Fast feature pyramids for object detection
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Fast feature pyramids for object detection. / Dollar, Piotr; Appel, Ron; Belongie, Serge; Perona, Pietro.
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 36, No. 8, 6714453, 08.2014, p. 1532-1545.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Fast feature pyramids for object detection
AU - Dollar, Piotr
AU - Appel, Ron
AU - Belongie, Serge
AU - Perona, Pietro
PY - 2014/8
Y1 - 2014/8
N2 - 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).
AB - 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).
KW - image pyramids
KW - natural image statistics
KW - object detection
KW - pedestrian detection
KW - real-time systems
KW - Visual features
UR - http://www.scopus.com/inward/record.url?scp=84903622275&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2014.2300479
DO - 10.1109/TPAMI.2014.2300479
M3 - Journal article
AN - SCOPUS:84903622275
VL - 36
SP - 1532
EP - 1545
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
SN - 0162-8828
IS - 8
M1 - 6714453
ER -
ID: 302045927