The prevention and management of crop diseases play an important role in agricultural production, but there are many types of crop diseases and complex causes, and their prevention and identification add difficulties to the process. The traditional methods of identifying diseases mostly rely on human visual and manual inspection, which requires a certain amount of expert knowledge and experience. There are shortcomings such as strong subjectivity and low accuracy. This paper takes the common diseases of kiwifruit as the research object. Based on deep learning and computer vision models, and given the influence of a complex background in actual scenes on the detection of diseases, as well as the shape and size characteristics of diseases, an innovative method of target detection and semantic segmentation was proposed to identify diseases accurately. The main contributions of this research are as follows: We produced the world’s first high-quality dataset on kiwifruit. We used the target detection algorithm YOLOX, we stripped the kiwi leaves from the natural background and removed the influencing factors existing in the complex background. Based on the mainstream semantic segmentation networks UNet and DeepLabv3+, the experimental results showed that the ResNet101 network achieved the most effective results in the identification of kiwi diseases, with an accuracy rate of 96.6%. We used the training method of learning rate decay to further improve the training effect without increasing the training cost. After experimental verification, our two-stage disease detection algorithm had the advantages of high accuracy, strong robustness, and wide detection range, which provided a more efficient solution for solving the problem of precise monitoring of crop growth environment parameters.

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.

The precise identification of postural behavior plays a crucial role in evaluation of animal welfare and captive management. Deep learning technology has been widely used in automatic behavior recognition of wild and domestic fauna species. The Asian slow loris is a group of small, nocturnal primates with a distinctive locomotion mode, and a large number of individuals were confiscated into captive settings due to illegal trade, making the species an ideal as a model for postural behavior monitoring. Captive animals may suffer from being housed in an inappropriate environment and may display abnormal behavior patterns. Traditional data collection methods are time-consuming and laborious, impeding efforts to improve lorises’ captive welfare and to develop effective reintroduction strategies. This study established the first human-labeled postural behavior dataset of slow lorises and used deep learning technology to recognize postural behavior based on object detection and semantic segmentation. The precision of the classification based on YOLOv5 reached 95.1%. The Dilated Residual Networks (DRN) feature extraction network showed the best performance in semantic segmentation, and the classification accuracy reached 95.2%. The results imply that computer automatic identification of postural behavior may offer advantages in assessing animal activity and can be applied to other nocturnal taxa.

No abstract