In recent years, remote photoplethysmography (rPPG) technology has made significant strides in non-contact health monitoring. However, existing methods are often constrained by high computational costs and large model parameter sizes, making them unsuitable for resource-constrained environments. To address these challenges, we propose CTA-Net, a lightweight rPPG estimation network that integrates a Channel-Temporal Attention Module (CTAM) to efficiently capture spatiotemporal features associated with rPPG signals. By constructing a multi-scale spatiotemporal map (MSTMap) through the fusion of RGB and YUV color spaces, CTA-Net enhances feature extraction capabilities while maintaining low computational complexity. The proposed method demonstrates outstanding performance on the PURE, COFACE, and UBFC datasets, achieving state-of-the-art (SOTA) results on the PURE and COFACE datasets, and near-SOTA performance on the UBFC dataset. Compared to representative deep learning models in the field, our method significantly reduces the model parameters and computational workload, showcasing a significant lightweight advantage. Furthermore, ablation studies validate the effectiveness of the MSTMap fusion strategy, CTAM configuration, activation function choice, and Cosine Annealing Learning Rate (CALR) adjustment in improving model performance. Overall, the proposed method strikes an optimal balance between estimation accuracy and computational efficiency. Our codes will be available at https://github.com/Jry-M/CTA-Net.git.

The basic task of vehicle density estimation is to use image information to estimate the distribution and quantity of vehicles within it. However, many previous methods only use the optical information in red-green–blue (RGB) images, which makes it difficult to effectively identify potential vehicles under poor light, strong reflections, and bad weather, resulting in unsatisfactory density estimation performance. To address these problems, we consider introducing thermal images to provide a richer source of information for the vehicle density estimation task, and propose a multimodal feature fusion network (MFCNet) for accurate RGB-Thermal (RGB-T) vehicle density estimation. First, multimodal features are cross-integrated through the attention-guided multiscale feature fusion coordination module (MFFC) to compensate for the limitations of single modal features. Following this, the edge feature calibration module (EFC) is utilized to correct the spatial misalignment regions between modalities. Subsequently, the adaptive deep fusion module (ADFM) is applied to further refine the features on the global scale and improve the intermodality correlation. Finally, the features of different stages are fused step by step to obtain the final fused feature, which is fed into a simple regression header to generate a pixel-level vehicle density map. Experimental results show that the GAME2 and root mean square error of the proposed method are reduced to 5.21 and 3.54 on the DroneVehicle dataset, respectively. Compared with existing vehicle density estimation methods, MFCNet achieves competitive accuracy and can be applied to the vehicle density estimation task in unconstrained scenarios. Our codes will be available athttps://github.com/QLingX/MFCNet.

Student engagement in online learning is an important indicator for measuring learning effectiveness. Due to the fact that facial video data of students during online learning contains a wider range of information such as time, current research has begun to focus on obtaining student engagement from video data. These studies primarily rely on supervised learning methods and have achieved certain success. However, the longstanding lack of large-scale and high-quality labeled data, as well as the time-consuming and laborious sample labeling work, have to some extent hindered their further improvement. To solve this problem, this paper proposes a self-supervised learning method, Facial Masked Autoencoder (FMAE), which is used to construct a student engagement recognition model. This method uses a masked autoencoder to process a large number of unlabeled facial videos, and performs self-supervised pre-training by learning masked facial features from the reconstruction process. In order to promote the encoder to better mask learning for the face, a new facial mask strategy and reconstruction module have been proposed. With this method, the model can not only focus on important facial regions, but also obtain more accurate appearance features and spatio-temporal details. Experiments have demonstrated that the proposed method achieves excellent results on DAiSEE and EmotiW datasets, showing its potential in the task of student engagement recognition.

The automatic extraction of lake water is one of the research hotspots in the field of remote sensing image processing. Due to the small inter-class variance between lakes and other ground objects, and the complex texture characteristics of lake boundaries, existing methods often have problems such as over-segmentation and inaccurate boundary segmentation when segmenting lake water bodies. To alleviate these problems, this paper designs an end-to-end semantic segmentation network (NT-Net) for the automatic extraction of lake water bodies from remote sensing images. Aiming at the problem of over-segmentation caused by non-lake objects, an interference attenuation module is designed in the network. This module can model the key features that are distinguishable and suitable for segmenting lake water by analyzing the difference in feature representation between lakes and other ground objects, thereby suppressing the feature representation of non-lake objects. To more accurately segment the lake boundary, a Multi-level Transformer module is designed. This module can capture the context association of boundary information and enhance the feature representation of boundary information by using the self-attention mechanism. The comparative experimental results show that, compared with the current mainstream semantic segmentation networks, the method in this paper has advantages in extracting lake water bodies comprehensively and coherently.

Aiming at the problems of colour distortion and residual dehazing in the existing image dehazing methods when processing outdoor images, a method of image dehazing based on the cycle generative adversarial network is proposed. Taking the cycle generative adversarial network as the overall framework of the model, firstly, the neural network is trained to obtain the mapping relationship between haze images and haze‐free images. Secondly, to accelerate the convergence speed of network training, using residual structure to improve network stability and reduce parameters. Then, a new loss function is proposed, fusing the Wasserstein distance into adversarial loss and cycle consistency loss, which reduces the deviation between the generated dehaze image and the real haze‐free image, and alleviating the problems of colour distortion and haze removal residue. Finally, use the optimised bounded ReLU (BReLU) activation function instead of the original activation function to improve the transmittance reflecting the haze depth information. The experimental results demonstrated that, compared with the comparison method, the proposed method improves the peak signal‐to‐noise ratio, structure similarity, information entropy, and average gradient, and has an achieved better performance in dehazing.

Abstract Virtual endoscopy is a technique to explore hollow organs and anatomical cavities using 3D medical imaging and computer graphics. In this paper, boundary model and local feature structure are used to realize tissue segmentation, and a new efficient algorithm is presented to solve path planning. As to real‐time processing, a frame in virtual endoscopy is divided into near viewpoint part and far viewpoint part based on volume data characteristics in our method. In the aspect of scene rendering, a ray casting algorithm based on the boundary voxel is proposed. Thus the voyage images can be rendered in real time with high quality in virtual endoscopy system by using these techniques. The experiments show that application results of our algorithm in tissue segmentation, path planning, scene rendering are better than other algorithms. Copyright © 2011 John Wiley & Sons, Ltd.