Hierarchical Graph based Segmentation and Consensus based Human Tracking Technique
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Accurate detection, tracking and analysis of human movement using robots and other visual surveillancesystems is still a challenge. Efforts are on to make the system robust against constraints such as variation inshape, size, pose and occlusion. Traditional methods of detection used the sliding window approach whichinvolved scanning of various sizes of windows across an image. This paper concentrates on employing a stateof-the-art, hierarchical graph based method for segmentation. It has two stages: part level segmentation forcolor-consistent segments and object level segmentation for category-consistent regions. The tracking phase isachieved by employing SIFT keypoint descriptor based technique in a combined matching and tracking schemewith validation phase. Localization of human region in each frame is performed by keypoints by casting votesfor the center of the human detected region. As it is difficult to avoid incorrect keypoints, a consensus-basedframework is used to detect voting behavior. The designed methodology is tested on the video sequences having3 to 4 persons.
Abstract
Accurate detection, tracking and analysis of human movement using robots and other visual surveillancesystems is still a challenge. Efforts are on to make the system robust against constraints such as variation inshape, size, pose and occlusion. Traditional methods of detection used the sliding window approach whichinvolved scanning of various sizes of windows across an image. This paper concentrates on employing a stateof-the-art, hierarchical graph based method for segmentation. It has two stages: part level segmentation forcolor-consistent segments and object level segmentation for category-consistent regions. The tracking phase isachieved by employing SIFT keypoint descriptor based technique in a combined matching and tracking schemewith validation phase. Localization of human region in each frame is performed by keypoints by casting votesfor the center of the human detected region. As it is difficult to avoid incorrect keypoints, a consensus-basedframework is used to detect voting behavior. The designed methodology is tested on the video sequences having3 to 4 persons.
참고문헌 (27)
- N. Dalal, "Histograms of oriented gradients for human detection", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp.886~893 (2005)
- B. Peng, "A survey of graph theoretical approaches to image segmentation", Pattern Recognition, 46(3), pp.1020~1038 (2013)
- R. Chaudhry, "Histograms of oriented optical flow and binet-cauchy kernels on nonlinear dynamical systems for the recognition of human actions", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp.1932~1939 (2009)
- J. Santner, "PROST: parallel robust online simple tracking", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.723~730 (2010)
- M. Andriluka, "People-tracking-by-detection and people-detection-by-tracking", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp.1~8 (2008)
- A. Andriyenko, "Discrete-continuous optimization for multi-target tracking", Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp.1926~1933 (2012)
- A. T., Kamal, "Information consensus for distributed multi-target tracking", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2403~2410 (2013)
- A. Milan, "Detection-and trajectory-level exclusion in multiple object tracking", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.3682~3689 (2013)
- S. Duffner, "PixelTrack: a fast adaptive algorithm for tracking non-rigid objects", Proceedings of the IEEE International Conference on Computer Vision, pp.2480~2487 (2013)
- S. Katragadda, "Neighbour consensus for distributed visual tracking", Proceedings of 2015IEEE 10th International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), pp.1~6 (2015)
- B. Babenko, "Robust object tracking with online multiple instance learning", IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(8), pp.1619~1632 (2011)
- T. P. Tian, "Fast globally optimal 2D human detection with loopy graph models", Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition, pp.81~88 (2010)
- A. P. Ta, "Pairwise features for human action recognition", Proceedings of 2010 International Conference on Pattern Recognition, pp.3224~3227 (2010)
- M. Yang, "Detecting human actions in surveillance videos", TREC Video Retrieval Evaluation (TRECVID) Workshop (2009)
- W. R. Schwartz, "Human detection using partial least squares analysis", Proceedings of 2009 IEEE 12th International Conference on Computer Vision, pp.24~31 (2009)
- B. Peng, "Evaluation of image segmentation quality by adaptive ground truth composition", Computer Vision – ECCV 2012, pp.287~300 (2012), Springer
- M. D. Breitenstein, "Online multiperson tracking-bydetection from a single, uncalibrated camera", IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(9), pp.1820~1833 (2011)
- X. Zhang, "Multiple object tracking via species-based particle swarm optimization", IEEE Transactions on Circuits and Systems for Video Technology, 20(11), pp.1590~1602 (2010)
- P. F. Felzenszwalb, "Efficient graph-based image segmentation", International Journal of Computer Vision, 59(2), pp.167~181 (2004)
- A practical guide to support vector classification, "C. W. Hsu", Department of Computer Science, National Taiwan University, ~ (2003)
- J. Kim, "Object detection using hierarchical graph-based segmentation", Proceedings of 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.1923~1926 (2013)
- A. K. Jain, "Object detection using Gabor filters", Pattern Recognition, 30(2), pp.295~309 (1997)
- Z. Sun, "On-road vehicle detection using Gabor filters and support vector machines", Proceedings of 2002 14th International Conference on Digital Signal Processing, pp.1019~1022 (2002)
- D. G. Lowe, "Distinctive image features from scale-invariant keypoints", International Journal of Computer Vision, 60(2), pp.91~110 (2004)
- G. Nebehay, "Consensus-based matching and tracking of keypoints for object tracking", Proceedings of 2014 IEEE Winter Conference on Applications of Computer Vision, pp.862~869 (2014)
- "CAVIAR dataset"[URL]
- P. M. Roth, "Multiple instance learning from multiple cameras", Proceedings of 2010 IEEE International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp.17~24 (2010)