People detection based on co-occurrence of appearance and spatio-temporal features

被引：9
作者：
Yamauchi Y. [1 ]
Fujiyoshi H. [1 ]
Iwahori Y. [1 ]
Kanade T. [2 ]
机构：
[1] Graduate School of Engineering, Chubu University
[2] Robotics Institute, Carnegie Mellon University
来源：
Progress in Informatics | 2010年 / 07期
关键词：
Adaboost; Co-occurrence; Histograms of oriented gradients; People detection; Pixel state analysis;
D O I：
10.2201/NiiPi.2010.7.5
中图分类号：
学科分类号：
摘要：
This paper presents a method for detecting people based on co-occurrence of appearance and spatio-temporal features. In our method, Histograms of Oriented Gradients (HOG) are used as appearance features, and the results of pixel state analysis are used as spatiotemporal features. The pixel state analysis classifies foreground pixels as either stationary or transient. The appearance and spatio-temporal features are projected into subspaces in order to reduce the dimension of feature vectors by principal component analysis (PCA). The cascade AdaBoost classifier is used to represent the co-occurrence of the appearance and spatio-temporal features. The use of feature co-occurrence, which captures the similarity of appearance, motion, and spatial information within the people class, makes it possible to construct an effective detector. Experimental results show that the performance of our method is about 29.0% better than that of the conventional method. © 2010 National Institute of Informatics.
引用
收藏
页码：33 / 42
页数：9
相关论文
共 14 条
  • [1] Lipton A., Fujiyoshi H., Patil R., Moving target classification and tracking from realtime video, IEEE Workshop On Application of Computer Vision, pp. 8-14, (1988)
  • [2] Grimson W.E.L., Stauffer C., Romano R., Lee L., Using adaptive tracking to classify and monitor activities in a site, IEEE CS Conference On Computer Vision and Pattern Recognition, pp. 22-31, (1998)
  • [3] Hasegawa O., Kanade T., Type classification, color estimation, and specific target detection of moving targets on public streets, IEEEMachine Vision and Applications, pp. 116-121, (2004)
  • [4] Levi K., Weiss Y., Learning object detection from a small number of examples: The importance of good features, IEEE CS Conference On Computer Vision and Pattern Recognition, pp. 53-60, (2004)
  • [5] Dalal N., Triggs B., Histograms of oriented gradients for human detection, IEEE CS Conference On Computer Vision and Pattern Recognition, pp. 886-893, (2005)
  • [6] Wu B., Nevatia R., Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors, IEEE CS Conference On Computer Vision and Pattern Recognition, pp. 90-97, (2005)
  • [7] Suard F., Broggi A., Pedestrian detection using infrared images and histograms of oriented gradients, IEEE Symposium On Intelligent Vehicles, pp. 206-212, (2006)
  • [8] Zhu Q., Avidan S., Yeh M., Cheng K., Fast human detection using a cascade of histograms of oriented gradients, IEEE CS Conference On Computer Vision and Pattern Recognition, pp. 1491-1498, (2006)
  • [9] Dalal N., Triggs B., Schmid C., Human detection using oriented histograms of flow and appearance, IEEE European Conference On Computer Vision, pp. 428-441, (2006)
  • [10] Viola P., Jones M., Snow D., Detecting pedestrians using patterns of motion and appearance, IEEE International Conference On Computer Vision, pp. 734-741, (2003)
12