Crosstalk cascades for frame-rate pedestrian detection
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Sparselet models for efficient multiclass object detection
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Beyond bounding-boxes: learning object shape by model-driven grouping
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Mixture component identification and learning for visual recognition
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
Bounding part scores for rapid detection with deformable part models
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Coarse to fine K nearest neighbor classifier
Pattern Recognition Letters
Local context priors for object proposal generation
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Data decomposition and spatial mixture modeling for part based model
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
A novel multiplex cascade classifier for pedestrian detection
Pattern Recognition Letters
Object class detection: A survey
ACM Computing Surveys (CSUR)
Discriminative Hough context model for object detection
The Visual Computer: International Journal of Computer Graphics
Hi-index | 0.00 |
We present a method that can dramatically accelerate object detection with part based models. The method is based on the observation that the cost of detection is likely to be dominated by the cost of matching each part to the image, and not by the cost of computing the optimal configuration of the parts as commonly assumed. Therefore accelerating detection requires minimizing the number of part-to-image comparisons. To this end we propose a multiple-resolutions hierarchical part based model and a corresponding coarse-to-fine inference procedure that recursively eliminates from the search space unpromising part placements. The method yields a ten-fold speedup over the standard dynamic programming approach and is complementary to the cascade-of-parts approach of. Compared to the latter, our method does not have parameters to be determined empirically, which simplifies its use during the training of the model. Most importantly, the two techniques can be combined to obtain a very significant speedup, of two orders of magnitude in some cases. We evaluate our method extensively on the PASCAL VOC and INRIA datasets, demonstrating a very high increase in the detection speed with little degradation of the accuracy.