CONTINUAL YOLO-BASED DETECTION FOR LONG-TERM MONITORING OF THE GREATER ONE-HORNED RHINO
DOI:
https://doi.org/10.53555/qn83mp49Keywords:
Continual Object Detection, Wildlife monitoring, YOLO, replay memory, self-distillation, human-in-loop, catastrophic forgettingAbstract
YOLO-based object detectors support fast wildlife monitoring across diverse habitats. Static training limits these detectors in the field because ecological conditions shift over time. Continual learning provides an incremental update process that preserves earlier knowledge while absorbing new information.
This article reviews recent progress in continual learning for YOLO detection, with emphasis on experience replay, self-distillation, and human-in-the-loop supervision. These approaches protect past knowledge, reduce annotation demands, and deliver more stable predictions during long-term deployments.
A focused case study on Greater One-Horned Rhino monitoring shows how adaptive learning pipelines strengthen detection reliability during seasonal changes, altered terrain, and new camera placements. The review outlines methods with strong potential for long-term conservation work and highlights future directions for resilient wildlife monitoring systems.
References
[1] R. De Monte, D. Dalle Pezze, and G. A. Susto, “Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detection,” arXiv:2503.04688, 2025.
[2] J.-L. Shieh, Q. M. U. Haq, M. A. Haq, S. Karam, P. Chondro, D.-Q. Gao, and S.-J. Ruan, “Continual Learning Strategy in One-Stage Object Detection Framework Based on Experience Replay for Autonomous Driving Vehicle,” Sensors, vol. 20, no. 23, p. 6777, 2020.
[3] J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” arXiv:1804.02767, 2018.
[4] K. Li, M. Shan, S. B. Perez, K. Luo, and S. Worrall, “Endangered Alert: A Field-Validated Self-Training Scheme for Detecting and Protecting Threatened Wildlife on Roads and Roadsides,” arXiv:2412.12222, 2024.
[5] J. Boulent, B. Charry, M. M. Kennedy, E. Tissier, R. Fan, M. Marcoux, C. A. Watt, and A. Gagné-Turcotte, “Scaling Whale Monitoring Using Deep Learning: A Human-in-the-Loop Solution for Analyzing Aerial Datasets,” Frontiers in Marine Science, vol. 10, p. 1099479, 2023.
[6] S. E. Huebner, M. S. Palmer, and C. Packer, “Human Supervision Is Key to Achieving Accurate AI-Assisted Wildlife Identifications in Camera Trap Images,” Citizen Science: Theory and Practice, vol. 9, no. 1, 2024.
[7] G. I. Parisi, R. Kemker, J. L. Part, C. Kanan, and S. Wermter, “Continual Lifelong Learning With Neural Networks: A Review,” Neural Networks, vol. 113, pp. 54–71, 2019.
[8] Y. Xu, Y. Wu, and X. Wang, “Continual Object Detection: A Review,” arXiv:2205.15445, 2022.
[9] E. Fini, S. Lathuilière, E. Sangineto, M. Nabi, and E. Ricci, “Online Continual Learning Under Extreme Memory Constraints,” in Proc. ECCV, 2020, pp. 704–720.
[10] R. De Monte, D. Dalle Pezze, M. Ceccon, F. Pasti, F. Paissan, E. Farella, G. A. Susto, and N. Bellotto, “Replay Consolidation With Label Propagation for Continual Object Detection,” arXiv:2409.05650, 2024.
[11] M. De Lange et al., "A Continual Learning Survey: Defying Forgetting in Classification Tasks," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 7, pp. 3366-3385, 1 July 2022, doi: 10.1109/TPAMI.2021.3057446.
[12] Beery, S., Van Horn, G., Perona, P. (2018). Recognition in Terra Incognita. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds) Computer Vision – ECCV 2018. ECCV 2018. Lecture Notes in Computer Science(), vol 11220. Springer, Cham. https://doi.org/10.1007/978-3-030-01270-0_28
[13] S. K. Beery et al., “The iWildCam 2020 Competition Dataset: Evaluating Transfer Learning for Wildlife Classification,” arXiv:2004.10340, 2020.
[14] C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors,” arXiv:2207.02696, 2022.
[15] M. Masana, X. Liu, B. Twardowski, M. Menta, A. D. Bagdanov and J. van de Weijer, "Class-Incremental Learning: Survey and Performance Evaluation on Image Classification," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 5, pp. 5513-5533, 1 May 2023, doi: 10.1109/TPAMI.2022.3213473.
[16] Schneider, Stefan & Taylor, Graham & Linquist, Stefan & Kremer, Stefan. (2018). “Past, Present and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data.”, Methods in Ecology and Evolution, vol . 10, doi: 10.1111/2041-210X.13133.
[17] M.S. Norouzzadeh,A. Nguyen,M. Kosmala,A. Swanson,M.S. Palmer,C. Packer, & J. Clune, Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning, Proc. Natl. Acad. Sci. U.S.A. 115 (25) E5716-E5725, https://doi.org/10.1073/pnas.1719367115 (2018).
[18] Fraunhofer IIS, “Continual Learning in Object Detection,” Fraunhofer Technical Report, 2023.
[19] S. Vasavi, V. Sripathi, and C. M. Simma, “Visualization of Humpback Whale Tracking on Edge Device Using Space-Borne Remote Sensing Data,” Egyptian Journal of Remote Sensing and Space Sciences, vol. 27, no. 4, pp. 705–715, 2024.
[20] S. Farquhar and Y. Gal, “Towards Robust Evaluations of Continual Learning,” arXiv:1805.09733, 2019.
[21] L. Chen, G. Li, S. Zhang, W. Mao, and M. Zhang, “YOLO-SAG: An Improved Wildlife Object Detection Algorithm Based on YOLOv8n,” Ecological Informatics, vol. 83, 102791, 2024.
[22] A. P. Naidu, H. Gosalia, I. Gakhar, S. S. Rathore, K. Didwania, and U. Verma, “DEAL-YOLO: Drone-Based Efficient Animal Localization Using YOLO,” arXiv:2503.04698, 2025.
[23] N. R. Varte, K. Bhattacharyya, and N. Saikia, “Advancing Environmental Monitoring: YOLO Algorithm for Real-Time Detection of Greater One-Horned Rhinos,” International Journal of Environmental Science, 2025.
[24] N. R. Varte et al., "Animal Detection and Alert System for Road Safety," 2025 IEEE Guwahati Subsection Conference (GCON), Itanagar, India, 2025, pp. 1-6, doi: 10.1109/GCON65540.2025.11173390.
[25] N. R. Varte, K. Bhattacharyya, and N. Saikia, “Advancing Greater One-Horned Rhino Conservation: A YOLO Instance Segmentation Framework with Morphological and Semantic False Positive Suppression,” Journal of Environmental Protection and Ecology, vol. 26, no. 6, pp. 2427–2438, 2025.
