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!
Description
Summary: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).
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
2160-9292
1939-3539
DOI:10.1109/TPAMI.2014.2300479