资源论文30Hz Ob ject Detection with DPM V5

30Hz Ob ject Detection with DPM V5

2020-04-06 | |  50 |   39 |   0

Abstract

We describe an implementation of the Deformable Parts Model [1] that operates in a user-defined time-frame. Our implemen- tation uses a variety of mechanism to trade-off speed against accuracy. Our implementation can detect all 20 PASCAL 2007 ob jects simulta- neously 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 frame- work 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 ob- ject 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.

上一篇:Image-Based 4-d Reconstruction Using 3-d Change Detection

下一篇:Active Deformable Part Models Inference*

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...