Goat farming is one of the pillar industries for sustainable development of national economies in some countries and plays an active role in social and economic development. In order to realize the precision and intelligence of goat breeding, this paper describes an integrated goat detection and counting method based on deep learning. First, we constructed a new dataset of video images of goats for the object tracking task. Then, we took YOLOv5 as the baseline of the object detector and improved it using a series of advanced methods, including: using RandAugment to explore suitable data augmentation strategies in a real goat barn environment, using AF-FPN to improve the network’s ability to represent multi-scale objects, and using the Dynamic Head framework to unify the attention mechanism with the detector’s heads to improve its performance. The improved detector achieved 92.19% mAP, a significant improvement compared to the 84.26% mAP of the original YOLOv5. In addition, we also input the information obtained by the detector into DeepSORT for goat tracking and counting. The average overlap rate of our proposed method is 89.69%, which is significantly higher than the 82.78% of the original combination of YOLOv5 and DeepSORT. In order to avoid double counting as much as possible, goats were counted using the single-line counting based on the results of goat head tracking, which can support practical applications.

The Chengdu ma goat is an excellent local breed in China. As one of the breeds listed in the National List of Livestock and Poultry Genetic Resources Protection, the protection of its germplasm resources is particularly important. However, the existing breeding and protection methods for them are relatively simple, due to the weak technical force and lack of intelligent means to assist. Most livestock farmers still conduct small-scale breeding in primitive ways, which is not conducive to the breeding and protection of Chengdu ma goats. In this paper, an automatic individual recognition method for Chengdu ma goats is proposed, which saves labor costs and does not depend on large-scale mechanized facilities. The main contributions of our work are as follows: (1) a new Chengdu ma goat dataset is built, which forms the basis for object detection and classification tasks; (2) an improved detection algorithm for Chengdu ma goats based on TPH-YOLOv5 is proposed, which is able to accurately localize goats in high-density scenes with severe scale variance of targets; (3) a classifier incorporating a self-supervised learning module is implemented to improve the classification performance without increasing the labeled data and inference computation overhead. Experiments show that our method is able to accurately recognize Chengdu ma goats in the actual indoor barn breeding environment, which lays the foundation for precision feeding based on sex and age.

The slow loris (Genus Nycticebus) is a group of small, nocturnal and venomous primates with a distinctive locomotion mode. The detection of slow loris plays an important role in the subsequent individual identification and behavioral recognition and thus contributes to formulating targeted conservation strategies, particularly in reintroduction and post-release monitoring. However, fewer studies have been conducted on efficient and accurate detection methods of this endangered taxa. The traditional methods to detect the slow loris involve long-term observation or watching surveillance video repeatedly, which would involve manpower and be time consuming. Because humans cannot maintain a high degree of attention for a long time, they are also prone to making missed detections or false detections. Due to these observational challenges, using computer vision to detect slow loris presence and activity is desirable. This article establishes a novel target detection dataset based on monitoring videos of captive Bengal slow loris (N. bengalensis) from the wildlife rescue centers in Xishuangbanna and Pu’er, Yunnan, China. The dataset is used to test two improvement schemes based on the YOLOv5 network: (1) YOLOv5-CBAM + TC, the attention mechanism and deconvolution are introduced; (2) YOLOv5-SD, the small object detection layer is added. The results demonstrate that the YOLOv5-CBAM + TC effectively improves the detection effect. At the cost of increasing the model size by 0.6 MB, the precision rate, the recall rate and the mean average precision (mAP) are increased by 2.9%, 3.7% and 3.5%, respectively. The YOLOv5-CBAM + TC model can be used as an effective method to detect individual slow loris in a captive environment, which helps to realize slow loris face and posture recognition based on computer vision.