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 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).

1. Introduction

Multi-Resolution multi-orientation decompositions are one of the foundational techniques of image analysis. The idea of analyzing image structure separately at every scale and orientation originated from a number of sources: measurements of the physiology of mammalian visual systems [1]–[3], principled reasoning about the statistics and coding of visual information [4]–[7] (Gabors, DOGs, and jets), harmonic analysis [8] [9] (wavelets), and signal processing [9] [10] (multirate filtering). Such representations have proven effective for visual processing tasks such as denoising [11], image enhancement [12], texture analysis [13], stereoscopic correspondence [14], motion flow [15] [16], attention [17], boundary detection [18] and recognition [19]–[21].