Multimodal Bird Monitoring System Integrating Micro-Motion Detection and Gimbal Control YOLOv8 Optimization and Laser Deterrence System
To mitigate aviation safety risks, agricultural damage, and power outages caused by bird activities, this study introduces a bird recognition and dynamic deterrence system that combines You Only Look Once version 8 (YOLOv8) object detection, advanced micro-motion detection algorithms, and intelligent gimbal control. Traditional bird deterrent methods are often inefficient and lack adaptability, while current detection systems struggle with accuracy and real-time tracking of small, fast-moving targets. By integrating the Lucas-Kanade optical flow technique with the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering algorithm, this research develops a multiscale, adaptive micro-motion detection model that effectively captures subtle bird movements while minimizing noise interference. This model is further enhanced by YOLOv8, utilizing an upgraded Cross-Stage Partial Network to 2-Stage FPN (C2f) architecture, the TaskAlignedAssigner for more accurate sample allocation, and dynamic Mosaic data augmentation for improved detection precision and speed. In addition, a gimbal control algorithm based on spatial registration and adaptive zoom adjustment ensures precise target localization and laser deterrence, employing a two-degree-of-freedom coordinate transformation and a 30x optical zoom field-of-view fitting function.
References
- Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788.
- Bergstra J, Bengio Y. Random search for hyper-parameter optimization [J]. The journal of machine learning research, 2012, 13(1): 281-305.
- Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arxiv preprint arxiv:1409.1556, 2014.
- Ren S, He K, Girshick R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 2015, 28.
- Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25.
- Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector[C]//Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer International Publishing, 2016: 21-37.
- Li M, Zhang Z, Lei L, et al. Agricultural greenhouses detection in high-resolution satellite images based on convolutional neural networks: Comparison of faster R-CNN, YOLO v3 and SSD[J]. Sensors, 2020, 20(17): 4938.
- Geiger A, Lenz P, Urtasun R. Are we ready for autonomous driving? the kitti vision benchmark suite[C]//2012 IEEE conference on computer vision and pattern recognition. IEEE, 2012: 3354-3361.
- Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision[C]//IJCAI'81: 7th international joint conference on Artificial intelligence. 1981, 2: 674-679.
- Sharp T, Keskin C, Robertson D, et al. Accurate, robust, and flexible real-time hand tracking[C]//Proceedings of the 33rd annual ACM conference on human factors in computing systems. 2015: 3633-3642.
- Bochkovskiy A, Wang C Y, Liao H Y M. Yolov4: Optimal speed and accuracy of object detection[J]. arxiv preprint arxiv:2004.10934, 2020.
- Marvasti-Zadeh S M, Cheng L, Ghanei-Yakhdan H, et al. Deep learning for visual tracking: A comprehensive survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(5): 3943-3968.
- Tuia D, Kellenberger B, Beery S, et al. Perspectives in machine learning for wildlife conservation[J]. Nature communications, 2022, 13(1): 792.