A Novel Human Detection Approach Based on Depth Map via Kinect

被引:14
作者
Shen, Yujie [1 ]
Hao, Zhonghua [1 ]
Wang, Pengfei [1 ]
Ma, Shiwei [1 ]
Liu, Wanquan [2 ]
机构
[1] Shanghai Univ, Sch Mechatron Engn & Automat, 149 Yanchang Rd, Shanghai 200072, Peoples R China
[2] Curtin Univ, Dept Comp, Bentley, WA 6102, Australia
来源
2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) | 2013年
基金
美国国家科学基金会;
关键词
D O I
10.1109/CVPRW.2013.85
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:535 / 541
页数:7
相关论文
共 19 条
  • [1] [Anonymous], 2011, June 2011. IEEE, DOI DOI 10.1109/CVPRW.2011.5981811
  • [2] [Anonymous], 2007, P 6 ACM INT C IM VID, DOI [DOI 10.1145/1282280.1282340, 10.1145/1282280.1282340]
  • [3] [Anonymous], 2011, 3 CHIN C INT VIS SUR
  • [4] Broggi A., 2005, IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops, P1
  • [5] LIBSVM: A Library for Support Vector Machines[J]. Chang, Chih-Chung;Lin, Chih-Jen. ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011(03)
  • [6] Histograms of oriented gradients for human detection[J]. Dalal, N;Triggs, B. 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005
  • [7] Demetriou Michael K., 2012, C COMP GRAPH IM, P254
  • [8] Dollár P, 2009, PROC CVPR IEEE, P304, DOI 10.1109/CVPRW.2009.5206631
  • [9] Felzenszwalb P, 2008, PROC CVPR IEEE, P1984
  • [10] Ikemura S., 2010, REAL TIME HUMAN DETE, P25