Study of a QueryPNet Model for Accurate Detection and Segmentation of Goose Body Edge Contours

SIMPLE SUMMARY: Precision animal husbandry based on computer vision has developed promptly, especially in poultry farming. It is believed to improve animal welfare. To achieve the precise target detection and segmentation of geese, which can improve data acquisition, we newly built the world’s first goose instance segmentation dataset. Moreover, a high-precision detection and segmentation model was constructed, and the final mAP@0.5 of both target detection and segmentation reached 0.963. The evaluation of the model showed that the automated detection method proposed in this paper is feasible in a complex environment and can serve as a reference for the relevant development of the industry. ABSTRACT: With the rapid development of computer vision, the application of computer vision to precision farming in animal husbandry is currently a hot research topic. Due to the scale of goose breeding continuing to expand, there are higher requirements for the efficiency of goose farming. To achieve precision animal husbandry and to avoid human influence on breeding, real-time automated monitoring methods have been used in this area. To be specific, on the basis of instance segmentation, the activities of individual geese are accurately detected, counted, and analyzed, which is effective for achieving traceability of the condition of the flock and reducing breeding costs. We trained QueryPNet, an advanced model, which could effectively perform segmentation and extraction of geese flock. Meanwhile, we proposed a novel neck module that improved the feature pyramid structure, making feature fusion more effective for both target detection and instance individual segmentation. At the same time, the number of model parameters was reduced by a rational design. This solution was tested on 639 datasets collected and labeled on specially created free-range goose farms. With the occlusion of vegetation and litters, the accuracies of the target detection and instance segmentation reached 0.963 (mAP@0.5) and 0.963 (mAP@0.5), respectively.