Cattle farming is an important part of the global livestock industry, and cattle body size is the key indicator of livestock growth. However, traditional manual methods for measuring body sizes are not only time-consuming and labor-intensive but also incur significant costs. Meanwhile, automatic measurement techniques are prone to being affected by environmental conditions and the standing postures of livestock. To overcome these challenges, this study proposes a multi-view fusion-driven automatic measurement system for full-attitude cattle body measurements. Outdoors in natural light, three Zed2 cameras were installed covering different views of the channel. Multiple images, including RGB images, depth images, and point clouds, were automatically acquired from multiple views using the YOLOv8n algorithm. The point clouds from different views undergo multiple denoising to become local point clouds of the cattle body. The local point clouds are coarsely and finely aligned to become a complete point cloud of the cattle body. After detecting the 2D key points on the RGB image created by the YOLOv8x-pose algorithm, the 2D key points are mapped onto the 3D cattle body by combining the internal parameters of the camera and the depth values of the corresponding pixels of the depth map. Based on the mapped 3D key points, the body sizes of cows in different poses are automatically measured, including height, length, abdominal circumference, and chest circumference. In addition, support vector machines and Bézier curves are employed to rectify the missing and deformed circumference body sizes caused by environmental effects. The automatic body measurement system measured the height, length, abdominal circumference, and chest circumference of 47 Huaxi Beef Cattle, a breed native to China, and compared the results with manual measurements. The average relative errors were 2.32%, 2.27%, 3.67%, and 5.22%, respectively, when compared with manual measurements, demonstrating the feasibility and accuracy of the system.

Skeleton-based action recognition, which aims to classify human actions through the coordinates of body joints and their connectivity, is a significant research area in computer vision with broad application potential. Although Graph Convolutional Networks (GCNs) have made significant progress in processing skeleton data represented as graphs, their performance is constrained by local receptive fields and fixed joint connection patterns. Recently, researchers have introduced Transformer-based methods to overcome these limitations and better capture long-range dependencies. However, these methods face significant computational resource challenges when attempting to capture the correlations between all joints across all frames. This paper proposes an innovative Spatio-Temporal Graph Convolutional Network: GCN-Former, which aims to enhance model performance in skeleton-based action recognition tasks. The model integrates the Transformer architecture with traditional GCNs, leveraging the Transformer’s powerful capability for handling long-sequence data and the effective capture of spatial dependencies by GCNs. Specifically, this study designs a Transformer Block temporal encoder based on the self-attention mechanism to model long-sequence temporal actions. The temporal encoder can effectively capture long-range dependencies in action sequences while retaining global contextual information in the temporal dimension. In addition, in order to achieve a smooth transition from graph convolutional networks (GCNs) to Transformers, we further develop a contextual temporal attention (CTA) module. These components are aimed at enhancing the understanding of temporal and spatial information within action sequences. Experimental validation on multiple benchmark datasets demonstrates that our approach not only surpasses existing techniques in prediction accuracy, but also has significant performance advantages in handling action recognition tasks involving long time sequences and can more effectively capture and understand long-range dependencies in complex action patterns.

This paper proposes a road crack detection algorithm based on an improved SparseInst network, called the SparseInst-CDSM algorithm, aimed at solving the problems of low recognition accuracy and poor real-time detection of existing algorithms. The algorithm introduces the CBAM module, DCNv2 convolution, SPM strip pooling module, MPM mixed pooling module, etc., effectively improving the integrity and accuracy of crack recognition. At the same time, the central axis skeleton of the crack is extracted using the central axis method, and the length and maximum width of the crack are calculated. In the experimental comparison under the self-built crack dataset, SparseInst-CDSM has an accuracy of 93.66%, a precision of 67.35%, a recall of 66.72%, and an IoU of 84.74%, all higher than mainstream segmentation models such as Mask-RCNN and SOLO that were compared, reflecting the superiority of the algorithm proposed in this paper. The comparison results of actual measurements show that the algorithm error is within 10%, indicating that it has high effectiveness and practicality.

With an improvement in the performance of radio telescopes, the number of pulsar candidates has increased rapidly, which makes selecting valuable pulsar signals from the candidates challenging. It is imperative to improve the recognition efficiency of pulsars. Therefore, we solved this problem from the perspective of intelligent image processing and a deep neural network model AR_Net was proposed in this paper. A single time–phase-subgraph or frequency-phase-subgraph was used as the judgment basis in the recognition model. The convolution blocks can be obtained by combining the attention mechanism module, feature extractor and residual connection. Then, different convolution blocks were superimposed to constitute the AR_Net to screen pulsars. The attention mechanism module was used to calculate the weight through an additional feedforward neural network and the important features in the sample were identified by weight, so the ability of the model to learn pivotal information was improved. The feature extractor was used to gain the high-dimensional features in the samples and the residual connection was introduced to alleviate the problem of network degradation and intensify feature reuse. The experimental results show that AR_Net has higher F1-score, recall and accuracy, and our method produces a competitive result compared with previous methods.

We propose MTC-BEV, a novel multi-modal 3D object detection framework for autonomous driving that achieves robust and efficient perception by combining spatial, temporal, and semantic cues. MTC-BEV integrates image and LiDAR features in the Bird’s-Eye View (BEV) space, where heterogeneous modalities are aligned and fused through the Bidirectional Cross-Modal Attention Fusion (BCAP) module with positional encodings. To model temporal consistency, the Temporal Fusion (TTFusion) module explicitly compensates for ego-motion and incorporates past BEV features. In addition, a segmentation-guided BEV enhancement projects 2D instance masks into BEV space, highlighting semantically informative regions. Experiments on the nuScenes dataset demonstrate that MTC-BEV achieves a nuScenes Detection Score (NDS) of 72.4% at 14.91 FPS, striking a favorable balance between accuracy and efficiency. These results confirm the effectiveness of the proposed design, highlighting the potential of semantic-guided cross-modal and temporal fusion for robust 3D object detection in autonomous driving.

Due to its high dependence on labeled data, animal pose estimation faces significant challenges in practical applications. Effectively utilizing large amounts of unlabeled data to improve the accuracy of pose estimation has become an urgent research topic to be addressed. In this paper, we propose the MVCRNet, which is designed to label a minimal amount of data at a low cost, while effectively utilizing large amounts of unlabeled data for accurate animal pose estimation. We first train an initial model on the limited set of labeled samples, and then use this model to generate preliminary pseudo-labels for the unlabeled data. Given the inevitable presence of noise in these pseudo-labels, the framework adopts the small loss trick coupled with confidence evaluation to retain only those pseudo-labels that satisfy both low loss and high confidence. However, this approach may be overly cautious, potentially discarding pseudo-labels of inferior quality that still contain learning value. To address this problem, we innovatively incorporate a multi-view based triple consistency checking strategy aimed at detecting and relabeling pseudo-labels containing potential learning value within high-loss, low-confidence samples, and a teacher-student consistency constraint strategy that further strengthens the stability and accuracy of the model throughout the training process. Experimental evaluations on two challenging datasets, AP-10K and Zebra, show that our method consistently outperforms existing semi-supervised algorithms, demonstrating its effectiveness and sophistication for animal pose estimation under data-constrained conditions. Our code and datasets are available at https://github.com/cf2xh123/MVCRNet.