Detection and Analysis of Sow Targets Based on Image Vision

Abstract

In large-scale sow production, real-time detection and recognition of sows is a key step towards the application of precision livestock farming techniques. In the pig house, the overlap of railings, floors, and sows usually challenge the accuracy of sow target detection. In this paper, a non-contact machine vision method was used for sow targets perception in complex scenarios, and the number position of sows in the pen could be detected. Two multi-target sow detection and recognition models based on the deep learning algorithms of Mask-RCNN and UNet-Attention were developed, and the model parameters were tuned. A field experiment was carried out. The data-set obtained from the experiment was used for algorithm training and validation. It was found that the Mask-RCNN model showed a higher recognition rate than that of the UNet-Attention model, with a final recognition rate of 96.8% and complete object detection outlines. In the process of image segmentation, the area distribution of sows in the pens was analyzed. The position of the sow’s head in the pen and the pixel area value of the sow segmentation were analyzed. The feeding, drinking, and lying behaviors of the sow have been identified on the basis of image recognition. The results showed that the average daily lying time, standing time, feeding and drinking time of sows were 12.67 h(MSE 1.08), 11.33 h(MSE 1.08), 3.25 h(MSE 0.27) and 0.391 h(MSE 0.10), respectively. The proposed method in this paper could solve the problem of target perception of sows in complex scenes and would be a powerful tool for the recognition of sows.

Visual Detection of Lost Ear Tags in Breeding Pigs in a Production Environment Using the Enhanced Cascade Mask R-CNN

“…A DCNN offers several advantages in breeding pig production, including high recognition rates, non-invasiveness, minimal animal stress response, and easy deployment. It enables real-time, efficient, and continuous detection, making it suitable for tasks such as individual recognition [4][5][6], pose detection [7][8][9], target tracking [10,11], and count statistics [12,13]. Previous studies have primarily focused on learning the image feature representation of breeding pigs, extracting features, and using image-based classification and object recognition for practical applications.…”

Pig Movement Estimation by Integrating Optical Flow with a Multi-Object Tracking Model

“…The preprocessor employs U-Net and Generative Adversarial Networks (GAN) for feature extraction and is trained on paired clean datasets and datasets with simulated noise. Lei et al [22] introduced a non-contact machine vision method where Mask R-CNN and UNet-Attention were implemented for sow target perception in complex scenarios. Ding et al [23] proposed a method named FD-CNN to detect the regions of the active piglets based on YOLOv5s model.…”

Sow Posture Analysis and Estrus Prediction Using Closed-Circuit Television Cameras

“…However, when attaching sensors to a pig's body, the sensor size, attachment location, attachment durability, and sensor detachment or malfunction must be considered. To address these issues, numerous studies have been conducted to detect sows in CCTV footage, track the detected sows, and analyze their activity levels by calculating how much they move in the video [8][9][10].…”