Height estimation from single aerial images using a deep convolutional encoder-decoder network
Extracting 3D information from aerial images is an important and still challenging topic in photogrammetry and remote sensing. Height estimation from only a single aerial image is an ambiguous and ill-posed problem. To address this challenging problem, in this paper, an architecture based on a deep...
Saved in:
| Published in: | ISPRS journal of photogrammetry and remote sensing Vol. 149; pp. 50 - 66 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier B.V
01.03.2019
|
| Subjects: | |
| ISSN: | 0924-2716, 1872-8235 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Extracting 3D information from aerial images is an important and still challenging topic in photogrammetry and remote sensing. Height estimation from only a single aerial image is an ambiguous and ill-posed problem. To address this challenging problem, in this paper, an architecture based on a deep convolutional neural network (CNN) is proposed in order to estimate the height values from a single aerial image. Methodologies for data preprocessing, selection of training data as well as data augmentation are presented. Subsequently, a deep CNN architecture is proposed consisting of encoding and decoding steps. In the encoding part, a deep residual learning is employed for extracting the local and global features. An up-sampling approach is proposed in the decoding part for increasing the output resolution and skip connections are employed in each scale to modify the estimated height values at the object boundaries. Finally, a post-processing approach is proposed to merge the predicted height image patches and generate a seamless continuous height map. The quantitative evaluation of the proposed approaches on the ISPRS datasets indicates relative and root mean square errors of approximately 0.9 m and 3.2 m, respectively. |
|---|---|
| AbstractList | Extracting 3D information from aerial images is an important and still challenging topic in photogrammetry and remote sensing. Height estimation from only a single aerial image is an ambiguous and ill-posed problem. To address this challenging problem, in this paper, an architecture based on a deep convolutional neural network (CNN) is proposed in order to estimate the height values from a single aerial image. Methodologies for data preprocessing, selection of training data as well as data augmentation are presented. Subsequently, a deep CNN architecture is proposed consisting of encoding and decoding steps. In the encoding part, a deep residual learning is employed for extracting the local and global features. An up-sampling approach is proposed in the decoding part for increasing the output resolution and skip connections are employed in each scale to modify the estimated height values at the object boundaries. Finally, a post-processing approach is proposed to merge the predicted height image patches and generate a seamless continuous height map. The quantitative evaluation of the proposed approaches on the ISPRS datasets indicates relative and root mean square errors of approximately 0.9 m and 3.2 m, respectively. |
| Author | Amirkolaee, Hamed Amini Arefi, Hossein |
| Author_xml | – sequence: 1 givenname: Hamed Amini surname: Amirkolaee fullname: Amirkolaee, Hamed Amini – sequence: 2 givenname: Hossein surname: Arefi fullname: Arefi, Hossein email: hossein.arefi@ut.ac.ir |
| BookMark | eNqNkD1PwzAQhi1UJNrCb8AjS4I_ktgZGKoKKFIlFlixUvtSHNI42GkR_x63RQwsIJ11lv0-J90zQaPOdYDQJSUpJbS4blIbeh-aeFJGaJkSGoufoDGVgiWS8XyExqRkWcIELc7QJISGEELzQo7RywLs-nXAEAa7qQbrOlx7t8HBdusWcAXeVi2OX2sIeLt_xRU2AD3Wrtu5drtHYgI67Qz4xMCh4w6GD-ffztFpXbUBLr77FD3f3T7NF8ny8f5hPlsmmmdySERFNa8N4yvDZJ6VmTCCslUhqJa6yFeCFKYkuZYZXZXATZbFq6gZ54Zm3JR8iq6Oc3vv3rdxGbWxQUPbVh24bVCMMUpyTqSMUXGMau9C8FCr3sf9_KeiRO2Nqkb9GFV7o4rQWDySN79IbYeDs8FXtv0HPzvyEE3sLHgVtI3iwFgPelDG2T9nfAH2jJv2 |
| CitedBy_id | crossref_primary_10_1109_LGRS_2024_3461791 crossref_primary_10_3390_rs15153786 crossref_primary_10_1016_j_inffus_2024_102358 crossref_primary_10_1109_TGRS_2023_3321255 crossref_primary_10_3390_rs14092252 crossref_primary_10_1109_TRO_2025_3562048 crossref_primary_10_1093_nsr_nwz058 crossref_primary_10_1109_LGRS_2022_3222457 crossref_primary_10_1016_j_rineng_2024_103436 crossref_primary_10_1109_TGRS_2023_3311764 crossref_primary_10_3390_ijgi13030062 crossref_primary_10_1109_TGRS_2025_3591180 crossref_primary_10_1016_j_isprsjprs_2023_01_003 crossref_primary_10_3390_rs16060958 crossref_primary_10_1016_j_isprsjprs_2021_11_012 crossref_primary_10_1016_j_isprsjprs_2022_11_014 crossref_primary_10_1109_ACCESS_2021_3122894 crossref_primary_10_1109_JSTARS_2023_3297710 crossref_primary_10_3390_ijgi11070385 crossref_primary_10_3390_rs11192219 crossref_primary_10_3390_rs14143450 crossref_primary_10_1109_LGRS_2021_3090470 crossref_primary_10_1080_01431161_2022_2135410 crossref_primary_10_1016_j_agrformet_2020_108234 crossref_primary_10_1109_TGRS_2023_3290232 crossref_primary_10_1016_j_radi_2021_07_024 crossref_primary_10_1186_s13007_024_01171_w crossref_primary_10_3390_rs17030496 crossref_primary_10_1109_TGRS_2023_3295802 crossref_primary_10_1109_JSTARS_2025_3602630 crossref_primary_10_3390_rs12172719 crossref_primary_10_1016_j_jag_2023_103311 crossref_primary_10_1016_j_jag_2023_103399 crossref_primary_10_1016_j_jag_2025_104443 crossref_primary_10_1016_j_jdeveco_2024_103322 crossref_primary_10_3390_rs13122417 crossref_primary_10_3390_rs17111915 crossref_primary_10_1016_j_isprsjprs_2021_03_024 crossref_primary_10_1016_j_scs_2024_105733 crossref_primary_10_1016_j_inffus_2025_103307 crossref_primary_10_1109_TGRS_2023_3266477 crossref_primary_10_1016_j_asoc_2022_108870 crossref_primary_10_1016_j_jag_2024_103809 crossref_primary_10_1109_ACCESS_2025_3570629 crossref_primary_10_1109_LGRS_2021_3126767 crossref_primary_10_1016_j_isprsjprs_2025_06_010 crossref_primary_10_1080_2150704X_2021_1880659 crossref_primary_10_1109_LGRS_2019_2947783 crossref_primary_10_1109_TGRS_2022_3197409 crossref_primary_10_1109_JSTARS_2020_3043442 crossref_primary_10_1016_j_aei_2020_101169 crossref_primary_10_3390_s21072272 crossref_primary_10_3390_rs17071297 crossref_primary_10_1109_TGRS_2022_3176670 crossref_primary_10_1080_2150704X_2023_2283901 crossref_primary_10_1016_j_uclim_2023_101736 crossref_primary_10_1109_TGRS_2022_3177796 crossref_primary_10_3390_rs16020295 crossref_primary_10_1109_LGRS_2020_2976485 crossref_primary_10_1016_j_landurbplan_2022_104624 crossref_primary_10_1109_JSTARS_2025_3582823 crossref_primary_10_3390_rs17142529 crossref_primary_10_1016_j_rse_2021_112590 crossref_primary_10_1016_j_isprsjprs_2025_07_010 crossref_primary_10_3390_rs14071567 crossref_primary_10_1016_j_isprsjprs_2025_06_022 crossref_primary_10_1109_JSTARS_2025_3567064 crossref_primary_10_1093_pnasnexus_pgad076 crossref_primary_10_3390_s23198162 crossref_primary_10_1016_j_isprsjprs_2021_03_008 crossref_primary_10_3390_s23136186 crossref_primary_10_3390_rs12223833 crossref_primary_10_1109_TGRS_2024_3358397 crossref_primary_10_1109_LGRS_2024_3374526 crossref_primary_10_1016_j_isprsjprs_2020_06_004 crossref_primary_10_1016_j_isprsjprs_2024_03_023 crossref_primary_10_1109_TIM_2025_3593596 crossref_primary_10_1109_LGRS_2020_3019252 crossref_primary_10_1080_01431161_2020_1742944 crossref_primary_10_1016_j_cities_2019_102481 crossref_primary_10_1134_S0001433820120427 crossref_primary_10_3390_rs13214434 crossref_primary_10_1080_01431161_2020_1767821 crossref_primary_10_1080_01431161_2023_2251185 crossref_primary_10_3390_rs14215392 crossref_primary_10_1109_TGRS_2022_3171407 crossref_primary_10_1016_j_rse_2022_113014 |
| Cites_doi | 10.3758/BF03211716 10.1177/0278364914549607 10.3390/rs8040329 10.1109/34.308479 10.1109/3DV.2016.32 10.1109/LGRS.2018.2806945 10.1007/978-3-319-24574-4_28 10.3390/s90100568 10.1109/CVPR.2017.699 10.1109/CVPR.2015.7298761 10.1109/CVPR.2017.238 10.1007/s11263-007-0071-y 10.1109/IDAACS.2017.8095172 10.1023/B:SUPE.0000020178.66165.f3 10.1111/j.1477-9730.2006.00383.x 10.1155/2017/3296874 10.1109/TPAMI.2015.2505283 10.1109/ICCV.2007.4408828 10.1016/j.geomorph.2012.08.021 10.1109/LGRS.2012.2195471 10.1109/TGRS.2016.2616585 10.1007/s11263-015-0816-y |
| ContentType | Journal Article |
| Copyright | 2019 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS) |
| Copyright_xml | – notice: 2019 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS) |
| DBID | AAYXX CITATION 7S9 L.6 |
| DOI | 10.1016/j.isprsjprs.2019.01.013 |
| DatabaseName | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Geography Engineering |
| EISSN | 1872-8235 |
| EndPage | 66 |
| ExternalDocumentID | 10_1016_j_isprsjprs_2019_01_013 S0924271619300139 |
| GroupedDBID | --K --M .~1 0R~ 1B1 1RT 1~. 1~5 29J 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABJNI ABMAC ABQEM ABQYD ABXDB ABYKQ ACDAQ ACGFS ACLVX ACNNM ACRLP ACSBN ACZNC ADBBV ADEZE ADJOM ADMUD AEBSH AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG ATOGT AVWKF AXJTR AZFZN BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HMA HVGLF HZ~ H~9 IHE IMUCA J1W KOM LY3 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SDF SDG SEP SES SEW SPC SPCBC SSE SSV SSZ T5K T9H WUQ ZMT ~02 ~G- 9DU AAHBH AATTM AAXKI AAYWO AAYXX ABDPE ABUFD ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD 7S9 L.6 |
| ID | FETCH-LOGICAL-c348t-7a1c3fd23bd2854947d712b671c8c65b706d905c841b9e3d44c847f233d143d93 |
| ISICitedReferencesCount | 101 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000461535600005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0924-2716 |
| IngestDate | Wed Oct 01 14:33:50 EDT 2025 Sat Nov 29 05:55:02 EST 2025 Tue Nov 18 22:37:00 EST 2025 Fri Feb 23 02:28:02 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Height image Digital aerial image Decoder Convolutional neural network Encoder |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c348t-7a1c3fd23bd2854947d712b671c8c65b706d905c841b9e3d44c847f233d143d93 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PQID | 2221053088 |
| PQPubID | 24069 |
| PageCount | 17 |
| ParticipantIDs | proquest_miscellaneous_2221053088 crossref_primary_10_1016_j_isprsjprs_2019_01_013 crossref_citationtrail_10_1016_j_isprsjprs_2019_01_013 elsevier_sciencedirect_doi_10_1016_j_isprsjprs_2019_01_013 |
| PublicationCentury | 2000 |
| PublicationDate | March 2019 2019-03-00 20190301 |
| PublicationDateYYYYMMDD | 2019-03-01 |
| PublicationDate_xml | – month: 03 year: 2019 text: March 2019 |
| PublicationDecade | 2010 |
| PublicationTitle | ISPRS journal of photogrammetry and remote sensing |
| PublicationYear | 2019 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Saxena, A., Schulte, J., Ng, A.Y., 2007a. Depth Estimation Using Monocular and Stereo Cues, IJCAI. Pfister, Charles, Zisserman (b0155) 2015 Wang, Shen, Lin, Cohen, Price, Yuille (b0240) 2015 Saxena, Chung, Ng (b0195) 2008; 76 Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N., 2016. Deeper depth prediction with fully convolutional residual networks. In: 3D Vision (3DV), 2016 Fourth International Conference on. IEEE, pp. 239–248. Batra, D., Saxena, A., 2012. Learning the right model: Efficient max-margin learning in laplacian crfs. In: Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, pp. 2136–2143. Eigen, Fergus (b0035) 2015 He, Zhang, Ren, Sun (b0065) 2016 Ladicky, Shi, Pollefeys (b0095) 2014 Vedaldi, Lenc (b0230) 2015 Arefi, Hahn (b0005) 2005; 36 Carrio, A., Sampedro, C., Rodriguez-Ramos, A., Campoy, P., 2017. A review of deep learning methods and applications for unmanned aerial vehicles. J. Sens. Saxena, A., Sun, M., Ng, A.Y., 2007b. Learning 3-d scene structure from a single still image. In: Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on. IEEE, pp. 1–8. Lenz, Lee, Saxena (b0110) 2015; 34 Godard, C., Mac Aodha, O., Brostow, G.J., 2016. Unsupervised monocular depth estimation with left-right consistency. In: CVPR, vol. 2, No. 6, p. 7. Kuznietsov, Y., Stückler, J., Leibe, B., 2017. Semi-Supervised Deep Learning for Monocular Depth Map Prediction. arXiv preprint arXiv:1702.02706. de Vries, Kappers, Koenderink (b0025) 1993; 53 Liu, Shen, Lin, Reid (b0120) 2016; 38 Mou, L., Zhu, X. X., 2018. IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Network, 2018, arXiv preprint arXiv:1802.10249. Huang, Liu, Maaten, Weinberger (b0060) 2017; 2017 Volpi, Tuia (b0235) 2017; 55 Nayar, Nakagawa (b0145) 1994; 16 Simonyan, Zisserman (b0210) 2015 Roy, Todorovic (b0175) 2016 Krizhevsky, A., Hinton, G., 2009. Learning multiple layers of features from tiny images, vol. 1, No. 4, p. 7. Technical report, University of Toronto. Ronneberger, O., Fischer, P., Brox, T., 2015. U-net: Convolutional networks for biomedical image segmentation. In: Paper presented at International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, pp. 234–241. Westoby, Brasington, Glasser, Hambrey, Reynolds (b0245) 2012; 179 Chen, Qin, Lin, Liu, Zhan (b0020) 2013; 10 Xu, C., Yang, J., Lai, H., Gao, J., Shen, L., Yan, S., 2017. UP-CNN: un-pooling augmented convolutional neural network. Pattern Recognition Letters. Szegedy, Liu, Jia, Sermanet, Reed, Anguelov, Erhan, Vanhoucke, Rabinovich (b0220) 2015 Ghamisi, Yokoya (b0050) 2018; 15 Liu, Salzmann, He (b0125) 2014 Sansoni, Trebeschi, Docchio (b0185) 2009; 9 Eigen, Puhrsch, Fergus (b0040) 2014 Turchenko, V., Chalmers, E., Luczak, A., 2017. A Deep Convolutional Auto-Encoder with Pooling-Unpooling Layers in Caffe. arXiv preprint arXiv:1701.04949. Srivastava, Volpi, Tuia (b0215) 2017 Rajabi, Blais (b0160) 2004; 28 Zhu, J., Ma, R., 2016. Real-Time Depth Estimation from 2D Images, available at: <http://cs231n.stanford.edu/reports/2016/pdfs/407_Report.pdf>. Niemeyer, Rottensteiner, Soergel (b0150) 2013 Kim, Park, Sohn, Lin (b0075) 2016 Remondino, El-Hakim (b0165) 2006; 21 Russakovsky, Deng, Su, Krause, Satheesh, Ma, Huang, Karpathy, Khosla, Bernstein (b0180) 2015; 115 Garg, Carneiro, Reid (b0045) 2016 Karsch, Liu, Kang (b0070) 2012 Long, Shelhamer, Darrell (b0130) 2015 Mikolov, Sutskever, Chen, Corrado, Dean (b0135) 2013 Li, Shen, Dai, van den Hengel, He (b0115) 2015 Saxena, Chung, Ng (b0190) 2006 Krizhevsky, Sutskever, Hinton (b0085) 2012 Längkvist, Kiselev, Alirezaie, Loutfi (b0105) 2016; 8 Dosovitskiy, A., Springenberg, J.T., Brox, T., 2015. Learning to generate chairs with convolutional neural networks. In: Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on. IEEE, pp. 1538–1546. Zhuo, Salzmann, He, Liu (b0265) 2015 Yu, F., Koltun, V., 2015. “Multi-scale context aggregation by dilated convolutions”. arXiv preprint arXiv:1511.07122. Kim (10.1016/j.isprsjprs.2019.01.013_b0075) 2016 Westoby (10.1016/j.isprsjprs.2019.01.013_b0245) 2012; 179 Chen (10.1016/j.isprsjprs.2019.01.013_b0020) 2013; 10 Wang (10.1016/j.isprsjprs.2019.01.013_b0240) 2015 Garg (10.1016/j.isprsjprs.2019.01.013_b0045) 2016 10.1016/j.isprsjprs.2019.01.013_b0200 10.1016/j.isprsjprs.2019.01.013_b0205 Russakovsky (10.1016/j.isprsjprs.2019.01.013_b0180) 2015; 115 10.1016/j.isprsjprs.2019.01.013_b0080 Krizhevsky (10.1016/j.isprsjprs.2019.01.013_b0085) 2012 Liu (10.1016/j.isprsjprs.2019.01.013_b0120) 2016; 38 Remondino (10.1016/j.isprsjprs.2019.01.013_b0165) 2006; 21 Pfister (10.1016/j.isprsjprs.2019.01.013_b0155) 2015 Saxena (10.1016/j.isprsjprs.2019.01.013_b0195) 2008; 76 Ladicky (10.1016/j.isprsjprs.2019.01.013_b0095) 2014 Eigen (10.1016/j.isprsjprs.2019.01.013_b0040) 2014 Rajabi (10.1016/j.isprsjprs.2019.01.013_b0160) 2004; 28 10.1016/j.isprsjprs.2019.01.013_b0055 10.1016/j.isprsjprs.2019.01.013_b0255 Zhuo (10.1016/j.isprsjprs.2019.01.013_b0265) 2015 10.1016/j.isprsjprs.2019.01.013_b0015 Sansoni (10.1016/j.isprsjprs.2019.01.013_b0185) 2009; 9 10.1016/j.isprsjprs.2019.01.013_b0170 10.1016/j.isprsjprs.2019.01.013_b0250 10.1016/j.isprsjprs.2019.01.013_b0010 Eigen (10.1016/j.isprsjprs.2019.01.013_b0035) 2015 Niemeyer (10.1016/j.isprsjprs.2019.01.013_b0150) 2013 10.1016/j.isprsjprs.2019.01.013_b0090 Simonyan (10.1016/j.isprsjprs.2019.01.013_b0210) 2015 Ghamisi (10.1016/j.isprsjprs.2019.01.013_b0050) 2018; 15 Lenz (10.1016/j.isprsjprs.2019.01.013_b0110) 2015; 34 Long (10.1016/j.isprsjprs.2019.01.013_b0130) 2015 Mikolov (10.1016/j.isprsjprs.2019.01.013_b0135) 2013 10.1016/j.isprsjprs.2019.01.013_b0100 10.1016/j.isprsjprs.2019.01.013_b0225 He (10.1016/j.isprsjprs.2019.01.013_b0065) 2016 Längkvist (10.1016/j.isprsjprs.2019.01.013_b0105) 2016; 8 Li (10.1016/j.isprsjprs.2019.01.013_b0115) 2015 10.1016/j.isprsjprs.2019.01.013_b0140 10.1016/j.isprsjprs.2019.01.013_b0260 Vedaldi (10.1016/j.isprsjprs.2019.01.013_b0230) 2015 Arefi (10.1016/j.isprsjprs.2019.01.013_b0005) 2005; 36 Volpi (10.1016/j.isprsjprs.2019.01.013_b0235) 2017; 55 Karsch (10.1016/j.isprsjprs.2019.01.013_b0070) 2012 Szegedy (10.1016/j.isprsjprs.2019.01.013_b0220) 2015 de Vries (10.1016/j.isprsjprs.2019.01.013_b0025) 1993; 53 Huang (10.1016/j.isprsjprs.2019.01.013_b0060) 2017; 2017 Nayar (10.1016/j.isprsjprs.2019.01.013_b0145) 1994; 16 Srivastava (10.1016/j.isprsjprs.2019.01.013_b0215) 2017 10.1016/j.isprsjprs.2019.01.013_b0030 Saxena (10.1016/j.isprsjprs.2019.01.013_b0190) 2006 Liu (10.1016/j.isprsjprs.2019.01.013_b0125) 2014 Roy (10.1016/j.isprsjprs.2019.01.013_b0175) 2016 |
| References_xml | – reference: Krizhevsky, A., Hinton, G., 2009. Learning multiple layers of features from tiny images, vol. 1, No. 4, p. 7. Technical report, University of Toronto. – volume: 36 start-page: 120 year: 2005 end-page: 125 ident: b0005 article-title: A morphological reconstruction algorithm for separating off-terrain points from terrain points in laser scanning data publication-title: Int. Arch. Photogram., Remote Sens. Spatial Inform. Sci. – reference: Turchenko, V., Chalmers, E., Luczak, A., 2017. A Deep Convolutional Auto-Encoder with Pooling-Unpooling Layers in Caffe. arXiv preprint arXiv:1701.04949. – reference: Saxena, A., Sun, M., Ng, A.Y., 2007b. Learning 3-d scene structure from a single still image. In: Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on. IEEE, pp. 1–8. – volume: 55 start-page: 881 year: 2017 end-page: 893 ident: b0235 article-title: Dense semantic labeling of subdecimeter resolution images with convolutional neural networks publication-title: IEEE Trans. Geosci. Remote Sens. – reference: Batra, D., Saxena, A., 2012. Learning the right model: Efficient max-margin learning in laplacian crfs. In: Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, pp. 2136–2143. – volume: 10 start-page: 145 year: 2013 end-page: 149 ident: b0020 article-title: DEM densification using perspective shape from shading through multispectral imagery publication-title: IEEE Geosci. Remote Sens. Lett. – start-page: 5173 year: 2017 end-page: 5176 ident: b0215 article-title: Joint height estimation and semantic labeling of monocular aerial images with CNNS publication-title: IEEE Int. Geosci. Remote Sens. Symp. (IGARSS) – volume: 2017 start-page: 2261 year: 2017 end-page: 2269 ident: b0060 article-title: Densely connected convolutional networks publication-title: IEEE Conf. Comput. Vision Pattern Recogn. (CVPR) – reference: Kuznietsov, Y., Stückler, J., Leibe, B., 2017. Semi-Supervised Deep Learning for Monocular Depth Map Prediction. arXiv preprint arXiv:1702.02706. – volume: 28 start-page: 193 year: 2004 end-page: 213 ident: b0160 article-title: Optimization of DTM interpolation using SFS with single satellite imagery publication-title: J. Supercomput. – start-page: 689 year: 2015 end-page: 692 ident: b0230 article-title: Matconvnet: convolutional neural networks for matlab publication-title: Proceedings of the 23rd ACM International Conference on Multimedia – reference: Ronneberger, O., Fischer, P., Brox, T., 2015. U-net: Convolutional networks for biomedical image segmentation. In: Paper presented at International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, pp. 234–241. – volume: 8 start-page: 329 year: 2016 ident: b0105 article-title: Classification and segmentation of satellite orthoimagery using convolutional neural networks publication-title: Remote Sens. – start-page: 5506 year: 2016 end-page: 5514 ident: b0175 article-title: Monocular depth estimation using neural regression forest publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 76 start-page: 53 year: 2008 end-page: 69 ident: b0195 article-title: 3-d depth reconstruction from a single still image publication-title: Int. J. Comput. Vision – reference: Saxena, A., Schulte, J., Ng, A.Y., 2007a. Depth Estimation Using Monocular and Stereo Cues, IJCAI. – start-page: 770 year: 2016 end-page: 778 ident: b0065 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 716 year: 2014 end-page: 723 ident: b0125 article-title: Discrete-continuous depth estimation from a single image publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 16 start-page: 824 year: 1994 end-page: 831 ident: b0145 article-title: Shape from focus publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 1 year: 2015 end-page: 9 ident: b0220 article-title: Going deeper with convolutions publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 34 start-page: 705 year: 2015 end-page: 724 ident: b0110 article-title: Deep learning for detecting robotic grasps publication-title: Int. J. Robot. Res. – start-page: 740 year: 2016 end-page: 756 ident: b0045 article-title: Unsupervised CNN for single view depth estimation: geometry to the rescue publication-title: Eur. Conf. Comput. Vision. Springer – start-page: 143 year: 2016 end-page: 159 ident: b0075 article-title: Unified depth prediction and intrinsic image decomposition from a single image via joint convolutional neural fields publication-title: Eur. Conf. Comput. Vision. Springer – reference: Carrio, A., Sampedro, C., Rodriguez-Ramos, A., Campoy, P., 2017. A review of deep learning methods and applications for unmanned aerial vehicles. J. Sens. – reference: Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N., 2016. Deeper depth prediction with fully convolutional residual networks. In: 3D Vision (3DV), 2016 Fourth International Conference on. IEEE, pp. 239–248. – reference: Mou, L., Zhu, X. X., 2018. IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Network, 2018, arXiv preprint arXiv:1802.10249. – start-page: 1119 year: 2015 end-page: 1127 ident: b0115 article-title: Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 139 year: 2013 end-page: 142 ident: b0150 article-title: Classification of urban LiDAR data using conditional random field and random forests publication-title: Urban Remote Sens. Event (JURSE) – volume: 53 start-page: 71 year: 1993 end-page: 80 ident: b0025 article-title: Shape from stereo: a systematic approach using quadratic surfaces publication-title: Attention, Percept., Psychophys. – start-page: 614 year: 2015 end-page: 622 ident: b0265 article-title: Indoor scene structure analysis for single image depth estimation publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 775 year: 2012 end-page: 788 ident: b0070 article-title: Depth extraction from video using non-parametric sampling publication-title: Eur. Conf. Comput. Vision. Springer – volume: 21 start-page: 269 year: 2006 end-page: 291 ident: b0165 article-title: Image-based 3D modelling: a review publication-title: Photogram. Rec. – reference: Yu, F., Koltun, V., 2015. “Multi-scale context aggregation by dilated convolutions”. arXiv preprint arXiv:1511.07122. – reference: Xu, C., Yang, J., Lai, H., Gao, J., Shen, L., Yan, S., 2017. UP-CNN: un-pooling augmented convolutional neural network. Pattern Recognition Letters. – start-page: 3111 year: 2013 end-page: 3119 ident: b0135 article-title: Distributed representations of words and phrases and their compositionality publication-title: Adv. Neural Inform. Process. Syst. – start-page: 3431 year: 2015 end-page: 3440 ident: b0130 article-title: Fully convolutional networks for semantic segmentation publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition – start-page: 2800 year: 2015 end-page: 2809 ident: b0240 article-title: Towards unified depth and semantic prediction from a single image publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 1913 year: 2015 end-page: 1921 ident: b0155 article-title: Flowing convnets for human pose estimation in videos publication-title: Proceedings of the IEEE International Conference on Computer Vision – volume: 115 start-page: 211 year: 2015 end-page: 252 ident: b0180 article-title: Imagenet large scale visual recognition challenge publication-title: Int. J. Comput. Vision – start-page: (ICLR'15). year: 2015 ident: b0210 article-title: Very deep convolutional networks for large-scale image recognition publication-title: International Conference on Learning Representations – volume: 38 start-page: 2024 year: 2016 end-page: 2039 ident: b0120 article-title: Learning depth from single monocular images using deep convolutional neural fields publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 179 start-page: 300 year: 2012 end-page: 314 ident: b0245 article-title: ‘Structure-from-Motion’photogrammetry: a low-cost, effective tool for geoscience applications publication-title: Geomorphology – reference: Dosovitskiy, A., Springenberg, J.T., Brox, T., 2015. Learning to generate chairs with convolutional neural networks. In: Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on. IEEE, pp. 1538–1546. – start-page: 1097 year: 2012 end-page: 1105 ident: b0085 article-title: Imagenet classification with deep convolutional neural networks publication-title: Adv. Neural Inform. Process. Syst. – start-page: 2366 year: 2014 end-page: 2374 ident: b0040 article-title: Depth map prediction from a single image using a multi-scale deep network publication-title: Adv. Neural Inform. Process. Syst. – reference: Godard, C., Mac Aodha, O., Brostow, G.J., 2016. Unsupervised monocular depth estimation with left-right consistency. In: CVPR, vol. 2, No. 6, p. 7. – start-page: 2650 year: 2015 end-page: 2658 ident: b0035 article-title: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture publication-title: Proceedings of the IEEE International Conference on Computer Vision – volume: 9 start-page: 568 year: 2009 end-page: 601 ident: b0185 article-title: State-of-the-art and applications of 3D imaging sensors in industry, cultural heritage, medicine, and criminal investigation publication-title: Sensors – start-page: 1161 year: 2006 end-page: 1168 ident: b0190 article-title: Learning depth from single monocular images publication-title: Adv. Neural Inform. Process. Syst. – start-page: 89 year: 2014 end-page: 96 ident: b0095 article-title: Pulling things out of perspective publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – reference: Zhu, J., Ma, R., 2016. Real-Time Depth Estimation from 2D Images, available at: <http://cs231n.stanford.edu/reports/2016/pdfs/407_Report.pdf>. – volume: 15 start-page: 794 year: 2018 end-page: 798 ident: b0050 article-title: IMG2DSM: Height Simulation From Single Imagery Using Conditional Generative Adversarial Net publication-title: IEEE Geosci. Remote Sens. Lett. – start-page: 3111 year: 2013 ident: 10.1016/j.isprsjprs.2019.01.013_b0135 article-title: Distributed representations of words and phrases and their compositionality publication-title: Adv. Neural Inform. Process. Syst. – volume: 53 start-page: 71 year: 1993 ident: 10.1016/j.isprsjprs.2019.01.013_b0025 article-title: Shape from stereo: a systematic approach using quadratic surfaces publication-title: Attention, Percept., Psychophys. doi: 10.3758/BF03211716 – start-page: 689 year: 2015 ident: 10.1016/j.isprsjprs.2019.01.013_b0230 article-title: Matconvnet: convolutional neural networks for matlab – start-page: 775 year: 2012 ident: 10.1016/j.isprsjprs.2019.01.013_b0070 article-title: Depth extraction from video using non-parametric sampling publication-title: Eur. Conf. Comput. Vision. Springer – volume: 34 start-page: 705 issue: 4–5 year: 2015 ident: 10.1016/j.isprsjprs.2019.01.013_b0110 article-title: Deep learning for detecting robotic grasps publication-title: Int. J. Robot. Res. doi: 10.1177/0278364914549607 – volume: 8 start-page: 329 year: 2016 ident: 10.1016/j.isprsjprs.2019.01.013_b0105 article-title: Classification and segmentation of satellite orthoimagery using convolutional neural networks publication-title: Remote Sens. doi: 10.3390/rs8040329 – start-page: 1119 year: 2015 ident: 10.1016/j.isprsjprs.2019.01.013_b0115 article-title: Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs – volume: 16 start-page: 824 year: 1994 ident: 10.1016/j.isprsjprs.2019.01.013_b0145 article-title: Shape from focus publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/34.308479 – ident: 10.1016/j.isprsjprs.2019.01.013_b0010 – ident: 10.1016/j.isprsjprs.2019.01.013_b0100 doi: 10.1109/3DV.2016.32 – volume: 15 start-page: 794 issue: 5 year: 2018 ident: 10.1016/j.isprsjprs.2019.01.013_b0050 article-title: IMG2DSM: Height Simulation From Single Imagery Using Conditional Generative Adversarial Net publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2018.2806945 – start-page: 770 year: 2016 ident: 10.1016/j.isprsjprs.2019.01.013_b0065 article-title: Deep residual learning for image recognition – ident: 10.1016/j.isprsjprs.2019.01.013_b0170 doi: 10.1007/978-3-319-24574-4_28 – volume: 9 start-page: 568 year: 2009 ident: 10.1016/j.isprsjprs.2019.01.013_b0185 article-title: State-of-the-art and applications of 3D imaging sensors in industry, cultural heritage, medicine, and criminal investigation publication-title: Sensors doi: 10.3390/s90100568 – ident: 10.1016/j.isprsjprs.2019.01.013_b0255 – ident: 10.1016/j.isprsjprs.2019.01.013_b0055 doi: 10.1109/CVPR.2017.699 – start-page: 740 year: 2016 ident: 10.1016/j.isprsjprs.2019.01.013_b0045 article-title: Unsupervised CNN for single view depth estimation: geometry to the rescue publication-title: Eur. Conf. Comput. Vision. Springer – start-page: 2650 year: 2015 ident: 10.1016/j.isprsjprs.2019.01.013_b0035 article-title: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture – ident: 10.1016/j.isprsjprs.2019.01.013_b0080 – ident: 10.1016/j.isprsjprs.2019.01.013_b0030 doi: 10.1109/CVPR.2015.7298761 – ident: 10.1016/j.isprsjprs.2019.01.013_b0250 – ident: 10.1016/j.isprsjprs.2019.01.013_b0090 doi: 10.1109/CVPR.2017.238 – volume: 76 start-page: 53 year: 2008 ident: 10.1016/j.isprsjprs.2019.01.013_b0195 article-title: 3-d depth reconstruction from a single still image publication-title: Int. J. Comput. Vision doi: 10.1007/s11263-007-0071-y – start-page: 1161 year: 2006 ident: 10.1016/j.isprsjprs.2019.01.013_b0190 article-title: Learning depth from single monocular images publication-title: Adv. Neural Inform. Process. Syst. – start-page: 139 year: 2013 ident: 10.1016/j.isprsjprs.2019.01.013_b0150 article-title: Classification of urban LiDAR data using conditional random field and random forests publication-title: Urban Remote Sens. Event (JURSE) – ident: 10.1016/j.isprsjprs.2019.01.013_b0260 – start-page: 1097 year: 2012 ident: 10.1016/j.isprsjprs.2019.01.013_b0085 article-title: Imagenet classification with deep convolutional neural networks publication-title: Adv. Neural Inform. Process. Syst. – ident: 10.1016/j.isprsjprs.2019.01.013_b0225 doi: 10.1109/IDAACS.2017.8095172 – start-page: 3431 year: 2015 ident: 10.1016/j.isprsjprs.2019.01.013_b0130 article-title: Fully convolutional networks for semantic segmentation – ident: 10.1016/j.isprsjprs.2019.01.013_b0140 – start-page: 1 year: 2015 ident: 10.1016/j.isprsjprs.2019.01.013_b0220 article-title: Going deeper with convolutions – start-page: 2800 year: 2015 ident: 10.1016/j.isprsjprs.2019.01.013_b0240 article-title: Towards unified depth and semantic prediction from a single image – start-page: 2366 year: 2014 ident: 10.1016/j.isprsjprs.2019.01.013_b0040 article-title: Depth map prediction from a single image using a multi-scale deep network publication-title: Adv. Neural Inform. Process. Syst. – volume: 28 start-page: 193 year: 2004 ident: 10.1016/j.isprsjprs.2019.01.013_b0160 article-title: Optimization of DTM interpolation using SFS with single satellite imagery publication-title: J. Supercomput. doi: 10.1023/B:SUPE.0000020178.66165.f3 – start-page: 143 year: 2016 ident: 10.1016/j.isprsjprs.2019.01.013_b0075 article-title: Unified depth prediction and intrinsic image decomposition from a single image via joint convolutional neural fields publication-title: Eur. Conf. Comput. Vision. Springer – start-page: (ICLR'15). year: 2015 ident: 10.1016/j.isprsjprs.2019.01.013_b0210 article-title: Very deep convolutional networks for large-scale image recognition – start-page: 5173 year: 2017 ident: 10.1016/j.isprsjprs.2019.01.013_b0215 article-title: Joint height estimation and semantic labeling of monocular aerial images with CNNS publication-title: IEEE Int. Geosci. Remote Sens. Symp. (IGARSS) – volume: 21 start-page: 269 year: 2006 ident: 10.1016/j.isprsjprs.2019.01.013_b0165 article-title: Image-based 3D modelling: a review publication-title: Photogram. Rec. doi: 10.1111/j.1477-9730.2006.00383.x – ident: 10.1016/j.isprsjprs.2019.01.013_b0015 doi: 10.1155/2017/3296874 – volume: 38 start-page: 2024 year: 2016 ident: 10.1016/j.isprsjprs.2019.01.013_b0120 article-title: Learning depth from single monocular images using deep convolutional neural fields publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2015.2505283 – start-page: 5506 year: 2016 ident: 10.1016/j.isprsjprs.2019.01.013_b0175 article-title: Monocular depth estimation using neural regression forest – start-page: 716 year: 2014 ident: 10.1016/j.isprsjprs.2019.01.013_b0125 article-title: Discrete-continuous depth estimation from a single image – ident: 10.1016/j.isprsjprs.2019.01.013_b0205 doi: 10.1109/ICCV.2007.4408828 – start-page: 1913 year: 2015 ident: 10.1016/j.isprsjprs.2019.01.013_b0155 article-title: Flowing convnets for human pose estimation in videos – start-page: 89 year: 2014 ident: 10.1016/j.isprsjprs.2019.01.013_b0095 article-title: Pulling things out of perspective – ident: 10.1016/j.isprsjprs.2019.01.013_b0200 – volume: 179 start-page: 300 year: 2012 ident: 10.1016/j.isprsjprs.2019.01.013_b0245 article-title: ‘Structure-from-Motion’photogrammetry: a low-cost, effective tool for geoscience applications publication-title: Geomorphology doi: 10.1016/j.geomorph.2012.08.021 – volume: 2017 start-page: 2261 year: 2017 ident: 10.1016/j.isprsjprs.2019.01.013_b0060 article-title: Densely connected convolutional networks publication-title: IEEE Conf. Comput. Vision Pattern Recogn. (CVPR) – volume: 10 start-page: 145 year: 2013 ident: 10.1016/j.isprsjprs.2019.01.013_b0020 article-title: DEM densification using perspective shape from shading through multispectral imagery publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2012.2195471 – volume: 55 start-page: 881 year: 2017 ident: 10.1016/j.isprsjprs.2019.01.013_b0235 article-title: Dense semantic labeling of subdecimeter resolution images with convolutional neural networks publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2016.2616585 – start-page: 614 year: 2015 ident: 10.1016/j.isprsjprs.2019.01.013_b0265 article-title: Indoor scene structure analysis for single image depth estimation – volume: 36 start-page: 120 year: 2005 ident: 10.1016/j.isprsjprs.2019.01.013_b0005 article-title: A morphological reconstruction algorithm for separating off-terrain points from terrain points in laser scanning data publication-title: Int. Arch. Photogram., Remote Sens. Spatial Inform. Sci. – volume: 115 start-page: 211 year: 2015 ident: 10.1016/j.isprsjprs.2019.01.013_b0180 article-title: Imagenet large scale visual recognition challenge publication-title: Int. J. Comput. Vision doi: 10.1007/s11263-015-0816-y |
| SSID | ssj0001568 |
| Score | 2.543919 |
| Snippet | Extracting 3D information from aerial images is an important and still challenging topic in photogrammetry and remote sensing. Height estimation from only a... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 50 |
| SubjectTerms | aerial photography Convolutional neural network data collection Decoder Digital aerial image Encoder Height image image analysis neural networks photogrammetry quantitative analysis remote sensing |
| Title | Height estimation from single aerial images using a deep convolutional encoder-decoder network |
| URI | https://dx.doi.org/10.1016/j.isprsjprs.2019.01.013 https://www.proquest.com/docview/2221053088 |
| Volume | 149 |
| WOSCitedRecordID | wos000461535600005&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-8235 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001568 issn: 0924-2716 databaseCode: AIEXJ dateStart: 19950201 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3fb9MwELZKhwQ8IBggxi8ZibcoUmKncbK3Cg06HqaJDqlPRIl9FevatErbaX8Cf_bOOSftOtBACKlNozSuLd-Xu_P17jNjH5RBrRhA4Rv0HXzUfuAnMgEfdAw6yi3h0bjebEKdnCSjUXra6fxsamEup6osk6urdPFfRY3XUNi2dPYvxN3-KF7AcxQ6HlHsePwjwQ_qYKdn2TNmLpPQlpDYmMAUvBxom45Zbskd1nWkIPcMwKJOQHcjwzsswaWByjdQf3ol5YtvO7PHw9Ovw23uicWP-apO95rBqiJipwoQC-AtbZ68M5IWXrPz6gIX1ZQFNMjRJHt9y3KywR-MaT9tNOLg2MFdcMLWQ8nt4MTtqhkKPYrIFyp0FNikeBOFmlkQdUmrmYnN1OlWIqh1Vpq2arml_ykUMcF-FtVygm-bvJfWxKxU8rpDrj20Y7FDQT-29obvsT2hemnSZXv946PRl9aqh1RW2Y79Rq7gL7v7naezY_NrR-bsCXvsViC8T8h5yjpQ7rNHW7yU--zBZ3BM5s_Yd8IT3-CJWzxxwhMnPHHCE6_xxHNu8cRv4Inv4Ik7PD1n3z4dnX0c-G5TDl_LKFn5Kg-1HBshC2OLb9NIGRWKIlahTnTcK1QQmzTo6SQKixSkiSI8VWMhpUHX3KTyBeuW8xJeMi7w-3BchAK0Qb8ySrUsQKIBKlQhjY4PWNxMYKYdY73dOGWaNamJk6yd-czOfBaE-JIHLGgbLoi05e4mh42EMud7kk-ZIbTubvy-kWmG2tn-5ZaXMF_jTULgAkaiKX_1Lx28Zg83T9cb1l1Va3jL7uvL1fmyeuegeg2J1b76 |
| linkProvider | Elsevier |
| 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=Height+estimation+from+single+aerial+images+using+a+deep+convolutional+encoder-decoder+network&rft.jtitle=ISPRS+journal+of+photogrammetry+and+remote+sensing&rft.au=Amirkolaee%2C+Hamed+Amini&rft.au=Arefi%2C+Hossein&rft.date=2019-03-01&rft.pub=Elsevier+B.V&rft.issn=0924-2716&rft.eissn=1872-8235&rft.volume=149&rft.spage=50&rft.epage=66&rft_id=info:doi/10.1016%2Fj.isprsjprs.2019.01.013&rft.externalDocID=S0924271619300139 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0924-2716&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0924-2716&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0924-2716&client=summon |