Multi-person tracking using SURF and background subtraction for surveillance
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Surveillance cameras have installed in many places because security and safety is becoming important inmodern society. Through surveillance cameras installed, we can deal with troubles and prevent accidents. However, watching surveillance videos and judging the accidental situations is very labor-intensive. So now,the need for research to analyze surveillance videos is growing. This study proposes an algorithm to trackmultiple persons using SURF and background subtraction. While the SURF algorithm, as a person-trackingalgorithm, is robust to scaling, rotating and different viewpoints, SURF makes tracking errors with suddenchanges in videos. To resolve such tracking errors, we combined SURF with a background subtractionalgorithm and showed that the proposed approach increased the tracking accuracy. In addition, the backgroundsubtraction algorithm can detect persons in videos, and SURF can initialize tracking targets with these detectedpersons, and thus the proposed algorithm can automatically detect the enter/exit of persons.
Abstract
Surveillance cameras have installed in many places because security and safety is becoming important inmodern society. Through surveillance cameras installed, we can deal with troubles and prevent accidents. However, watching surveillance videos and judging the accidental situations is very labor-intensive. So now,the need for research to analyze surveillance videos is growing. This study proposes an algorithm to trackmultiple persons using SURF and background subtraction. While the SURF algorithm, as a person-trackingalgorithm, is robust to scaling, rotating and different viewpoints, SURF makes tracking errors with suddenchanges in videos. To resolve such tracking errors, we combined SURF with a background subtractionalgorithm and showed that the proposed approach increased the tracking accuracy. In addition, the backgroundsubtraction algorithm can detect persons in videos, and SURF can initialize tracking targets with these detectedpersons, and thus the proposed algorithm can automatically detect the enter/exit of persons.
참고문헌 (15)
- U. Joshi, "Object tracking and classification under illumination variations", International Journal of Engineering Development and Research, 4(1), pp.667~670 (2016)
- H. Patel, "Advances in Computing and Information Technology", pp.749~756 (2012), Springer
- C. Li, "A new method combining HOG and Kalman filter for video-based human detection and tracking", Proceedings of the 3rd International Congress on Image and Signal Processing, Yantai, pp.290~293 (2010)
- C. T. Chu, "Human tracking by adaptive Kalman filtering and multiple kernels tracking with projected gradients", Proceedings of the 5th ACM, 2011, 1~6
- Y. Tian, "Robust detection of abandoned and removed objects in complex surveillance videos", IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 41(5), pp.565~576 (2011)
- K. Du, "Object tracking based on improved MeanShift and SIFT", Proceedings of the 2nd International Conference on Consumer Electronics, Communications and Networks, pp.2716~2719 (2012)
- Kenan Mu, "Multiple Vehicle Detection and Tracking in Highway Traffic Surveillance Video Based on SIFT Feature Matching", JIPS(Journal of Information Processing Systems), 12(2), pp.183~195 (2016), 한국정보처리학회[DOI]
- H. Shuo, "Object tracking method based on SURF", AASRI Procedia, 3, pp.351~356 (2012)
- D. Zhou, "A robust object tracking algorithm based on SURF", Proceedings of International Conference on the Wireless Communications & Signal Processing, pp.1~5 (2013)
- J. Li, "Object tracking using improved Camshift with SURF method", Proceedings of International Workshop on Open-Source Software for Scientific Computation, pp.136~141 (2011)
- H. Bay, "SURF: speeded up robust features", Computer Vision–ECCV 2006, pp.404~471 (2006), Springer
- N. Ren, "Robust visual tracking based on scale invariance and deep learning", Frontiers of Computer Science, 11(2), pp.230~242 (2017)
- R. Cao, "Adaptive block-based target tracking method fusing color histogram and SURF features", Proceedings of the 2016 Chinese Intelligence System Conference, pp.193~200 (2016), Springer
- K. M. Lee, "Computational and Information Science", pp.1201~1207 (2005), Springer
- "NLPR_MCT dataset"[URL]