TIR-MS: Thermal Infrared Mean-Shift for Robust Pedestrian Head Tracking in Dynamic Target and Background Variations
Source abstract
Abstract
Thermal infrared (TIR) pedestrian tracking is one of the major issues in computer vision. Mean-shift is a powerful and versatile non-parametric iterative algorithm for finding local maxima in probability distributions. In existing infrared data, and mean-shift-based tracking is generally based on the brightness feature values. Unfortunately, the brightness is distorted by the target and background variations. This paper proposes a novel pedestrian tracking algorithm, thermal infrared mean-shift (TIR-MS), by introducing radiometric temperature data in mean-shift tracking. The thermal brightness image (eight-bits) was distorted by the automatic contrast enhancement of the scene such as hot objects in the background. On the other hand, the temperature data was unaffected directly by the background change, except for variations by the seasonal effect, which is more stable than the brightness. The experimental results showed that the TIR-MS outperformed the original mean-shift-based brightness when tracking a pedestrian head with successive background variations.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Impact of Light on Environment and Health · Infrared Target Detection Methodologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electronics Engineering, Yeungnam University, 280 Daehak-ro, Gyeongsan-si 38541, Korea
Funding
National Research Foundation of Korea
References (35)
Show source-provided references
1. Real-time tracking of non-rigid objects using mean shift
2. Improved infrared target-tracking algorithm based on mean shift10.1364/AO.51.005051 ↗
3. Du, K., Ju, Y., Jin, Y., Li, G., Qian, S., and Li, Y. (2012, January 21–23). MeanShift tracking algorithm with adaptive block color histogram. Proceedings of the 2012 2nd International Conference on Consumer Electronics, Communications and Networks (CECNet), Piscataway, NJ, USA.10.1109/CECNet.2012.6202074 ↗
4. Optimal colour-based mean shift algorithm for tracking objects10.1049/iet-cvi.2013.0004 ↗
5. Feng, F., Wu, X.J., and Xu, T. (2017, January 14–17). Object tracking with kernel correlation filters based on mean shift. Proceedings of the 2017 International Smart Cities Conference (ISC2), Wuxi, China.10.1109/ISC2.2017.8090863 ↗
6. Robust mean-shift tracking with corrected background-weighted histogram10.1049/iet-cvi.2009.0075 ↗
7. Scale and orientation adaptive mean shift tracking10.1049/iet-cvi.2010.0112 ↗
8. Zhang, X., Zhang, X., Wang, Y., and Yu, H. (2016, January 26–28). Extended social force model-based mean shift for pedestrian tracking under obstacle avoidance. Proceedings of the IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), Seoul, Korea.
9. Object tracking system using Camshift, Meanshift and Kalman filter
10. Robust Correlation, Kalman filter and adaptive fast mean shift based heuristic approach for robust visual tracking10.1007/s11760-014-0612-0 ↗
11. Mean shift tracker combined with online learning-based detector and Kalman filtering for real-time tracking10.1016/j.eswa.2017.02.043 ↗
12. Pedestrian detection and tracking with night vision10.1109/TITS.2004.838222 ↗
13. Pedestrian detection at night time in FIR domain: Comprehensive study about temperature and brightness and new benchmark10.1016/j.patcog.2018.01.029 ↗
14. Thermal cameras and applications: a survey10.1007/s00138-013-0570-5 ↗
15. Li, C., and Wang, W. (2018). Detection and tracking of moving targets for thermal infrared video sequences. Sensors, 18.10.3390/s18113944 ↗
16. Ma, Y., Wu, X., Yu, G., Xu, Y., and Wang, Y. (2016). Pedestrian detection and tracking from low-resolution unmanned aerial vehicle thermal imagery. Sensors, 16.10.3390/s16040446 ↗
17. Computer vision and deep learning techniques for pedestrian detection and tracking: A survey10.1016/j.neucom.2018.01.092 ↗
18. Jia, X., Lu, H., and Yang, M.H. (2012, January 16–21). Visual tracking via adaptive structural local sparse appearance model. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.
19. Felsberg, M. (2013, January 1–8). Enhanced distribution field tracking using channel representations. Proceedings of the IEEE International Conference on Computer Vision Workshops, Sydney, Australia.10.1109/ICCVW.2013.22 ↗
20. Zhong, W., Lu, H., and Yang, M.H. (2012, January 16–21). Robust object tracking via sparsity-based collaborative model. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI.
21. Danelljan, M., Häger, G., Khan, F., and Felsberg, M. (2014, January 1–5). Accurate scale estimation for robust visual tracking. Proceedings of the British Machine Vision Conference, Nottingham, UK.10.5244/C.28.65 ↗
22. Berg, A., Ahlberg, J., and Felsberg, M. (2015, January 25–28). A thermal object tracking benchmark. Proceedings of the 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Karlsruhe, Germany.10.1109/AVSS.2015.7301772 ↗
23. Felsberg, M., Berg, A., Hager, G., Ahlberg, J., Kristan, M., Matas, J., and Nebehay, G. (2015, January 7–13). The thermal infrared visual object tracking VOT-TIR2015 challenge results. Proceedings of the IEEE International Conference on Computer Vision Workshops, Santiago, Chile.
24. Part-based pedestrian detection and feature-based tracking for driver assistance: Real-time, robust algorithms, and evaluation10.1109/TITS.2013.2262045 ↗
25. Pedestrian protection systems: Issues, survey, and challenges10.1109/TITS.2007.903444 ↗
26. Kernel-based object tracking10.1109/TPAMI.2003.1195991 ↗
27. Caulfield, D. (2011). Mean-Shift Tracking for Surveillance: Evaluations and Enhancements. [Ph.D. Thesis, University of Dublin].
28. Gorry, B., Chen, Z., Hammond, K., Wallace, A., and Michaelson, G. (2019, July 26). Using mean-shift tracking algorithms for real-time tracking of moving images on an autonomous vehicle testbed platform. Available online: https://pdfs.semanticscholar.org/4eed/a6bcee928e4ed1e1b497a6420127748424d0.pdf.
29. Milian, A., Rezatofighi, S.H., Dick, A.R., Reid, I.D., and Schindler, K. (2017). Online Multi-Target Tracking Using Recurrent Neural Networks. arXiv.10.1609/aaai.v31i1.11194 ↗
30. Yi, S., Li, H., and Wang, X. (2016, January 8–16). Pedestrian behavior understanding and prediction with deep neural networks. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_16 ↗
31. Human tracking using convolutional neural networks10.1109/TNN.2010.2066286 ↗
32. Jacobs, P.A. (2006). Society of Photo-optical Instrumentation Engineers. Thermal infrared Characterization of Ground Targets and Backgrounds, SPIE.10.1117/3.651915 ↗
33. Held, D., Thrun, S., and Savarese, S. (2016, January 11–14). Learning to track at 100 fps with deep regression networks. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_45 ↗
34. Re 3: Re al-Time Recurrent Regression Networks for Visual Tracking of Generic Objects10.1109/LRA.2018.2792152 ↗
35. Yun, S., Choi, J., Yoo, Y., Yun, K., and Young Choi, J. (2017, January 21–26). Action-decision networks for visual tracking with deep reinforcement learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.148 ↗