30Hz Object Detection with DPM V5

Mohammad Amin Sadeghi, David Forsyth
University of Illinois at Urbana-Champaign
NIPS'13

Abstract

We describe an implementation of the Deformable Parts Model [1] that operates in a user-defined time-frame. Our implementation uses a variety of mechanism to trade-off speed against accuracy. Our implementation can detect all 20 PASCAL 2007 objects simultaneously at 30Hz with an mAP of 0.26. At 15Hz, its mAP is 0.30; and at 100Hz, its mAP is 0.16. By comparison the reference implementation of [1] runs at 0.07Hz and mAP of 0.33 and a fast GPU implementation runs at 1Hz. Our technique is over an order of magnitude faster than the previous fastest DPM implementation. Our implementation exploits a series of important speedup mechanisms. We use the cascade framework of [3] and the vector quantization technique of [2]. To speed up feature computation, we compute HOG features at few scales, and apply many interpolated templates. A hierarchical vector quantization method is used to compress HOG features for fast template evaluation. An object proposal step uses hash-table methods to identify locations where evaluating templates would be most useful; these locations are inserted into a priority queue, and processed in a detection phase. Both proposal and detection phases have an any-time property. Our method applies to legacy templates, and no retraining is required.

Download Code


Code

Paper


Download PDF (1MB)

BibTeX

@article{ftvq,
title = {30Hz Object Detection with DPM V5},
author = {Mohammad Amin Sadeghi and David Forsyth},
booktitle = {European Conference on Computer Vision},
year = {2014},
}