Object tracking in video processing is a significance task because of its applications in surveillance, activity monitoring and recognition, traffic management etc. In outdoor and indoor environment multiple objects tracking is a challenging task because of poor lighting conditions, variation in poses, orientations, changes in location, shape and size etc. This paper proposes a method for tracking multiple objects in a video stream. Haar- like features are used to train the classifier from the training image set. Haar-like rectangular features are extracted and these features are used to train the method to track moving objects from video sequences using particle filter. Proposed method is tested on standard data sets: KTH, Caviar data set. The experimental results show that the proposed method can track multiple objects in a video adequately fast in the presence of poor lighting conditions, variation in poses of objects, shape, size etc. and the technique can handle varying number of objects in a video at various points of time.

Object tracking, video, surveillance, human detection

[1] Ashish Khare, Nguyen Thanh Binh and Nguyen Chi Thanh, “Human tracking based on context awareness in outdoor environment”, KSII Transactions on Internet and Information Systems, vol.1 ,no 6, pp 3104-3120, jun. 2017.
[2] Kabir Hossain, Chi-Woo Lee, “Visual tracking using particle filter”, 9th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), pp 98-102, 2012.
[3] Fabian Sigges and Marcus Baum, and Uwe D. Hanebeck, “A likelihood-free particle filter for multi-object tracking”, 20th International Conference on Information Fusion, pp 1 -5, july 10 - 13, 2017.
[4] Aashish Sharma, Ajay Singh, and Rajesh Rohilla, “Color based human detection and tracking algorithm using a non-gaussian adaptive particle filter”, 3rd International Conference on Recent Advances in Information Technology (RAIT), pp 439 - 442, 2016.
[5] Tassaphan Suwannatat and Krisana Chinnasarn, and Nakorn Indra-Payoong, “ Multi-features particle PHD filtering for multiple humans tracking”, International Computer Science and Engineering Conference (ICSEC), pp 1-6, 2015.
[6] Tram Tran Nguyen Quynh, “Improved particle filter for tracking objects in video”,International Journal of Advanced Research in Computer Engineering and Technology (IJARCET), Vol. 4, Issue 11, pp 4254-4261, Nov 2015.
[7] Atsushi Yoshida, Hyoungseop Kim, Joo Kooi Tan, and Seiji Ishikawa, “ Person tracking on kinect images using particle filter”, Soft Computing and Intelligent Systems (SCIS), 2014 Joint 7th International Conference on and Advanced Intelligent Systems (ISIS), pp 1486-1489, 2014.
[8] Di Yuan, Guanglei Zhao Donghao Li, Zhenyu He, and Nan Luo, “Visual object tracking based on particle filter re-detection”, International Conference on Security, Pattern Analysis, and Cybernetics (SPAC), pp 1-6, 2017.
[9] Peng Tian, “ A particle filter object tracking based on feature and location fusion”, 6th IEEE International Conference on Software Engineering and Service Science (ICSESS), pp 762-765, 2015.
[10] Hamd Ait Abdelali, Fedwa Essannouni, Leila Essannouni, and Driss Aboutajdine, “ A new moving object tracking method using particle filter and probability product kernel”, Intelligent Systems and Computer Vision (ISCV), pp 1-6, 2015.
[11] Ding Dongsheng, Jiang Zengru, and Liu Chengyuan, “Object tracking algorithm based on particle filter with color and texture feature”, 35th Chinese Control Conference (CCC), pp 4031-4036, 2016.
[12] Haris Masood, Saad Rehman, Muazzam Khan, Qaiser Javed, M. Abbas, M. Alam, and Rupert Young , “ Tracking of fixed shape moving objects based on modified particle filters”, 19th International Conference on Computer and Information Technology (ICCIT), pp 240-245, 2016.
[13] Mir Abbas Daneshyar, and Manoochehr Nahvi, “Improvement of moving objects tracking via modified particle distribution in particle filter algorithm”, 2nd International Conference on Pattern Recognition and Image Analysis (IPRIA), pp 1-6, 2015.
[14] Tassaphan Suwannatat, Nakron Indra-Payoong, and Krisana Chinnasarn, “ Robust human tracking based on multi-features particle filter”,12th International Joint Conference on Computer Science and Software Engineering (JCSSE) , pp 12-17, 2015.
[15] Abdul-Lateef Yussiff, Suet-Peng Yong, and Baharum B. Bahardin, “ Human tracking in video surveillance using particle filter”, International Symposium on Mathematical Sciences and Computing Research (iSMSC), pp 83-88, 2015.