Fast Feature Pyramids for Object Detection
Top Cited Papers
- 16 January 2014
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 36 (8), 1532-1545
- https://doi.org/10.1109/tpami.2014.2300479
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).Keywords
This publication has 62 references indexed in Scilit:
- A Fast Stereo-based System for Detecting and Tracking Pedestrians from a Moving VehicleThe International Journal of Robotics Research, 2009
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Distortion invariant object recognition in the dynamic link architectureInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP), 1993
- Computational framework for determining stereo correspondence from a set of linear spatial filtersImage and Vision Computing, 1992
- Scale-space for discrete signalsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Multirate digital filters, filter banks, polyphase networks, and applications: a tutorialProceedings of the IEEE, 1990
- A theory for multiresolution signal decomposition: the wavelet representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989
- A theory of multirate filter banksIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- The Laplacian Pyramid as a Compact Image CodeIEEE Transactions on Communications, 1983
- A Characterization of the Exponential FunctionThe American Mathematical Monthly, 1957