A Two-Stage Method to Detect the Sex Ratio of Hemp Ducks Based on Object Detection and Classification Networks

Abstract

The sex ratio is an important factor affecting the economic benefits of duck groups in the process of hemp duck breeding. However, the current manual counting method is inefficient, and the results are not always accurate. On the one hand, ducks are in constant motion, and on the other hand, the manual counting method relies on manpower; thus, it is difficult to avoid repeated and missed counts. In response to these problems, there is an urgent need for an efficient and accurate way of calculating the sex ratio of ducks to promote the farming industry. Detecting the sex ratio of ducks requires accurate counting of male ducks and female ducks. We established the world’s first manually marked sex classification dataset for hemp ducks, including 1663 images of duck groups; 17,090 images of whole, individual duck bodies; and 15,797 images of individual duck heads, which were manually captured and had sex information markers. Additionally, we used multiple deep neural network models for the target detection and sex classification of ducks. The average accuracy reached 98.68%, and with the combination of Yolov5 and VovNet_27slim, we achieved 99.29% accuracy, 98.60% F1 score, and 269.68 fps. The evaluation of the algorithm's performance indicates that the automation method proposed in this paper is feasible for the sex classification of ducks in the farm environment, and is thus a feasible tool for sex ratio estimation.

GAM-YOLOv7-tiny and Soft-NMS-AlexNet: Improved lightweight sheep body object detection and pose estimation network

“…2022 Yu L et al proposed using E cientNet, a lightweight neural network, as a feature extraction network for YOLOv3 and added a SENet attention mechanism to detect the oestrus behavior of female sheep, achieving 99.44% accuracy 7 . In addition, there are some object detection studies on sh and ducks that suggest the feasibility of applying deep learning to animals [8][9][10][11][12] .…”

Interindividual distances and orientations of laying hens under 8 stocking densities measured by integrative deep learning techniques

“…Image classification is one of the tasks that can assign an input image to a predefined category or label and was used to identify individual beef cattle ( Li et al, 2022b ) and monitor broiler behaviors at different ages ( Guo et al, 2022 ). Object detection is a vision task that provides a horizontal rectangular bounding box to identify location and extent of each predefined object in an image and was used to detect pecking behaviors of laying hens ( Subedi et al, 2023 ), measure comfort behavior of laying hens ( Sozzi et al, 2023 ), and mark genders of the hemp ducks ( Zheng et al, 2022 ). Oriented object detection is a computer vision task that renders an oriented or rotated rectangular bounding box fitted to the orientation of each predefined object in an image and was used to identify fish faces ( Li et al, 2022a ), surveillance vehicles ( Shi et al, 2021 ), and detect flights and ships from satellite images ( Han et al, 2022 ).…”

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

“…The acquisition of livestock images using cameras and other means, followed by automated monitoring with the aid of computer vision, can result in substantial labor and equipment cost savings. Zheng Xingze et al estimated the sex of sisal ducks through a two-stage detection method with target detection and a classification network and achieved an accuracy rate as high as 98.68% [ 10 ]. Lin Bin et al conducted a study related to the estimation of fish pose using rotating target detection and a pose estimation algorithm [ 11 ].…”