Video sequence object detection and tracking algorithms

Authors: Malyshev P.V.
Published in issue: #4(93)/2024
DOI:
Category: Informatics, Computer Engineering and Control | Chapter: Information Technology. Computer techologies. Theory of computers and systems
Keywords: algorithm, object detection, object tracking, video surveillance, video surveillance systems, image processing, background model, computer vision
Published: 16.09.2024

The paper considers the video sequence object detection and tracking algorithms, and selects the most suitable methods in identifying and highlighting the object contours in a video stream without using the machine learning. It proposes an algorithm for creating a simple video surveillance system. Many approaches to object tracking combine tracking, learning, and detection. The tracking algorithm, or the so-called tracker, follows an object from one frame to another. The detection algorithm, or the detector, localizes all the features observed so far and, if necessary, adjusts the tracker. During learning, errors of the detector are assessed and its operation is corrected to avoid these errors in future. Let us note that learning in object detection is usually performed under the condition that all the learning examples are labeled. This paper analyzes algorithms and methods that could be introduced to create detectors and trackers.

References

[1] Darrell T., Pentland A.P. Pfinder: Real-Time Tracking of the Human Body. IEEE PAMI, 1997, vol. 19, iss. 7. http://dx.doi.org/10.1109/34.598236

[2] Verschae R., Ruiz-del-Solar J. Object Detection: Current and Future Directions. Front. Robot. AI, 2015, vol. 2. https://doi.org/10.3389/frobt.2015.00029

[3] Ramakant C., Rohit R., Rohit M., Upasana Si., Alok Kumar S.K., Hiral R. Enhanced the moving object detection and object tracking for traffic surveillance using RBF-FDLNN and CBF algorithm. Expert Systems with Applications, 2021, vol. 191. https://doi.org/10.1016/j.eswa.2021.116306

[4] Bartels A., Zeki S. The architecture of the colour centre in the human visual brain: new results and a review. European Journal of Neuroscience, 2000, vol. 12. https://doi.org/10.1046/j.1460-9568.2000.00905.x

[5] Ren Li, Xian Weifu, Tang Hao, Jiang Yadong, Jia Haitao, Li Jing. Pedestrian and Face Detection with Low Resolution Based on Improved MTCNN. ICCPR 2020: 2020 9th International Conference on Computing and Pattern Recognition, 2020. https://doi.org/10.1145/3436369.3436492

[6] Ochs P., Malik J., Brox T. Segmentation of moving objects by long term video analysis. IEEE transactions on pattern analysis and machine intelligence, 2014, vol. 36. https://doi.org/ 10.1109/TPAMI.2013.242

[7] Yu Zhang, Hongjie Wang, Yongkai Yin, Wenjie Jiang, and Baoqing Sun. Mask-based single-pixel tracking and imaging for moving objects. Opt. Express, 2023, vol. 31, pp. 32554–32564. https://doi.org/10.1364/OE.501531

[8] Lionel Rakai, Huansheng Song, ShiJie Sun, Wentao Zhang, Yanni Yang. Data association in multiple object tracking: A survey of recent techniques. Expert Systems with Applications, 2021, vol. 192. https://doi.org/10.1016/j.eswa.2021.116300

[9] Shanq-Jang Ruan. Illumination-Sensitive Background Modeling Approach for Accurate Moving Object Detection. IEEE Transactions on Broadcasting, 2011, vol. 57 (4), pp. 794–801. https://doi.org/ 10.1109/TBC.2011.2160106

[10] Myung-Cheol Roh, Tae-Yong Kim, Jihun Park, Seong-Whan Lee. Accurate object contour tracking based on boundary edge selection. Pattern Recognition, 2007, vol. 40, iss. 3.