Pigeon cleaning behavior detection algorithm based on light-weight network

• Proposing a pigeon behavior detection method base on YOLO v4 deep learning algorithm. • Using self-made data sets, comparison of multiple target detection models and comparison of multiple lightweight feature extraction networks. • Comparative study between parameter, weight size, computation, accuracy and FPS. • The proposed method contributes to the development of dovecote inspection robots. The behavior of pigeons in the dovecote reflects their environmental comfort and health indicators. In order to solve the problems of time-consuming, labor-consuming, and subjectivity of traditional manual experience, an improved YOLO V4 light-weight target detection algorithm was proposed for row detection of breeding pigeons. Employ SPP, FPN, and PANet networks to strengthen the features retrieved from GhostNet as the backbone. To ensure accuracy, Ghostnet-yolo V4 reduced the model's number of parameters and raised its size to 43 MB. The light-weight feature extraction network GhostNet outperformed MobileNet V1~V3 under the modified model. Faster RCNN, SSD, YOLO V4 and YOLO V3 compression rates were increased by 43.4 percent, 35.8 percent, 70.1 percent, and 69.1 percent, respectively. The improved algorithm has an accuracy of 97.06 percent and a recognition speed of 0.028 s per frame. The improved model can provide a theoretical foundation and technological reference for detecting breeding pigeon behavior in real-time in a dovecote.