ABSTRACT Detecting student behaviour objects in classroom environments is crucial for assessing educational progress, optimizing teaching strategies and improving student learning outcomes. With the ongoing advancement of educational informatization, analysing classroom behaviour has become an important tool for enhancing teaching quality and personalized learning. However, current student behaviour object detection models based on CNN and Transformer architectures face challenges such as large parameter sizes and high inference delays when deployed on edge devices in classrooms, limiting their practical application. To address these issues, this study proposes a lightweight student behaviour detection framework based on the Mamba architecture, aimed at balancing computational efficiency and detection accuracy. First, the framework based on the state‐space model (SSM) efficiently captures global dependencies, using local convolutions to enhance detection accuracy and scene understanding while maintaining real‐time performance. Second, the C2CGA module increases attention diversity through feature splitting, self‐attention, cascading and projected concatenation, deepening the network while reducing computational overhead. Finally, the A2CMoCA module aggregates multi‐scale features, improving the learning of small objects and occluded behaviours. Experiments on a self‐built classroom behaviour dataset (containing eight typical teaching behaviours) show that the proposed method achieves 91.5% detection accuracy while maintaining a lightweight design. Compared to the baseline model, its computational efficiency (5.9G FLOPs) is reduced by 56.6%, the parameter size is compressed to 3.65 M (a 39% reduction) and the inference speed is 3.2 ms, meeting the real‐time monitoring requirements in classroom teaching scenarios.

Low-Light Image Enhancement (LLIE) methods based on either Retinex theory or deep learning still exhibit significant shortcomings in handling image corruptions, such as noise, artifacts, and color distortion. The primary issue is that both Retinex algorithms and existing networks may introduce or amplify these corruptions during enhancement. To address these limitations, we propose the Denoised-Modulated Hybrid-Semantic Scale-Aware Network (DHSNet), a novel one-stage LLIE method. DHSNet integrates a Signal-to-Noise Ratio (SNR)-based denoising mechanism and a Hybrid-Semantic Scale-Aware Module (HSM) to preprocess noise and fuse multi-scale features for robust image enhancement. Moreover, we introduce the Illumination Partial Attention Block (IPAB) to further improve illumination correction and nonlinear transformation capabilities. DHSNet effectively mitigates noise, preserves intricate details, and restores degraded structures. Extensive experiments on multiple LLIE datasets demonstrate that it outperforms state-of-the-art (SOTA) methods in both qualitative and quantitative metrics. Furthermore, DHSNet exhibits strong generalization in no-reference LLIE and low-light object detection tasks, underscoring its practical value for real-world applications.

ABSTRACT Real‐time monitoring of fires is crucial for safeguarding lives and property. However, current fire detection methods still suffer from issues such as redundant feature information, poor network generalisation capabilities and low perception of target location information. To address these challenges, a novel fire detection method called YOLO‐FDI has been proposed. This method utilises partial convolution and coordinate convolution with attention mechanisms and Alpha loss at different stages. Specifically, to enhance target localisation accuracy, an attention mechanism is integrated into the model to autonomously focus on fire‐affected areas. In terms of feature extraction, partial convolution is employed to reduce computational redundancy and memory access, improving performance and effectively extracting spatial features. During the feature fusion stage, coordinate convolution embeds feature information into coordinate data, further enhancing the coordinate perception capabilities of pixels on the feature map, thereby improving adaptability and accuracy in detecting fire targets. Additionally, the model utilises Alpha loss to enhance flexibility and robustness in fire object detection and recognition. Experimental results demonstrate the effectiveness of the proposed model based on three self‐constructed datasets. Compared to the baseline YOLOv7 model, its mAP has improved by 4.5 percentage points, 1.7 percentage points and 2.6 percentage points, respectively. This method demonstrates the capability to accurately represent fire targets and exhibits better stability and reliability in fire target detection, effectively reducing false positives and missed detections.

To fully leverage contextual information for the precise segmentation of objects in remote sensing images, while addressing the challenges associated with substantial object scale variations and complex backgrounds, we propose a lightweight cross-domain coupling network (LCCN) tailored for semantic segmentation of high-resolution remote sensing images (HRSIs). To standardize feature selection and fusion procedures, the LCCN incorporates an innovative Encoder-Coupler-Decoder architecture designed to facilitate key feature extraction and optimization. A cross-domain coupling module (CDCM) is created in the Coupler to conduct preliminary features screening of spaces and dimensions based on channel and spatial attention. It performs multi-scale feature extraction and global information modeling through the feature grouping and loop aggregation. This helps to extract key features while reducing the computational overhead. To further decrease the interference from complex backgrounds, a secondary optimization of the key features is carried out: a lightweight fully-featured mapping attention module (LFMAM) is designed within the Decoder. LFMAM utilizes an interactive fusion strategy and a lightweight linear self-attention mechanism, comprehensively considering all interactions between global-to-global, global-to-local, local-to-local, and local-to-global processes. By capturing the effective correlations and variances among features to further refine them, it enables the network to further optimize the crucial information while ensuring light weight. We have conducted extensive comparison experiments and ablation experiments on the ISPRS Vaihingen and ISPRS Potsdam datasets. The extensive experimental results demonstrate that our proposed LCCN can obtain superior performance compared to other advanced semantic segmentation models.

Graph Convolutional Networks (GCNs) are widely used for skeleton-based action recognition and achieved remarkable performance. Due to the locality of graph convolution, GCNs can only utilize short-range node dependencies but fail to model long-range node relationships. In addition, existing graph convolution based methods normally use a uniform skeleton topology for all frames, which limits the ability of feature learning. To address these issues, we present the Graph Convolution Network with Self-Attention (SelfGCN), which consists of a mixing features across self-attention and graph convolution (MFSG) module and a temporal-specific spatial self-attention (TSSA) module. The MFSG module models local and global relationships between joints by executing graph convolution and self-attention branches in parallel. Its bi-directional interactive learning strategy utilizes complementary clues in the channel dimensions and the spatial dimensions across both of these branches. The TSSA module uses self-attention to learn the spatial relationships between joints of each frame in a skeleton sequence. It also models the unique spatial features of the single frames. We conduct extensive experiments on three popular benchmark datasets, NTU RGB+D, NTU RGB+D120, and Northwestern-UCLA. The results of the experiment demonstrate that our method achieves or exceeds the record accuracies on all three benchmarks. Our project website is available at https://github.com/SunPengP/SelfGCN.

Abstract Image segmentation plays a pivotal role in image processing. Level set model is a traditional variation image segmentation method. In order to achieve level set evolution equation, the level set energy functionals are minimized with the gradient descent methods and then the partial differential equation (PDE) was solved by finite difference scheme. Slow speed is one of its disadvantages. We propose a sweep optimization algorithm based on global cosine fitting (GCF) energy. Instead of calculating the PDE and the curvature, the proposed sweeping algorithm directly calculates the energy change when a pixel moves from one side of evolving contour to the other. It checks whether the GCF energy is decreased or not. The proposed algorithm has many advantages. For example, independent of initial level set contour positions and parameters, need not consider the Courant Friedrichs Lew condition and the regularization energy term. The proposed algorithm can be easily extended to high dimension image segmentation. The experiments on synthetic images, noise images and real images demonstrate the effectiveness of the proposed sweeping optimization algorithm.

The popular Richardson-Lucy (RL) image deconvolution algorithm often produces undesirable ringing artifacts. In this paper, we propose a novel Dual Range Deringing (DRD) algorithm to address this problem. As a post-deconvolution scheme, the proposed approach follows RL deconvolution and removes ringing artifacts by utilizing information from both the input blurred image and the RL-deblurred image. DRD first marks smooth regions in the input blurred image that are likely to be subjected to ringing artifacts far away from any strong edge. It then identifies short-range ringing artifacts from the regions that surround strong edges in the RL-deblurred image. Once marked, both long- and short-range ringing artifacts are then suppressed by an edge-preserving deringing filter. We demonstrate the effectiveness of this procedure by performing experiments on a set of images blurred with various Point Spread Functions (PSFs). We compare DRD with state-of-the-art non-blind deconvolution algorithms and show that our results are virtually free of ringing artifacts with only minor detail losses. Moreover, DRD consists of computationally efficient local operations and is suitable for parallelization on modern GPUs.

In this paper, a novel scheme is introduced for human facial feature extraction. Unlike previous methods that fit a 3D morphable model to 2D intensity images, our scheme utilizes 3D range images to extract features without requiring manually-defined initial landmark points. A linear transformation is used to achieve the mapping between the 3D model and a 3D range image, which makes the computation simple and fast. Moreover, our scheme is robust to the illumination and pose variations. In addition to features from range images, extra features can be obtained by examining optional 2D texture images. Using our scheme, we can also perform automatic eye/mouth corner localization. Experimental results show the high accuracy and robustness of our scheme.

In this paper, we describe a novel 3-D face recognition scheme for 3-D face recognition that can automatically identify faces from range images, and is insensitive to holes, facial expression, and hair. In our scheme, a number of carefully selected range images constitute a set of example faces, and another range image is chosen as a ldquogeneric face.rdquo The generic face is then warped to match each of the example faces in the least mean square sense. Each such warp is specified by a vector of displacement values. In feature extraction operation, when a target face image comes in, the generic face is warped to match it. The geometric transformation used in the warping is a linear combination of the example face warping vectors. The coefficients in the linear combination are adjusted to minimize the root mean square error. After the matching process is complete, the coefficients of the composite warp are used as features and passed to a Mahalanobis-distance-based classifier for face recognition. Our technique is tested on a data set containing more than 600 range images. Experimental results in the access-control scenario show the effectiveness of the extracted features.

The dead-end problem is an importance issue of location-based routing in sensor networks, which occurs when a message falls into a local minimum using greedy forwarding. Current methods for this problem are insufficient either in eliminating traffic/path memorization or finding satisfied short paths. We propose a novel algorithm, named partial-partition avoiding geographic routing (PAGER), to solve the problem. The basic idea of PAGER is to divide a sensor network graph into functional sub-graphs, and provide each sensor node with message forwarding directions based on these sub-graphs. That results in loop-free short paths without memorization of traffics/paths in sensor nodes. We implement our algorithm in a protocol and evaluate it in sensor networks with different parameters. Results show that PAGER generates considerably shorter paths, higher delivery ratio and lower energy consumption than the greedy perimeter stateless routing protocol. At the same time, PAGER achieves better performance in handling large-scale networks than the ad-hoc on-demand distance vector protocol.