_003 crossref_primary_10_3390_electronics13091697 crossref_primary_10_1007_s10489_022_03549_6 crossref_primary_10_1007_s00521_017_3152_z crossref_primary_10_1016_j_cviu_2022_103554 crossref_primary_10_1016_j_dsp_2021_103370 crossref_primary_10_1016_j_infrared_2019_103178 crossref_primary_10_1007_s11554_020_00962_3 crossref_primary_10_1016_j_neucom_2020_12_005 crossref_primary_10_1007_s11042_022_13458_y crossref_primary_10_1109_LRA_2024_3392083 crossref_primary_10_1109_TITS_2016_2561262 crossref_primary_10_3390_s18124290 crossref_primary_10_1109_ACCESS_2019_2948876 crossref_primary_10_1007_s11042_018_6057_7 crossref_primary_10_1007_s11042_018_6769_8 crossref_primary_10_1016_j_neunet_2023_01_028 crossref_primary_10_1007_s11042_022_13007_7 crossref_primary_10_1016_j_patcog_2018_10_028 crossref_primary_10_3390_agronomy14102253 crossref_primary_10_1109_ACCESS_2021_3114399 crossref_primary_10_1109_TIV_2016_2615523 crossref_primary_10_3390_rs16203862 crossref_primary_10_1109_ACCESS_2020_3046515 crossref_primary_10_3390_ijgi10040234 crossref_primary_10_3390_s25175497 crossref_primary_10_1109_TITS_2015_2409889 crossref_primary_10_1016_j_inffus_2022_06_008 crossref_primary_10_1109_JSEN_2019_2962834 crossref_primary_10_1016_j_patrec_2017_02_018 crossref_primary_10_1134_S1054661818020074 crossref_primary_10_1109_TIP_2018_2818018 crossref_primary_10_1007_s00138_018_0984_1 crossref_primary_10_1007_s13735_019_00180_z crossref_primary_10_1051_itmconf_20171205004 crossref_primary_10_1007_s10489_023_04750_x crossref_primary_10_1049_iet_ipr_2018_5424 crossref_primary_10_1049_iet_cvi_2016_0068 crossref_primary_10_1109_TIP_2018_2855399 crossref_primary_10_3390_rs12071217 crossref_primary_10_3390_sym11101205 crossref_primary_10_3390_app9020315 crossref_primary_10_3390_s19122671 crossref_primary_10_1016_j_phycom_2024_102303 crossref_primary_10_1016_j_enbuild_2024_113936 crossref_primary_10_1109_ACCESS_2021_3120618 crossref_primary_10_1007_s11263_018_1087_1 crossref_primary_10_1007_s13369_020_04990_w crossref_primary_10_1109_LGRS_2019_2919755 crossref_primary_10_1109_TGRS_2019_2897139 crossref_primary_10_1109_TGRS_2020_3011418 crossref_primary_10_1109_ACCESS_2021_3119629 crossref_primary_10_1109_TITS_2019_2929618 crossref_primary_10_1007_s10334_020_00871_3 crossref_primary_10_1007_s11042_018_6974_5 crossref_primary_10_1016_j_cviu_2022_103508 crossref_primary_10_1109_TPAMI_2020_3032166 crossref_primary_10_1109_TITS_2020_3041679 crossref_primary_10_1007_s11760_018_1406_6 crossref_primary_10_1007_s00779_019_01278_1 crossref_primary_10_1109_TCDS_2019_2928338 crossref_primary_10_1007_s11042_019_07825_5 crossref_primary_10_1109_ACCESS_2019_2936454 crossref_primary_10_1142_S0218001416550223 crossref_primary_10_1109_ACCESS_2019_2943112 crossref_primary_10_1109_TMM_2017_2759508 crossref_primary_10_3390_s21124184 crossref_primary_10_1016_j_neunet_2023_06_012 crossref_primary_10_1109_JSEN_2021_3115016 crossref_primary_10_1016_j_isprsjprs_2023_01_009 crossref_primary_10_1016_j_neucom_2021_06_072 crossref_primary_10_1007_s00521_020_04731_y crossref_primary_10_1016_j_patcog_2022_108738 crossref_primary_10_1049_itr2_12066 crossref_primary_10_1109_TIP_2016_2609807 crossref_primary_10_1109_TITS_2019_2906132 crossref_primary_10_1109_TITS_2020_2991848 crossref_primary_10_3389_fnbot_2023_1255085 crossref_primary_10_1109_ACCESS_2021_3093698 crossref_primary_10_3390_s17112699 crossref_primary_10_1007_s00521_021_05978_9 crossref_primary_10_1007_s11042_024_18852_2 crossref_primary_10_1186_s41935_022_00314_1 crossref_primary_10_1007_s11263_020_01369_0 crossref_primary_10_1007_s10489_023_04628_y crossref_primary_10_1016_j_heliyon_2022_e09633 crossref_primary_10_1109_LSP_2022_3215920 crossref_primary_10_1109_TMM_2019_2929005 crossref_primary_10_1109_MM_2017_4241343 crossref_primary_10_1109_TIP_2019_2944306 crossref_primary_10_1007_s11042_018_5819_6 crossref_primary_10_1109_TII_2019_2897128 crossref_primary_10_1007_s11771_020_4448_1 crossref_primary_10_1109_TPAMI_2019_2897684 crossref_primary_10_3390_s18113776 crossref_primary_10_1002_rob_22082 crossref_primary_10_1155_2022_5878443 crossref_primary_10_1016_j_neucom_2018_03_070 crossref_primary_10_1109_TITS_2018_2847224 crossref_primary_10_1109_TPAMI_2014_2377734 crossref_primary_10_1016_j_knosys_2017_06_001 crossref_primary_10_1016_j_neucom_2018_02_068 crossref_primary_10_1109_TPAMI_2018_2807450 crossref_primary_10_1016_j_cviu_2016_03_003 crossref_primary_10_1007_s11042_019_08008_y crossref_primary_10_1109_TITS_2019_2910643 crossref_primary_10_3390_app9030565 crossref_primary_10_3390_s21010027 crossref_primary_10_1016_j_eswa_2022_118406 crossref_primary_10_1007_s11263_022_01728_z crossref_primary_10_1016_j_neucom_2019_11_023 crossref_primary_10_1016_j_neucom_2019_11_024 crossref_primary_10_3390_s24041168 crossref_primary_10_1007_s42154_018_0009_9 crossref_primary_10_3390_s16010128 crossref_primary_10_1007_s11042_019_07747_2 crossref_primary_10_3390_s18041063 crossref_primary_10_1007_s00138_020_01106_0 crossref_primary_10_1007_s00521_019_04424_1 crossref_primary_10_1007_s11042_023_15608_2 crossref_primary_10_1007_s00138_021_01169_7 crossref_primary_10_1016_j_eswa_2023_122190 crossref_primary_10_1016_j_jvcir_2016_06_011 crossref_primary_10_1177_0278364917730603 crossref_primary_10_1007_s13369_017_2424_3 crossref_primary_10_3390_a11120192 crossref_primary_10_4271_12_08_03_0027 crossref_primary_10_1016_j_imavis_2022_104553 crossref_primary_10_1109_TIM_2022_3165838 crossref_primary_10_1109_TSMC_2016_2587483 crossref_primary_10_1109_TCSVT_2016_2581660 crossref_primary_10_3390_rs13142665 crossref_primary_10_1088_1361_6501_acfd4d crossref_primary_10_1109_THMS_2016_2620110 crossref_primary_10_1049_iet_its_2019_0468 crossref_primary_10_1016_j_neucom_2018_03_041 crossref_primary_10_1109_TITS_2018_2807199 crossref_primary_10_1049_iet_its_2018_5197 crossref_primary_10_1109_TIP_2022_3154286 crossref_primary_10_1016_j_eswa_2018_07_020 crossref_primary_10_1007_s11042_017_5002_5 crossref_primary_10_1016_j_procs_2017_09_094 crossref_primary_10_1109_TITS_2015_2502325 crossref_primary_10_1109_JIOT_2022_3195359 crossref_primary_10_3390_electronics12173576 crossref_primary_10_1051_0004_6361_202243478 crossref_primary_10_1007_s11063_016_9561_7 crossref_primary_10_1016_j_patcog_2022_108786 crossref_primary_10_3390_jimaging6120142 crossref_primary_10_1109_TITS_2024_3447453 crossref_primary_10_1016_j_matdes_2023_112470 crossref_primary_10_3390_s17020336 crossref_primary_10_1016_j_autcon_2021_103704 crossref_primary_10_1007_s11554_016_0573_3 crossref_primary_10_1007_s13735_019_00171_0 crossref_primary_10_1061_JTEPBS_TEENG_8652 crossref_primary_10_1016_j_cviu_2024_103957 crossref_primary_10_1109_ACCESS_2019_2922479 crossref_primary_10_3390_rs10121990 crossref_primary_10_1109_TETCI_2018_2865215 crossref_primary_10_1587_transinf_2018RCP0005 crossref_primary_10_1016_j_neucom_2019_10_025 crossref_primary_10_1117_1_JEI_32_2_023011 crossref_primary_10_1007_s10462_023_10475_7 crossref_primary_10_1109_TITS_2020_3019390 crossref_primary_10_1016_j_cosrev_2020_100301 crossref_primary_10_3390_sym13020250 crossref_primary_10_1007_s11042_020_09143_7 crossref_primary_10_1109_TPAMI_2021_3076733 crossref_primary_10_1016_j_displa_2022_102317 crossref_primary_10_1109_TITS_2017_2676182 crossref_primary_10_1007_s40998_022_00512_6 crossref_primary_10_1109_ACCESS_2020_2981620 crossref_primary_10_1109_TIP_2020_2966371 crossref_primary_10_1016_j_cviu_2020_102907 crossref_primary_10_1109_JSTARS_2020_3032221 crossref_primary_10_1016_j_imavis_2016_10_010 crossref_primary_10_2478_ttj_2019_0017 crossref_primary_10_1080_21642583_2022_2062479 crossref_primary_10_3390_s23239380 crossref_primary_10_1007_s00530_022_00974_y crossref_primary_10_1109_TIP_2017_2773199 crossref_primary_10_3390_jimaging6080078 crossref_primary_10_1109_TITS_2016_2614548 crossref_primary_10_1109_TVT_2020_2983825 crossref_primary_10_1109_JSTARS_2025_3576127 crossref_primary_10_1049_ipr2_12297 crossref_primary_10_1109_TCSVT_2019_2913114 crossref_primary_10_1016_j_cviu_2016_09_001 crossref_primary_10_1016_j_procs_2019_01_018 crossref_primary_10_1016_j_jvcir_2019_06_004 crossref_primary_10_1109_TPAMI_2023_3290594 crossref_primary_10_1109_TITS_2019_2911315 crossref_primary_10_1109_TPAMI_2019_2929520 crossref_primary_10_1007_s10479_020_03823_1 crossref_primary_10_1109_TIV_2017_2726764 crossref_primary_10_1051_e3sconf_202124503062 crossref_primary_10_1007_s11227_020_03345_4 crossref_primary_10_3390_app10030809 crossref_primary_10_1109_TCSVT_2019_2950526 crossref_primary_10_1007_s11265_018_1374_7 crossref_primary_10_1109_TITS_2015_2495342 crossref_primary_10_1007_s00521_021_06628_w crossref_primary_10_1109_TCSVT_2021_3060162 crossref_primary_10_1109_ACCESS_2025_3598771 crossref_primary_10_1109_TITS_2019_2933581 crossref_primary_10_3390_s18030882 crossref_primary_10_3390_jimaging6050027 crossref_primary_10_1109_TIP_2015_2483376 crossref_primary_10_1016_j_procs_2016_11_016 crossref_primary_10_1016_j_isprsjprs_2016_11_006 crossref_primary_10_1109_TIV_2017_2772889 crossref_primary_10_1007_s00521_021_06265_3 crossref_primary_10_1016_j_knosys_2022_108439 crossref_primary_10_1016_j_patcog_2016_09_010 crossref_primary_10_1109_ACCESS_2018_2889187 crossref_primary_10_1007_s00521_019_04057_4 crossref_primary_10_1049_iet_cvi_2018_5304 crossref_primary_10_1007_s11042_019_7204_5 crossref_primary_10_1109_TITS_2017_2756989 crossref_primary_10_1016_j_neucom_2017_11_060 crossref_primary_10_1016_j_patcog_2017_04_027 crossref_primary_10_1109_ACCESS_2020_3025193 crossref_primary_10_3390_s22124441 crossref_primary_10_1002_rob_21814 crossref_primary_10_1007_s10489_021_02254_0 crossref_primary_10_1049_iet_cvi_2018_5315 crossref_primary_10_1109_LGRS_2015_2439517 crossref_primary_10_1007_s00500_020_04999_1 crossref_primary_10_1109_TCYB_2018_2803217 crossref_primary_10_3389_fimag_2024_1387543 crossref_primary_10_1049_iet_cvi_2016_0403 crossref_primary_10_1088_1361_6501_abb745 crossref_primary_10_1109_TCYB_2015_2508603 crossref_primary_10_1016_j_neucom_2017_03_078 crossref_primary_10_1109_TPAMI_2023_3268864 crossref_primary_10_3390_jimaging6060048 crossref_primary_10_1007_s11265_018_1361_z crossref_primary_10_1016_j_cej_2023_142756 crossref_primary_10_1016_j_knosys_2022_108254 crossref_primary_10_1080_01431161_2019_1685720 crossref_primary_10_1007_s11760_025_04032_8 crossref_primary_10_1186_s40537_018_0131_x crossref_primary_10_3390_app132112068 crossref_primary_10_1109_TITS_2019_2923752 crossref_primary_10_1109_TITS_2024_3360875 crossref_primary_10_1109_ACCESS_2020_3015580 crossref_primary_10_1016_j_neucom_2017_03_050 crossref_primary_10_3390_rs12152379 crossref_primary_10_1016_j_isprsjprs_2019_02_005 crossref_primary_10_1016_j_fusengdes_2025_115164 crossref_primary_10_1016_j_neucom_2018_09_003 crossref_primary_10_1016_j_isprsjprs_2022_02_006 crossref_primary_10_1177_1729881417704544 crossref_primary_10_1680_jsmic_19_00017 crossref_primary_10_1587_transinf_2019EDP7092 crossref_primary_10_1109_ACCESS_2020_3012089 crossref_primary_10_1109_TITS_2019_2942045 crossref_primary_10_1117_1_JEI_31_4_043004 crossref_primary_10_1109_JSEN_2020_3038487 crossref_primary_10_3390_s19010004 crossref_primary_10_1016_j_cviu_2020_103030 crossref_primary_10_1109_TIP_2019_2938877 crossref_primary_10_1007_s11042_018_6173_4 crossref_primary_10_3390_s18072272 crossref_primary_10_1109_TIM_2019_2955799 crossref_primary_10_3233_ICA_200636 crossref_primary_10_1109_TNNLS_2024_3387282 crossref_primary_10_1049_iet_cvi_2018_5598 crossref_primary_10_1007_s11045_021_00764_1 crossref_primary_10_1007_s00530_016_0518_5 crossref_primary_10_1109_TCSVT_2021_3049397 crossref_primary_10_1109_TII_2019_2958826 crossref_primary_10_1109_TCSVT_2016_2539684 crossref_primary_10_1109_TITS_2020_2982804 crossref_primary_10_1007_s11042_022_14131_0 crossref_primary_10_3390_s22124416 crossref_primary_10_3390_diagnostics14151646 crossref_primary_10_1016_j_cviu_2017_10_009 crossref_primary_10_1109_TCSVT_2018_2882192 crossref_primary_10_1016_j_patcog_2016_08_015 crossref_primary_10_3390_s18113994 crossref_primary_10_1109_TMM_2021_3075323 crossref_primary_10_1007_s11265_023_01843_1 crossref_primary_10_1016_j_neucom_2017_03_007 crossref_primary_10_1109_TMM_2023_3323860 crossref_primary_10_1016_j_neucom_2015_03_125 crossref_primary_10_1109_TMM_2021_3140025 crossref_primary_10_1088_1742_6596_1964_6_062047 crossref_primary_10_1016_j_cosrev_2025_100804 crossref_primary_10_1016_j_engappai_2021_104469 crossref_primary_10_1109_TIP_2020_2973513 crossref_primary_10_1109_TPAMI_2019_2910514 crossref_primary_10_1109_ACCESS_2019_2901270 crossref_primary_10_1016_j_neucom_2017_12_042 crossref_primary_10_1007_s11042_022_13667_5 crossref_primary_10_1016_j_patrec_2017_11_014 crossref_primary_10_1109_TIP_2021_3049948 crossref_primary_10_1016_j_robot_2018_12_007 crossref_primary_10_1109_ACCESS_2025_3607191 crossref_primary_10_1109_ACCESS_2020_3022517 crossref_primary_10_1109_TITS_2018_2857814 crossref_primary_10_1016_j_cviu_2016_07_003 crossref_primary_10_1002_mp_14118 crossref_primary_10_1016_j_patcog_2018_01_029 crossref_primary_10_1007_s11063_019_10046_4 crossref_primary_10_1515_amcs_2017_0013 crossref_primary_10_1002_rob_21667 crossref_primary_10_1007_s11042_023_17188_7 crossref_primary_10_1007_s11063_022_10855_0 crossref_primary_10_1109_ACCESS_2019_2940626 crossref_primary_10_1109_TIE_2019_2898624 crossref_primary_10_3390_s151229838 crossref_primary_10_1049_joe_2015_0032 crossref_primary_10_1007_s41315_019_00107_1 crossref_primary_10_1109_TCSVT_2019_2906195 crossref_primary_10_1038_s41467_024_55749_y crossref_primary_10_1109_TIP_2019_2896952 crossref_primary_10_1109_TITS_2019_2904836 crossref_primary_10_1145_3472288 crossref_primary_10_3390_e24081091 crossref_primary_10_1016_j_patcog_2016_07_010 crossref_primary_10_3390_rs9111170 crossref_primary_10_1016_j_seares_2018_09_014 crossref_primary_10_1007_s11263_020_01393_0 crossref_primary_10_1007_s11042_023_16595_0 crossref_primary_10_1016_j_imavis_2017_02_007 crossref_primary_10_3390_rs14143347 crossref_primary_10_1109_TITS_2019_2958486 crossref_primary_10_1007_s11045_018_0621_1 crossref_primary_10_3390_electronics8060595 crossref_primary_10_1088_1757_899X_646_1_012053 crossref_primary_10_1038_s41598_019_56309_x crossref_primary_10_1007_s11554_021_01178_9 crossref_primary_10_1049_iet_cvi_2015_0451 crossref_primary_10_1109_TIV_2023_3302032 crossref_primary_10_3389_fnbot_2018_00064 crossref_primary_10_1109_LGRS_2017_2677954 crossref_primary_10_1177_1729881418770545 crossref_primary_10_1016_j_autcon_2020_103289 crossref_primary_10_1080_09540091_2023_2202363 crossref_primary_10_3390_electronics7100216 crossref_primary_10_1016_j_neucom_2019_08_038 crossref_primary_10_3390_s24216911 crossref_primary_10_1109_TITS_2017_2682181 crossref_primary_10_1109_TVT_2015_2500275 crossref_primary_10_1109_ACCESS_2022_3153708 crossref_primary_10_1016_j_cviu_2017_01_003 crossref_primary_10_1007_s10586_018_1747_5 crossref_primary_10_1016_j_cviu_2017_01_001 crossref_primary_10_1007_s11227_017_2202_8 crossref_primary_10_1109_TITS_2016_2594816 crossref_primary_10_3390_app14020731 crossref_primary_10_3390_s17040843 crossref_primary_10_1109_TITS_2016_2567418 crossref_primary_10_1007_s11063_017_9746_8 crossref_primary_10_1108_IR_11_2020_0246 crossref_primary_10_1016_j_imavis_2024_105106 crossref_primary_10_1016_j_neucom_2020_02_096 crossref_primary_10_3390_s21248410 crossref_primary_10_1007_s11042_018_6467_6 crossref_primary_10_3390_s16081296 crossref_primary_10_1007_s00034_025_03148_z crossref_primary_10_3390_jmse13020205 crossref_primary_10_3390_s25082446 crossref_primary_10_1109_TCSVT_2017_2672686 crossref_primary_10_1007_s00371_021_02157_8 crossref_primary_10_1145_3635155 crossref_primary_10_1016_j_isprsjprs_2022_04_002 crossref_primary_10_3390_s20030628 crossref_primary_10_1109_TIFS_2019_2916592 crossref_primary_10_3390_rs15082041 crossref_primary_10_1007_s10586_024_04326_5 crossref_primary_10_1016_j_neucom_2019_08_016 crossref_primary_10_3390_s151229874 crossref_primary_10_1109_TSMC_2018_2871750 crossref_primary_10_3390_electronics13101989 crossref_primary_10_1109_TIP_2023_3272826 crossref_primary_10_1109_JSEN_2021_3062762 crossref_primary_10_1155_2015_767423 crossref_primary_10_1049_ipr2_12042 crossref_primary_10_1007_s10489_021_02294_6 crossref_primary_10_1109_ACCESS_2019_2939201 crossref_primary_10_3788_gzxb20255406_0610001 crossref_primary_10_1016_j_flowmeasinst_2023_102370 crossref_primary_10_1016_j_neucom_2020_02_075 crossref_primary_10_1016_j_neucom_2019_08_008 crossref_primary_10_1109_TPAMI_2014_2345390 crossref_primary_10_1016_j_neucom_2015_08_107 crossref_primary_10_1109_TITS_2019_2948044 crossref_primary_10_4018_IJSWIS_359769 crossref_primary_10_3390_s18124385 crossref_primary_10_3390_s24051709 crossref_primary_10_1109_TIV_2024_3367688 crossref_primary_10_1016_j_infrared_2016_12_021 crossref_primary_10_1016_j_patrec_2017_09_040 crossref_primary_10_1016_j_jvcir_2020_102843 crossref_primary_10_1371_journal_pone_0173317 crossref_primary_10_1088_1742_6596_1634_1_012032 crossref_primary_10_1109_TIP_2018_2865280 crossref_primary_10_1088_1742_6596_1544_1_012022 crossref_primary_10_1109_ACCESS_2019_2904712 crossref_primary_10_1007_s11042_018_6241_9 crossref_primary_10_1016_j_imavis_2021_104107 crossref_primary_10_1016_j_cviu_2014_10_003 crossref_primary_10_1016_j_patcog_2024_110541 crossref_primary_10_1109_TIP_2019_2917781 crossref_primary_10_1007_s00371_023_03137_w crossref_primary_10_1177_09544070231153199 crossref_primary_10_1049_itr2_12562 crossref_primary_10_1016_j_apgeog_2015_07_010 crossref_primary_10_1109_JSSC_2019_2937437 crossref_primary_10_3390_s20133646 crossref_primary_10_1016_j_jvcir_2018_01_013 crossref_primary_10_1016_j_ifacol_2019_09_078 crossref_primary_10_1016_j_patcog_2018_02_022 crossref_primary_10_1016_j_compag_2024_109718 crossref_primary_10_1007_s11042_023_15862_4 crossref_primary_10_3390_app9020237 crossref_primary_10_1109_TITS_2016_2612705 crossref_primary_10_1016_j_engappai_2017_06_017 crossref_primary_10_1007_s11265_024_01941_8 crossref_primary_10_1109_TCSVT_2016_2556538 crossref_primary_10_1007_s11760_018_1364_z crossref_primary_10_1016_j_engappai_2025_111979 crossref_primary_10_1016_j_jvcir_2021_103195 crossref_primary_10_1587_transinf_2016EDL8053 crossref_primary_10_1007_s00138_021_01181_x crossref_primary_10_1109_ACCESS_2018_2803160 crossref_primary_10_1007_s11042_020_09493_2 crossref_primary_10_3390_s24010172 crossref_primary_10_1109_ACCESS_2018_2840329 crossref_primary_10_1109_TMM_2021_3082687 crossref_primary_10_3390_s20082180 crossref_primary_10_1016_j_imavis_2019_103867 crossref_primary_10_1007_s10846_018_0840_6 crossref_primary_10_3390_jimaging11060177 crossref_primary_10_1109_TCSVT_2019_2905373 crossref_primary_10_1007_s11042_020_08848_z crossref_primary_10_1016_j_knosys_2021_106990 crossref_primary_10_1109_TIP_2019_2957927 crossref_primary_10_1016_j_isprsjprs_2018_04_003 crossref_primary_10_1016_j_patrec_2017_08_030 crossref_primary_10_1109_TPAMI_2022_3221079 crossref_primary_10_1109_ACCESS_2023_3297265 crossref_primary_10_4018_IJIRR_356489 crossref_primary_10_1016_j_patcog_2018_03_007 crossref_primary_10_1007_s11042_018_6387_5 crossref_primary_10_1016_j_compeleceng_2018_02_013 crossref_primary_10_3390_ijgi9020098 crossref_primary_10_1007_s10489_021_02798_1 crossref_primary_10_3390_s23135977 crossref_primary_10_1016_j_neucom_2023_126285 crossref_primary_10_4316_AECE_2023_02011 crossref_primary_10_3390_app11199202 crossref_primary_10_1109_TIP_2020_3038371 crossref_primary_10_1109_ACCESS_2024_3395786 crossref_primary_10_1109_TITS_2015_2465296 crossref_primary_10_1109_ACCESS_2019_2899105 crossref_primary_10_1109_JSTARS_2017_2694890 crossref_primary_10_1109_TIP_2019_2942686 crossref_primary_10_1049_iet_rsn_2020_0224 crossref_primary_10_1109_TIP_2019_2922095 crossref_primary_10_1109_TIM_2022_3192294 crossref_primary_10_1016_j_neucom_2022_10_080 crossref_primary_10_1016_j_dt_2021_10_007 crossref_primary_10_1109_LGRS_2019_2936173 crossref_primary_10_1007_s11042_019_08498_w crossref_primary_10_3390_s16111904 crossref_primary_10_1002_ecs2_2992 crossref_primary_10_1016_j_compag_2021_106404 crossref_primary_10_1002_spe_3089 crossref_primary_10_1109_TIP_2017_2762591 crossref_primary_10_3390_app12189171 crossref_primary_10_3390_rs16061081 crossref_primary_10_1016_j_compenvurbsys_2020_101481 crossref_primary_10_1109_TITS_2015_2433019 crossref_primary_10_1109_TNNLS_2021_3105143 crossref_primary_10_1109_TIM_2022_3213016 crossref_primary_10_1016_j_patcog_2022_108847 crossref_primary_10_1631_FITEE_1601873 crossref_primary_10_1155_2015_148081 crossref_primary_10_1109_TCYB_2017_2776977 crossref_primary_10_1109_TITS_2018_2799228 crossref_primary_10_1109_ACCESS_2022_3150988 crossref_primary_10_1049_cvi2_12081 crossref_primary_10_3390_app13031461 crossref_primary_10_4081_jae_2024_1641 crossref_primary_10_1016_j_autcon_2019_102894 crossref_primary_10_1109_TIP_2016_2554321 crossref_primary_10_1016_j_patrec_2018_01_004 crossref_primary_10_1016_j_neucom_2019_03_004 crossref_primary_10_1109_ACCESS_2019_2953276 crossref_primary_10_1016_j_infrared_2021_103965 crossref_primary_10_1109_TNNLS_2020_3004819 crossref_primary_10_1109_TPAMI_2021_3119563 crossref_primary_10_3390_s16020263 crossref_primary_10_1109_TITS_2022_3206709 crossref_primary_10_1134_S0361768817040053 crossref_primary_10_3390_s21217267 crossref_primary_10_1007_s00530_022_00929_3 crossref_primary_10_1007_s11042_020_09616_9 crossref_primary_10_1109_TIV_2021_3133849 crossref_primary_10_1088_1757_899X_428_1_012030 crossref_primary_10_1016_j_neucom_2021_08_136 crossref_primary_10_1109_ACCESS_2019_2924947 crossref_primary_10_1016_j_patcog_2024_110704 crossref_primary_10_1145_3460770 crossref_primary_10_1371_journal_pone_0269198 crossref_primary_10_1049_joe_2018_8284 crossref_primary_10_1016_j_patrec_2015_07_043 crossref_primary_10_1007_s10278_023_00774_4 crossref_primary_10_1007_s12559_021_09898_7 crossref_primary_10_1186_s41074_018_0048_5 crossref_primary_10_3390_s21041232 crossref_primary_10_1016_j_cviu_2017_05_010 crossref_primary_10_1007_s11042_017_5530_z crossref_primary_10_1016_j_cviu_2017_05_015 crossref_primary_10_1016_j_cviu_2019_102883 crossref_primary_10_3390_rs16162971 crossref_primary_10_1109_ACCESS_2019_2929182 crossref_primary_10_1016_j_ymssp_2020_107181 crossref_primary_10_1007_s10044_017_0625_8 crossref_primary_10_1145_3595379 crossref_primary_10_1007_s11042_019_08201_z crossref_primary_10_1007_s11263_016_0960_z crossref_primary_10_1109_ACCESS_2020_2967414 crossref_primary_10_1109_TCYB_2019_2916158 crossref_primary_10_1109_TCSVT_2016_2607378 crossref_primary_10_1007_s40313_015_0202_6 crossref_primary_10_1109_TNSE_2021_3139335 crossref_primary_10_1109_TPAMI_2017_2700460 crossref_primary_10_1007_s10489_023_04747_6 crossref_primary_10_1016_j_image_2019_115764 crossref_primary_10_1049_iet_ipr_2018_6209 crossref_primary_10_3390_s21175851 crossref_primary_10_1016_j_scs_2020_102600 crossref_primary_10_3390_s21041254 crossref_primary_10_1016_j_neucom_2017_01_084 crossref_primary_10_3390_s25020363 crossref_primary_10_1109_TCSVT_2021_3138851 crossref_primary_10_1134_S1054661817040149 crossref_primary_10_1007_s12652_025_04956_6 crossref_primary_10_1016_j_powtec_2024_119437 crossref_primary_10_1007_s11042_019_08578_x crossref_primary_10_1016_j_patcog_2021_108373 crossref_primary_10_1109_ACCESS_2020_3003751 crossref_primary_10_1109_TVLSI_2018_2808104 crossref_primary_10_1007_s00371_021_02280_6 crossref_primary_10_1088_1742_6596_1802_3_032075 crossref_primary_10_1016_j_ijbiomac_2025_139519 crossref_primary_10_1007_s13735_021_00212_7 crossref_primary_10_1016_j_jpdc_2017_05_011 crossref_primary_10_1016_j_neucom_2019_04_001 crossref_primary_10_1007_s11263_019_01237_6 crossref_primary_10_1080_21642583_2021_1901156 crossref_primary_10_1109_TCSI_2021_3098053 crossref_primary_10_3390_s18103415 crossref_primary_10_3390_app9235172 crossref_primary_10_1109_MSEC_2018_2875851 crossref_primary_10_1016_j_jvcir_2021_103189 crossref_primary_10_1016_j_neucom_2024_128357 crossref_primary_10_1109_TITS_2021_3126231 crossref_primary_10_1007_s11042_019_08080_4 crossref_primary_10_3390_jsan10030042 crossref_primary_10_1007_s00521_023_08239_z crossref_primary_10_1109_TMM_2020_3020691 crossref_primary_10_1016_j_neucom_2020_05_019 crossref_primary_10_1016_j_compmedimag_2017_07_003 crossref_primary_10_1016_j_cogr_2025_04_001 crossref_primary_10_1007_s00500_021_05912_0 crossref_primary_10_1007_s40815_016_0172_2 crossref_primary_10_1109_ACCESS_2019_2895376 crossref_primary_10_1049_iet_its_2019_0376 crossref_primary_10_1109_TIP_2017_2694224 crossref_primary_10_1007_s10489_022_03217_9 crossref_primary_10_1016_j_neucom_2017_01_043 crossref_primary_10_1007_s11042_021_10863_7 crossref_primary_10_53525_jster_1469697 crossref_primary_10_3390_jmmp9090297 crossref_primary_10_1109_TITS_2018_2801560
Cites_doi	10.1109/CVPR.2010.5539906 10.1364/JOSAA.2.001160 10.1109/5.52200 10.1109/ICCV.2007.4409092 10.1109/ICIP.1996.559512 10.1109/34.93808 10.1109/34.192463 10.1109/5.726791 10.1109/CVPR.2001.990517 10.1364/JOSAA.4.002379 10.1109/TPAMI.2011.155 10.1109/TASSP.1987.1165137 10.1088/0954-898X/5/4/006 10.1016/0042-6989(78)90232-8 10.1016/0042-6989(73)90201-0 10.1023/B:VISI.0000029664.99615.94 10.1109/34.730558 10.1007/s11263-009-0275-4 10.1109/TPAMI.2009.109 10.1109/CVPR.2005.310 10.1109/IVS.2010.5548145 10.1109/12.210173 10.1023/A:1011113216584 10.1109/CVPR.2012.6248017 10.1016/0042-6989(82)90113-4 10.1109/ICVS.2006.9 10.5244/C.23.91 10.1109/CVPR.2003.1211479 10.1103/PhysRevLett.73.814 10.2307/2310428 10.1109/CVPR.2011.5995668 10.1364/JOSAA.7.000923 10.1007/BF00288907 10.1007/BF00318371 10.1023/A:1008162616689 10.1177/0278364909341884 10.1109/ICCV.2007.4408860 10.1109/CVPR.2010.5540226 10.1007/s11263-007-0095-3 10.1109/TCOM.1983.1095851 10.1109/34.49051 10.1214/aos/1016218223 10.1016/0262-8856(92)90015-U 10.1038/14819 10.1113/jphysiol.1968.sp008455 10.1109/ICCV.1990.139492 10.1109/CVPR.2005.188 10.1109/CVPR.2005.177 10.1109/CVPR.2007.383134 10.1109/TPAMI.2009.144 10.1364/JOSAA.2.000284 10.1109/CVPR.2000.854739 10.1109/CVPR.2009.5206638 10.5244/C.24.68 10.1007/s11263-005-6644-8 10.1109/ICCV.2009.5459207 10.1109/ICCV.2009.5459205 10.1109/CVPR.1996.517092 10.1109/CVPR.2010.5540102 10.1109/ICCV.1999.790410 10.1109/TPAMI.2009.167
ContentType	Journal Article
Copyright	2015 INIST-CNRS Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Aug 2014
Copyright_xml	– notice: 2015 INIST-CNRS – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Aug 2014
DBID	97E RIA RIE AAYXX CITATION IQODW NPM 7SC 7SP 8FD JQ2 L7M L~C L~D F28 FR3 7X8
DOI	10.1109/TPAMI.2014.2300479
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Pascal-Francis PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional ANTE: Abstracts in New Technology & Engineering Engineering Research Database MEDLINE - Academic
DatabaseTitle	CrossRef PubMed Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional Engineering Research Database ANTE: Abstracts in New Technology & Engineering MEDLINE - Academic
DatabaseTitleList	Technology Research Database PubMed Technology Research Database MEDLINE - Academic
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science Applied Sciences
EISSN	2160-9292 1939-3539
EndPage	1545
ExternalDocumentID	3378272931 26353336 28720933 10_1109_TPAMI_2014_2300479 6714453
Genre	orig-research Research Support, U.S. Gov't, Non-P.H.S Research Support, Non-U.S. Gov't Journal Article
GroupedDBID	--- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E 9M8 AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ADRHT AENEX AETEA AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P FA8 HZ~ H~9 IBMZZ ICLAB IEDLZ IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNI RNS RXW RZB TAE TN5 UHB VH1 XJT ~02 AAYXX CITATION AAYOK IQODW RIG NPM 7SC 7SP 8FD JQ2 L7M L~C L~D F28 FR3 7X8
ID	FETCH-LOGICAL-c414t-e562498397eb4a078dbdd7f43b74dff173f5244086efc235ba655535dbd60d7d3
IEDL.DBID	RIE
ISICitedReferencesCount	1423
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000340191900004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0162-8828
IngestDate	Thu Oct 02 12:10:40 EDT 2025 Sat Sep 27 20:59:22 EDT 2025 Mon Jun 30 04:29:28 EDT 2025 Mon Jul 21 05:51:17 EDT 2025 Wed Apr 02 07:46:48 EDT 2025 Sat Nov 29 05:15:56 EST 2025 Tue Nov 18 21:39:56 EST 2025 Wed Aug 27 02:47:52 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	8
Keywords	Bottleneck Computer vision Image recognition Image resolution Statistical analysis Image processing Visual features pedestrian detection Pedestrian Real time image pyramids Narrow band Texture Multiresolution analysis Multiple image Visual system Extrapolation Surveillance natural image statistics real-time systems Object detection Fine grain structure Natural scenes Passband
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html CC BY 4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c414t-e562498397eb4a078dbdd7f43b74dff173f5244086efc235ba655535dbd60d7d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
PMID	26353336
PQID	1546090086
PQPubID	85458
PageCount	14
ParticipantIDs	proquest_miscellaneous_1711537016 crossref_primary_10_1109_TPAMI_2014_2300479 proquest_miscellaneous_1671504973 pubmed_primary_26353336 proquest_journals_1546090086 ieee_primary_6714453 crossref_citationtrail_10_1109_TPAMI_2014_2300479 pascalfrancis_primary_28720933
PublicationCentury	2000
PublicationDate	2014-08-01
PublicationDateYYYYMMDD	2014-08-01
PublicationDate_xml	– month: 08 year: 2014 text: 2014-08-01 day: 01
PublicationDecade	2010
PublicationPlace	Los Alamitos, CA
PublicationPlace_xml	– name: Los Alamitos, CA – name: United States – name: New York
PublicationTitle	IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev	TPAMI
PublicationTitleAlternate	IEEE Trans Pattern Anal Mach Intell
PublicationYear	2014
Publisher	IEEE IEEE Computer Society The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: IEEE Computer Society – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref57 ref13 ref56 ref12 wojek (ref74) 2008 ref59 ref15 ref14 maffei (ref3) 1973; 13 ref53 ref52 ref11 ref10 zhang (ref48) 2007 ref16 ref19 crowley (ref42) 2002 ref18 ref51 ref50 zhang (ref61) 2008 lin (ref71) 2008 itti (ref17) 1998; 20 ref46 ref45 ref47 ref41 ref44 ref43 agarwal (ref55) 2002 ref7 ref9 ref4 weber (ref54) 2000 ref6 gu (ref58) 2009 ref5 wojek (ref60) 2008 ref35 ref34 ref37 ref36 ref75 ref31 ref30 ochman (ref49) 2005 ref33 ref76 ref2 ref1 ref39 ref38 zhu (ref63) 2006 ref70 krizhevsky (ref26) 2012 ref73 maji (ref72) 2008 ref68 ref67 ref23 ref69 ref25 ref64 ref20 doll r (ref40) 2012 ref66 ref22 riesenhuber (ref24) 1999; 2 ref65 ref21 mallat (ref8) 1989; 11 park (ref77) 2010 ref28 ref27 (ref32) 0 ref29 ref62
References_xml	– ident: ref44 doi: 10.1109/CVPR.2010.5539906 – ident: ref5 doi: 10.1364/JOSAA.2.001160 – ident: ref9 doi: 10.1109/5.52200 – ident: ref37 doi: 10.1109/ICCV.2007.4409092 – ident: ref11 doi: 10.1109/ICIP.1996.559512 – ident: ref12 doi: 10.1109/34.93808 – volume: 11 start-page: 647 year: 1989 ident: ref8 article-title: A Theory for Multiresolution Signal Decomposition: The Wavelet Representation publication-title: IEEE Trans Pattern Analysis and Machine Intelligence doi: 10.1109/34.192463 – year: 2008 ident: ref71 article-title: A Pose-Invariant Descriptor for Human Detection and Segmentation publication-title: Proc 10th European Conf Computer Vision (ECCV) – ident: ref23 doi: 10.1109/5.726791 – ident: ref27 doi: 10.1109/CVPR.2001.990517 – ident: ref7 doi: 10.1364/JOSAA.4.002379 – ident: ref31 doi: 10.1109/TPAMI.2011.155 – ident: ref10 doi: 10.1109/TASSP.1987.1165137 – ident: ref67 doi: 10.1088/0954-898X/5/4/006 – ident: ref34 doi: 10.1016/0042-6989(78)90232-8 – volume: 13 start-page: 1255 year: 1973 ident: ref3 article-title: The Visual Cortex as a Spatial Frequency Analyser publication-title: Vision Research doi: 10.1016/0042-6989(73)90201-0 – year: 0 ident: ref32 – ident: ref25 doi: 10.1023/B:VISI.0000029664.99615.94 – volume: 20 start-page: 1254 year: 1998 ident: ref17 article-title: A Model of Saliency-Based Visual Attention for Rapid Scene Analysis publication-title: IEEE Trans Pattern Analysis and Machine Intelligence doi: 10.1109/34.730558 – ident: ref38 doi: 10.1007/s11263-009-0275-4 – year: 2000 ident: ref54 article-title: Unsupervised Learning of Models for Recognition publication-title: Proc European Conf Computer Vision (ECCV) – ident: ref65 doi: 10.1109/TPAMI.2009.109 – ident: ref47 doi: 10.1109/CVPR.2005.310 – year: 2008 ident: ref60 article-title: Sliding-Windows for Rapid Object Class Localization: A Parallel Technique publication-title: Proc 30th DAGM Symp Pattern Recognition – ident: ref62 doi: 10.1109/IVS.2010.5548145 – ident: ref19 doi: 10.1109/12.210173 – ident: ref51 doi: 10.1023/A:1011113216584 – year: 2012 ident: ref26 article-title: Imagenet Classification with Deep Convolutional Neural Networks publication-title: Proc Advances in Neural Information Processing Systems (NIPS) – ident: ref30 doi: 10.1109/CVPR.2012.6248017 – ident: ref22 doi: 10.1016/0042-6989(82)90113-4 – ident: ref43 doi: 10.1109/ICVS.2006.9 – ident: ref29 doi: 10.5244/C.23.91 – ident: ref56 doi: 10.1109/CVPR.2003.1211479 – year: 2008 ident: ref72 article-title: Classification Using Intersection Kernel SVMs Is Efficient publication-title: Proc IEEE Conf Computer Vision and Pattern Recognition (CVPR) – ident: ref33 doi: 10.1103/PhysRevLett.73.814 – ident: ref68 doi: 10.2307/2310428 – ident: ref45 doi: 10.1109/CVPR.2011.5995668 – ident: ref13 doi: 10.1364/JOSAA.7.000923 – ident: ref2 doi: 10.1007/BF00288907 – ident: ref6 doi: 10.1007/BF00318371 – year: 2008 ident: ref61 article-title: Efficient Scan-Window Based Object Detection Using GPGPU publication-title: Proc Workshop Visual Computer Vision on GPU?s (CVGPU) – ident: ref53 doi: 10.1023/A:1008162616689 – year: 2009 ident: ref58 article-title: Recognition Using Regions publication-title: Proc IEEE Conf Computer Vision and Pattern Recognition (CVPR) – ident: ref66 doi: 10.1177/0278364909341884 – ident: ref50 doi: 10.1109/ICCV.2007.4408860 – ident: ref59 doi: 10.1109/CVPR.2010.5540226 – ident: ref57 doi: 10.1007/s11263-007-0095-3 – ident: ref4 doi: 10.1109/TCOM.1983.1095851 – year: 2010 ident: ref77 article-title: Multiresolution Models for Object Detection publication-title: Proc 11th European Conf Computer Vision (ECCV) – ident: ref41 doi: 10.1109/34.49051 – ident: ref69 doi: 10.1214/aos/1016218223 – ident: ref14 doi: 10.1016/0262-8856(92)90015-U – volume: 2 start-page: 1019 year: 1999 ident: ref24 article-title: Hierarchical Models of Object Recognition in Cortex publication-title: Nature Neuroscience doi: 10.1038/14819 – year: 2002 ident: ref42 article-title: Fast Computation of Characteristic Scale Using a Half-Octave Pyramid publication-title: Proc Fourth Int?l Conf Scale-Space Theories in Computer Vision – ident: ref1 doi: 10.1113/jphysiol.1968.sp008455 – ident: ref18 doi: 10.1109/ICCV.1990.139492 – ident: ref64 doi: 10.1109/CVPR.2005.188 – ident: ref21 doi: 10.1109/CVPR.2005.177 – ident: ref70 doi: 10.1109/CVPR.2007.383134 – ident: ref46 doi: 10.1109/TPAMI.2009.144 – ident: ref15 doi: 10.1364/JOSAA.2.000284 – ident: ref52 doi: 10.1109/CVPR.2000.854739 – ident: ref36 doi: 10.1109/CVPR.2009.5206638 – ident: ref39 doi: 10.5244/C.24.68 – year: 2005 ident: ref49 article-title: Waldboost?Learning for Time Constrained Sequential Detection publication-title: Proc IEEE Conf Computer Vision and Pattern Recognition (CVPR) – year: 2012 ident: ref40 article-title: Crosstalk Cascades for Frame-Rate Pedestrian Detection publication-title: Proc 12th European Conf Computer Vision (ECCV) – ident: ref28 doi: 10.1007/s11263-005-6644-8 – ident: ref73 doi: 10.1109/ICCV.2009.5459207 – year: 2008 ident: ref74 article-title: A Performance Evaluation of Single and Multi-Feature People Detection publication-title: Proc 30th DAGM Symp Pattern Recognition (DAGM) – year: 2002 ident: ref55 article-title: Learning a Sparse Representation for Object Detection publication-title: Proc European Conf Computer Vision (ECCV) – ident: ref75 doi: 10.1109/ICCV.2009.5459205 – ident: ref16 doi: 10.1109/CVPR.1996.517092 – ident: ref76 doi: 10.1109/CVPR.2010.5540102 – ident: ref20 doi: 10.1109/ICCV.1999.790410 – ident: ref35 doi: 10.1109/TPAMI.2009.167 – year: 2006 ident: ref63 article-title: Fast Human Detection Using a Cascade of Histograms of Oriented Gradients publication-title: Proc IEEE Conf Computer Vision and Pattern Recognition (CVPR) – year: 2007 ident: ref48 article-title: Multiple-Instance Pruning for Learning Efficient Cascade Detectors publication-title: Proc Advances in Neural Information Processing Systems (NIPS)
SSID	ssj0014503
Score	2.663328
Snippet	Multi-resolution image features may be approximated via extrapolation from nearby scales, rather than being computed explicitly. This fundamental insight...
SourceID	proquest pubmed pascalfrancis crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1532
SubjectTerms	Accuracy Algorithmics. Computability. Computer arithmetics Algorithms Applied sciences Approximation Approximation methods Artificial intelligence Computation Computer science; control theory; systems Detectors Exact sciences and technology Feature extraction Histograms image pyramids Mathematical analysis natural image statistics Object detection Pattern recognition. Digital image processing. Computational geometry pedestrian detection Pyramids real-time systems Spectra Texture Theoretical computing Visual features Visual task performance Visualization
Title	Fast Feature Pyramids for Object Detection
URI	https://ieeexplore.ieee.org/document/6714453 https://www.ncbi.nlm.nih.gov/pubmed/26353336 https://www.proquest.com/docview/1546090086 https://www.proquest.com/docview/1671504973 https://www.proquest.com/docview/1711537016
Volume	36
WOSCitedRecordID	wos000340191900004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB61FQc4tKUFGmhXQeIEhCbxKz5WLSs4UPZQpL1FfkWqBFm0ySLx75lxsilIUIlbJI9lZ2Ysf2OP5wN4JVwltXNFpq1yGUeMnFVFU2VBM6N0sNIoG8km1PV1tVzqxQ68nd7ChBBi8ll4R5_xLt-v3IaOys6lQvgv2C7sKqWGt1rTjQEXkQUZEQyucAwjtg9kcn1-s7j49JGyuDilPVNNdSoBjDstY7Ey891-FAlWKD3SdKihZqC2-Df2jHvQ_OD_Zn8I-yPWTC8G53gMO6E9goMtj0M6LusjePRbUcJjeD03XZ8SNNysQ7r4uTbfbn2XIrhNP1s6tUmvQh8TuNon8GX-_ubyQzYyKmSOF7zPAqIdrhETqWC5QXTgrfeq4cwq7pumUKwRJXFQy9C4kglrpBCCCRSTuVeePYW9dtWGE0ixlwtOeoQ3nJemtL6yslSWc5t7HCaBYqvX2o3lxon14msdw45c19EsNZmlHs2SwJupz_eh2Ma90sek5Ely1G8Csz_MN7VjbFjS-U0Cp1t71uOC7WpEkjLXFOAl8HJqxqVG9yemDasNyuAIAiMqxe6RUQixmUI3TODZ4Ct3Exhd7vnfJ_4CHtLvDdmFp7DXrzfhDB64H_1tt56hzy-rWfT5X1FB9_Q
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS9xAEB-sFloftNVaY62m0Ke20ST7lX0U7aFUr_dwBd_CfgUEzZVLrtD_vrObXLTQCr4FdpbdzMyyv9mdnR_AR2YKLo3JEqmFSShi5KTIqiJxkighneZK6EA2Icbj4vpaTlbgy_AWxjkXks_ckf8Md_l2Zhb-qOyYC4T_jDyDNUZpnnWvtYY7A8oCDzJiGFzjGEgsn8ik8ng6Obm68Hlc1Cc--6rqvggw7rWEhNrM9ztSoFjxCZKqQR1VHbnF_9Fn2IVGm0-b_yvY6NFmfNK5x2tYcfUWbC6ZHOJ-YW_B-oOyhNvwaaSaNvbgcDF38eT3XN3d2CZGeBt_1_7cJj5zbUjhqt_Aj9HX6el50nMqJIZmtE0c4h0qERUJp6lCfGC1taKiRAtqqyoTpGK5Z6HmrjI5YVpxxhhhKMZTKyzZgdV6VrtdiLGXcYZbBDhoDZVrW2ieC02pTi0OE0G21Gtp-oLjnvfitgyBRyrLYJbSm6XszRLB56HPz67cxqPS217Jg2Sv3wgO_jLf0I7RYe5PcCLYX9qz7JdsUyKW5Kn0IV4EH4ZmXGz-BkXVbrZAGRyBYUwlyCMyAkE2EeiGEbztfOV-Ar3L7f174ofw4nx6dVleXoy_vYOX_le7XMN9WG3nC_cenptf7U0zPwie_weFA_pT
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Fast+Feature+Pyramids+for+Object+Detection&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Dollar%2C+Piotr&rft.au=Appel%2C+Ron&rft.au=Belongie%2C+Serge&rft.au=Perona%2C+Pietro&rft.date=2014-08-01&rft.issn=0162-8828&rft.volume=36&rft.issue=8&rft.spage=1532&rft.epage=1545&rft_id=info:doi/10.1109%2FTPAMI.2014.2300479&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon