Automatic detection of sow posture and estrus based on convolutional neural network

Abstract

Estrus detection is an essential operation in the breeding of sows, and accurate estrus detection is immensely important to maintain the productivity and reproductive performance of sow. However, traditional sow estrus detection relies on the manually back-pressure test, which is time-consuming and labor-intensive. This study aimed to develop an automatic method to detect estrus. In this study, a model based on the optimized yolov5s algorithm was constructed to detect the four sow postures of standing, sitting, sternum, lateral, and calculated the frequency of posture change in sows. Based on this, we studied the behavior of sows before and after estrus. The method embedded a convolutional block attention module into the backbone network to improve the feature extraction capability of the model. In addition, the object box judgment module was used to avoid interference from other sows in the detection region. Accelerate the optimized model on the TensorRT platform, ensuring that the embedded graphics card can run the model with lower latency. The result shows that the precision of estrus detection is 97.1%, and the accuracy of estrus detection is 94.1%. The processing time of a single image on the embedded graphics card is 74.4 ms, and this method could better meet the estrus detection demand in sow production.