Abstract | ||
---|---|---|
In this paper, a new method of human detection based on depth map from 3D sensor Kinect is proposed. First, the pixel filtering and context filtering are employed to roughly repair defects on the depth map due to information inaccuracy captured by Kinect. Second, a dataset consisting of depth maps with various indoor human poses is constructed as benchmark. Finally, by introducing Kirsch mask and three-value codes to Local Binary Pattern, a novel Local Ternary Direction Pattern (LTDP) feature descriptor is extracted and is used for human detection with SVM as classifier. The performance for the proposed approach is evaluated and compared with other five existing feature descriptors using the same SVM classifier. Experiment results manifest the effectiveness of the proposed approach. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/CVPRW.2013.85 | CVPR Workshops |
Keywords | Field | DocType |
feature descriptor,depth map,novel local ternary direction,existing feature,local binary pattern,local ternary direction pattern,defects repair,svm classifier,novel human detection approach,feature extraction,image classification,indoor human poses,three-value codes,object detection,filtering theory,kirsch mask,3d sensor kinect,sensor kinect,various indoor human,ltdp feature descriptor,human detection,information inaccuracy,support vector machines,context filtering,pixel filtering,noise,filtering,integrated circuits,histograms | Object detection,Computer vision,Pattern recognition,Computer science,Feature (computer vision),Support vector machine,Local binary patterns,Feature extraction,Artificial intelligence,Depth map,Classifier (linguistics),Contextual image classification | Conference |
Volume | Issue | ISSN |
2013 | 1 | 2160-7508 |
Citations | PageRank | References |
1 | 0.36 | 14 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yujie Shen | 1 | 5 | 1.13 |
Zhonghua Hao | 2 | 2 | 2.41 |
Pengfei Wang | 3 | 41 | 13.22 |
Shiwei Ma | 4 | 136 | 21.79 |
Wanquan Liu | 5 | 629 | 81.29 |