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

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.

Developing Edge AI Computer Vision for Smart Poultry Farms Using Deep Learning and HPC

“…The final model achieved accuracy of AP = 89.73%, AP50 = 98.35%, and AP75 = 96.23%. We have not identified a research to directly compare, but the results are comparable with a similar research on instance segmentation in geese images [ 26 ]. The authors were developing their own model and compared it to different instance segmentation networks and in this process reporter values around 81%, 96%, 90% for AP, AP50 and AP75, respectively.…”

“…The paper [ 25 ] deals with the assessment of gender ratio in which they state that the accuracy of their model is almost 97%. In the research [ 26 ] authors deal with instance segmentation tasks for a goose. They stated that AP50 for both detection and segmentation is 96%.…”

HSDNet: a poultry farming model based on few-shot semantic segmentation addressing non-smooth and unbalanced convergence

“…For instance, Li et al (2022a) have utilized target detection technology for carp identification, significantly reducing costs compared to traditional embedded chip methods. Similarly, Li et al (2022b) employed instance segmentation for intelligent monitoring of geese, testing in real-time on embedded devices to ensure feasibility for large-scale deployment. Jiang et al (2022) used target detection technology to identify the sex of ducks and improve returns.…”