In recent years, in Space-Ground-Sea Wireless Networks, the rapid development of image recognition also promotes the development of images fusion. For example, the content of a single-mode medical image is very single, and the fused image contains more image information, which provides a more reliable basis for diagnosis. However, in wireless communication and medical image processing, the image fusion effect is poor and the efficiency is low. To solve this problem, an image fusion algorithm based on fast finite shear wave transform and convolutional neural network is proposed for wireless communication in this paper. This algorithm adopts the methods such as fast finite shear wave transform (FFST), reducing the dimension of the convolution layer, and the inverse process of fast finite shear wave transform. The experimental results show that the algorithm has a very good effect in both objective indicators and subjective vision, and it is also very feasible in wireless communication.

Industrial particle tracking during discharge and transport is challenging because particles are often small, visually similar, densely packed, frequently occluded, and subject to rapid motion, all of which can cause tracking drift. To address these challenges, this paper proposes MSA-HPTrack, a Multi-Scale Attention-Guided Historical Prompt Tracking network for industrial particle tracking. Built upon the HIPTrack framework, the proposed method addresses two key limitations: the dilution of small-target responses caused by average pooling in historical prompt encoding, and the sensitivity of single-scale Key–Query representations in historical memory retrieval to scale variations and local disturbances. First, an attention-guided spatial pooling mechanism is introduced into the historical prompt encoder. It replaces global average pooling with attention-weighted aggregation and jointly models the result with max pooling, thereby enhancing target-relevant responses and reducing interference from dense backgrounds and neighboring particles during historical feature encoding. Second, a multi-scale adaptive Key–Query enhancement module is incorporated into the historical prompt decoder. By exploiting \(1 \times 1\), \(2 \times 2\), and \(4 \times 4\) pooling scales, the module captures global, regional, and local contextual information while preserving the original feature dimensionality, allowing the original L2-distance-based memory matching and prompt retrieval process to remain unchanged. Experimental results show that MSA-HPTrack maintains competitive general tracking performance while providing improved robustness in industrial small-particle scenarios,particularly under small target size, dense occlusion, high appearance similarity,rapid motion, and background interference.

To address video jitter and key-structure positional drift in industrial surveillance scenarios, this paper proposes a video stabilization method based on key-structure semantic constraints and grid motion fusion. First, Segment Anything Model 3 (SAM3) is employed to extract key structures and estimate semantic motion from their positional variations. The resulting semantic motion is then fused with deep unsupervised trajectory-based (DUT) grid motion to enhance key-structure positional stability while maintaining overall video stability and preserving local geometric structures. Subsequently, a geometric valid support domain is constructed using the fused motion to identify invalid boundary regions introduced by frame reprojection. The Flow-Guided Transformer (FGT) model is further employed to complete these regions and improve the visual completeness of the stabilized videos. Experiments conducted on general video sequences and industrial surveillance scenes demonstrate that the proposed method achieves favorable performance in geometric structure preservation and overall stability while reducing key-structure positional drift. Qualitative results further illustrate that the geometric support masks identify regions requiring completion and guide FGT in generating visually plausible boundary content in the presented examples. Ablation studies and fusion-weight sensitivity analysis further demonstrate the complementary roles of semantic motion and grid motion in achieving balanced stabilization performance.