Personnel detection in a coal mine is of great significance for monitoring the safety and real-time positioning of underground personnel. However, the uneven illumination, large dust, imaging noise, and other factors give the existing methods a high false detection rate for personnel detection. To overcome this problem, an improved YOLOv4 network for personnel detection based on thermal infrared images is proposed. First, the infrared personnel images are preprocessed by the method of super-resolution convolutional neural network to enhance their resolutions. Second, to improve the detection performance of the YOLOV4 network, the K-means++ clustering is used to optimize the anchor boxes estimation before the network training. Third, to further strengthen the generalization ability of the YOLOv4 and reduce the complexity of network training, the strategy of transfer learning is applied to train the YOLOv4 network. Experimental results show that on the infrared personnel image dataset underground coal mine, the improved YOLOv4 model achieves 96.25% and 48.2 fps in global AP and detection speed, respectively. Moreover, the improved YOLOv4 model has the advantages of strong robustness and generalization ability, which is very suitable for underground personnel detection, and provides a strong guarantee for the safety monitoring and management of coal mine personnel.

In the process of collecting facial images of cattle in the field, some features of the collected images end up going missing due to the changeable posture of the cattle, which makes the recognition accuracy decrease or impossible to recognize. This paper verifies the practical effects of the classical matching algorithms ORB, SURF, and SIFT in bull face matching recognition. The experimental results show that the traditional matching algorithms perform poorly in terms of matching accuracy and matching time. In this paper, a new matching recognition model is constructed. The model inputs the target cattle facial data from different angles into the feature extraction channel, combined with GMS (grid-based motion statistics) algorithm and random sampling consistent algorithm, to achieve accurate recognition of individual cattle, and the recognition process is simple and fast. The recognition accuracy of the model was 85.56% for the Holstein cow face dataset, 82.58% for the Simmental beef cattle, and 80.73% for the mixed Holstein and Simmental beef cattle dataset. The recognition model constructed in the study can achieve individual recognition of cattle in complex environments, has good robustness to matching data, and can effectively reduce the effects of data angle changes and partial features missing in cattle facial recognition.

The common non-contact, automatic body size measurement methods based on the whole livestock point cloud are complex and prone to errors. Therefore, a cattle body measuring system is proposed. The system includes a new algorithm called dynamic unbalanced octree grouping (DUOS), based on PointNet++, and an efficient method of body size measurement based on segmentation results. This system is suitable for livestock body feature sampling. The network divides the cow into seven parts, including the body and legs. Moreover, the key points of body size are located in the different parts. It combines density measurement, point cloud slicing, contour extraction, point cloud repair, etc. A total of 137 items of cattle data are collected. Compared with some of the other models, the DUOS algorithm improves the accuracy of the segmentation task and mean intersection by 0.53% and 1.21%, respectively. Moreover, compared with the manual measurement results, the relative errors of the experimental measurement results are as follows: withers height, 1.18%; hip height, 1.34%; body length, 2.52%; thoracic circumference, 2.12%; abdominal circumference, 2.26%; and cannon circumference, 2.78%. In summary, the model is proven to have a good segmentation effect on cattle bodies and is suitable for cattle body size measurement.

Monitoring the body condition of dairy cows is essential for ensuring their health and productivity, but traditional BCS methods—relying on visual or tactile assessments by skilled personnel—are subjective, labor-intensive, and impractical for large-scale farms. To overcome these limitations, we present BCS-YOLO, a lightweight and automated BCS framework built on YOLOv8, which enables consistent, accurate scoring under complex conditions with minimal computational resources. BCS-YOLO integrates the Star-EMA module and the Star Shared Lightweight Detection Head (SSLDH) to enhance the detection accuracy and reduce model complexity. The Star-EMA module employs multi-scale attention mechanisms that balance spatial and semantic features, optimizing feature representation for cow hindquarters in cluttered farm environments. SSLDH further simplifies the detection head, making BCS-YOLO viable for deployment in resource-limited scenarios. Additionally, channel-based knowledge distillation generates soft probability maps focusing on key body regions, facilitating effective knowledge transfer and enhancing performance. The results on a public cow image dataset show that BCS-YOLO reduces the model size by 33% and improves the mean average precision (mAP) by 9.4%. These advances make BCS-YOLO a robust, non-invasive tool for consistent and accurate BCS in large-scale farming, supporting sustainable livestock management, reducing labor costs, enhancing animal welfare, and boosting productivity.

With the Chinese data for solid rocket engines, traditional named entity recognition cannot be used to learn both character features and contextual sequence-related information from the input text, and there is a lack of research on the advantages of dual-channel networks. To address this problem, this paper proposes a BERT-based dual-channel named entity recognition model for solid rocket engines. This model uses a BERT pre-trained language model to encode individual characters, obtaining a vector representation corresponding to each character. The dual-channel network consists of a CNN and BiLSTM, using the convolutional layer for feature extraction and the BiLSTM layer to extract sequential and sequence-related information from the text. The experimental results showed that the model proposed in this paper achieved good results in the named entity recognition task using the solid rocket engine dataset. The accuracy, recall and F1-score were 85.40%, 87.70% and 86.53%, respectively, which were all higher than the results of the comparison models.