Abstract | ||
---|---|---|
Co-occurrence histograms of oriented gradients (CoHOG) are powerful descriptors in object detection. In this paper, we propose to utilize a very large pool of CoHOG features with variable-location and variable-size blocks to capture salient characteristics of the object structure. We consider a CoHOG feature as a block with a special pattern described by the offset. A boosting algorithm is further introduced to select the appropriate locations and offsets to construct an efficient and accurate cascade classifier. Experimental results on public datasets show that our approach simultaneously achieves high accuracy and fast speed on both pedestrian detection and car detection tasks. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ICIP.2010.5651963 | 2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING |
Keywords | Field | DocType |
Object Detection, CoHOG, Boosting, Cascade Classifier | Computer vision,Histogram,Object detection,Pattern recognition,Computer science,Cascading classifiers,Feature extraction,Boosting (machine learning),Artificial intelligence,Statistical classification,Pedestrian detection,Offset (computer science) | Conference |
ISSN | Citations | PageRank |
1522-4880 | 10 | 0.52 |
References | Authors | |
14 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haoyu Ren | 1 | 50 | 7.81 |
Cher-Keng Heng | 2 | 28 | 2.22 |
Wei Zheng | 3 | 71 | 4.82 |
Luhong Liang | 4 | 420 | 29.04 |
Xilin Chen | 5 | 6291 | 306.27 |