Camouflaged Target Tracking using a Thermal Imaging and a True Color Camera Fusion
Keywords:
image processing, camouflage object, tracking system, unmanned aerial vehicleAbstract
This research presents the development of an algorithm for tracking camouflaged objects through flight tests using an unmanned aerial vehicle (UAV) by fusing data from a true color (RGB) camera and a thermal imaging camera mounted on the UAV to enhance the tracking performance of targets that are complex and blend into the environment. The RGB camera provides clear spatial details, while the thermal camera can detect the thermal radiation emitted by objects, which is useful in low-light conditions or when the object is camouflaged. Real-time video feeds from both camera types are transmitted to a ground control station (GCS), enabling remote monitoring and analysis by operators. The developed algorithm combines data from both sources to achieve tracking accuracy by using four tracking algorithms: Boosting, CSR-DCF, KCF, and MOSSE. Experimental results indicate that the boosting algorithm achieves the highest tracking accuracy, with the performance metrics indicating a lowest Mean Center Location Error (mCLE) of 43.46 and a highest AUC Score of 0.154. Additionally, the Distance Precision (DP) of 0.1085 and Overlap Precision (OP) of 0.154 scores demonstrate improved accuracy, highlighting the effectiveness and consistency of the algorithm in tracking camouflaged objects in challenging environments where visibility is limited.
References
Asha, C. S., & Narasimhadhan, A. V. (2016). Adaptive learning rate for visual tracking using correlation filters. Procedia Computer Science, 89, 614-622. https://doi.org/10.1016/j.procs.2016.06.023
Bamrungthai, P., & Wongkamchang, P. (2018). Development of a thermal/visible image fusion system for situation awareness. In 2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA) (pp. 96-100). Krabi: IEEE.
Bolme, D. S., Beveridge, J. R., Draper, B. A., & Lui, Y. M. (2010). Visual object tracking using adaptive correlation filters. In 2010 IEEE computer society conference on computer vision and pattern recognition (pp. 2544-2550). San Francisco: IEEE.
Chotsisuparat, N. (2020). The numerical studies of the modified van der pol equation in electrical circuits (Master’s thesis). Srinakharinwirot University. Bangkok. (in Thai)
Christen, P., Hand, D. J., & Kirielle, N. (2023). A review of the F-measure: its history, properties, criticism, and alternatives. ACM Computing Surveys, 56(3), 1-24. Retrieved from https://bit.ly/4m25kQU
Grabner, H., & Bischof, H. (2006). On-line boosting and vision. In 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR’06) (pp. 260-267). New York: IEEE.
Grabner, H., Grabner, M., & Bischof, H. (2006). Real-time tracking via on-line boosting. In Proceedings of the British Machine Vision Conference (p. 6.1-6.10). Edinburgh: BMVA Press
Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2015). High-speed tracking with kernelized correlation filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(3), 583-596. https://doi.org/10.1109/TPAMI.2014.2345390
Kalal, Z., Matas, J., & Mikolajczyk, K. (2012). Tracking-learning-detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(7), 1409–1422. https://doi.org/10.1109/TPAMI.2011.239
Kowalski, M. Ł., Pałka, N., Młyńczak, J., Karol, M., Czerwińska, E., Życzkowski, M., Ciurapiński, W., Zawadzki, Z., & Brawata, S. (2021). Detection of inflatable boats and people in thermal infrared with deep learning methods. Sensors, 21(16), 5330. https://doi.org/10.3390/s21165330
Kristan, M., Matas, J., Leonardis, A., Felsberg, M., Cehovin, L., Fernandez, G., & Pflugfelder, R. (2015). The visual object tracking vot2015 challenge results. In Proceedings of the IEEE International Conference on Computer Vision Workshops. Santiago: IEEE
Lukežič, A., Vojíř, T., Čehovin, L., Matas, J., & Kristan, M. (2018). Discriminative correlation filter tracker with channel and spatial reliability. International Journal of Computer Vision (IJCV), 126, 671–688. https://doi.org/10.48550/arXiv.1611.08461
Mangale, S., & Khambete, M. (2016). Camouflaged target detection and tracking using thermal infrared and visible spectrum imaging. In Intelligent Systems Technologies and Applications 2016 (pp. 193-207). Cham: Springer International Publishing.
Shen, Y., Li, J., Lin, W., Chen, L., Huang, F., & Wang, S. (2021). Camouflaged target detection based on snapshot multispectral imaging. Remote Sensing, 13(19), 3949. https://doi.org/10.3390/rs13193949
Shopovska, I., Jovanov, L., & Philips, W. (2019). Deep visible and thermal image fusion for enhanced pedestrian visibility. Sensors, 19(17), 3727. https://doi.org/10.3390/s19173727
Wu, Y., Lim, J., & Yang, M. H. (2013). Online object tracking: A benchmark. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2411-2418). Portland: IEEE
Zhang, J., Yang, G., Liu, A., & Chen, X. (2023, November). A Data Augmentation Method Based on Multi-Modal Image Fusion for Detection and Segmentation. In 2023 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) (pp. 1-5). Xi’an: IEEE.
Zhang, Y., Wang, T., Liu, K., Zhang, B., & Chen, L. (2021). Recent advances of single-object tracking methods: A brief survey. Neurocomputing, 455, 1-11. https://doi.org/10.1016/j.neucom.2021.05.011
Mangale, S., & Khambete, M. (2016). Camouflaged target detection and tracking using thermal infrared and visible spectrum imaging. In: J. Corchado Rodriguez, S. Mitra, S. Thampi, & ES. El-Alfy, (Eds), Intelligent Systems Technologies and Applications 2016. ISTA 2016. Advances in Intelligent Systems and Computing, vol 530 (pp 193–207). Cham: Springer.
Yang Liu, Cong-Qing Wang, Bin Xu, and Yong-Jun Zhou (2023). Aerial tracking of camouflaged people in woodlands, Journal of Electronic Imaging, 32(6), 063018. https://doi.org/10.1117/1.JEI.32.6.063018
