In the trend of large-scale and intensive livestock farming, it has become difficult to monitor the physical health and breeding performance of animals accurately, quickly, and comprehensively in the traditional feeding management mode, and with the development of computer technology, machine vision has been widely used as a non-contact sensor technology. In this work, it reviews the current automatic behavior detection methods. The chapters are summarized with machine vision technology as the core and classical behavior detection techniques are added for comparison. It is classified into three aspects: breeding performance, disease and health, and social behavior, and then discusses in detail daily behaviors (lying, drinking, feeding, lameness, etc.) and complex behaviors (mounting, aggression, tail biting, etc.).

Automatic detection of sow estrus using a lightweight real-time detector and thermal images

Body temperature measurement is a very important task in the sow breeding process. The authors used an infrared camera to detect the temperature of the body surface of the sows, relying on calculating the average of the infrared image temperature in the ear root region. Based on the grayscale value of the target image of the infrared image and the corresponding temperature value of 180 infrared images, a G‐T (Gray‐Temperature ) model was established by linear least squares method, which achieved temperature inversion of each pixel of the target pig. For the different growth stages and different breeds of sows, the R‐square of the all established models is greater than 0.95. The average relative error of the model inversion of the body temperature was only 0.076977%. This means that the body temperature of the sows could be detected without relying on the software. Based on the G‐T model, the authors design a kind of sow's ear root recognition and body surface temperature detection algorithm for different sow population scenarios.

Context: During pig breeding, a change in a pig’s body size is an important indicator that reflects its health. However, it is difficult to extract the necessary features from images to estimate pig body size without contact. Aims: It is crucial to develop a fast and accurate body size estimation algorithm to meet the practical needs of farms, i.e., numerous body size detections. Methods: This report presents a rapid pig body size estimation technique based on deep learning. The YOLOv5 model is enhanced by integrating MobilenetV3, and a lightweight object detection network is introduced as the feature extraction network. An attention mechanism is also added to this system. Following these improvements, the proposed YOLOv5_Mobilenet_SE model is more suitable for the small-target detection of key parts of live pigs. A depth camera was used at a fixed height to capture the pig’s back information, which enables calculations of the critical height, i.e., the body height, of live pigs. Other key measuring points on the pig are generated according to the detection frame of the key parts located by the model. A gradient boosting regression algorithm is used to establish the body size prediction model based on the Euclidean distance between the key measuring points and the actual body size data. Key results: The upgraded YOLOv5_Mobilenet_SE model achieves a mean average precision of 3.9%, which is higher than that obtained using the original YOLOv5 model. The model size is reduced from 91.2 to 10.2 M, and the average detection time for each image is 4.4 ms. The mean absolute percent errors in terms of body size, body width, and body height are 2.02%, 1.95%, and 1.84%, respectively, relative to manual measurements. Conclusions: This method greatly reduces the model size and detection time while ensuring accuracy, and therefore, this method can cut costs for farms performing pig body size measurements. Implications: The results of this study can provide technical support for automated and digital monitoring in the pig breeding industry.

Rapid detection of quarantine diseases in apples is essential for import–export control but remains difficult because routine inspections rely on manual visual checks that limit automation at port scale. A fast, non-destructive system suitable for deployment at customs is therefore needed. In this study, three common apple quarantine pathogens were targeted using hyperspectral images acquired by a close-range hyperspectral camera and analyzed with a convolutional neural network (CNN). Symptoms of these diseases often appear similar in RGB images, making reliable differentiation difficult. Reflectance from 400 to 1000 nm was recorded to provide richer spectral detail for separating subtle disease signatures. To quantify stage-dependent differences, average reflectance curves were extracted for apples infected by each pathogen at early, middle, and late lesion stages. A CNN tailored to hyperspectral inputs, termed HSC-Resnet, was designed with an increased number of convolutional channels to accommodate the broad spectral dimension and with channel and spatial attention integrated to highlight informative bands and regions. HSC-Resnet achieved a precision of 95.51%, indicating strong potential for fast, accurate, and non-destructive detection of apple quarantine diseases in import–export management.

As an important oil crop in China, rapeseed (Brassica campestris) relies heavily on effective pest control to ensure both yield and quality. However, traditional detection methods suffer from high labor dependence, low efficiency, and poor real-time performance. To address these issues, this paper proposes an improved pest detection method based on YOLOv10s, named IAM-YOLO. Specifically, we propose a multi-scale fusion attention module (IAM), and further integrate existing modules, including the Convolution and Attention Fusion Module (CAFM) and the Efficient Channel Attention (ECA) module, to enhance the model’s feature extraction capability and detection accuracy. To validate the effectiveness of the proposed improvements, we constructed an image dataset containing multiple categories of rapeseed pests and designed a series of experiments. Experimental results demonstrate that our improved model outperforms the original YOLOv10s in terms of precision, recall, and mAP. In particular, the model incorporating IAM, CAFM, and ECA modules achieves a precision of 89.7%, representing a 3.9 percentage point improvement over the baseline model, showcasing excellent detection performance. These findings indicate that the proposed method holds significant potential for rapeseed pest detection and provides strong technical support for intelligent pest and disease monitoring in agriculture.