Against the backdrop of the increasing trend of aging population in China and even globally, the demand for hand function rehabilitation is growing day by day, and human-machine interaction virtual rehabilitation systems have become a research hotspot. Currently, 3D vision has shown great potential in morphological analysis, but the complexity and irregularity of hand surfaces pose challenges for accurate segmentation. This study has proposed a hand surface segmentation network (HSSN) for intelligent hand function rehabilitation in the virtual reality, which combines 3D graph deep learning and laser point cloud. HSSN integrates a series of methods, with edge convolution layers effectively addressing the complex morphology of hand surfaces, multi-scale edge convolution solving the problem of missing or redundant local features, multi density processing enhancing the robustness of the model to point cloud density, and normal vector feature enhancement solving the problem of insufficient geometric features of actual hand surface point clouds. Through the comprehensive application of these methods, HSSN has demonstrated excellent performance in comparative experiments. This study is of great significance for promoting the personalized and precise development of intelligent rehabilitation in the virtual reality environment. More importantly, this achievement has provided a new perspective for interdisciplinary research in fields, such as rehabilitation engineering and human-machine interaction.

Human-machine interaction and computational neuroscience have brought unprecedented application prospects to the field of medical rehabilitation, especially for the elderly population, where the decline and recovery of hand function have become a significant concern. Responding to the special needs under the context of normalized epidemic prevention and control and the aging trend of the population, this research proposes a method based on a 3D deep learning model to process laser sensor point cloud data, aiming to achieve non-contact gesture surface feature analysis for application in the field of intelligent rehabilitation of human-machine interaction hand functions. By integrating key technologies such as the collection of hand surface point clouds, local feature extraction, and abstraction and enhancement of dimensional information, this research has constructed an accurate gesture surface feature analysis system. In terms of experimental results, this research validated the superior performance of the proposed model in recognizing hand surface point clouds, with an average accuracy of 88.72%. The research findings are of significant importance for promoting the development of non-contact intelligent rehabilitation technology for hand functions and enhancing the safe and comfortable interaction methods for the elderly and rehabilitation patients.

Foreign objects intrusion into transmission lines can lead to serious troubles, using deep learning technology for foreign object detection has good performance and can reduce losses. Due to the complexity and diversity of the surrounding environment of the transmission lines, and the limitations of data acquisition methods, the image data of foreign objects invading transmission lines used in current research are extremely rare, and the types of foreign objects and background features are single. Deep learning requires large image data as a research driving force, Rare number of images leads to insufficient model fitting and affects the detection accuracy. We propose a Diverse Generation model, which can generate many images of foreign objects invading the transmission lines to provide support for deep learning, thereby solving the shortcomings of existing models. The results show that the dataset generated by our model has high quality and diversity, and can cover different scenes including those that are not convenient for data acquisition in reality. Thus, the accuracy of foreign objects detection can be effectively improved. This achievement provides a preliminary guarantee for abnormal detection of transmission lines, and helps to promote the integration of artificial intelligence technology in the power system.

Environmental perception is the core support of intelligent assistive systems in home rehabilitation scenarios. The unstructured characteristics of home rehabilitation scenarios pose significant challenges to indoor object detection. In addition, current research on indoor object detection mainly focuses on developing more complex network architectures. To address these issues, this paper proposes an efficient indoor object visual recognition model (IOVRM). IOVRM includes three innovative plug and play modules: multi-scale feature extraction module (MFEM), joint attention mechanism (JAM), and multi-scale feature fusion module (MFFM). These three modules respectively improve the computational efficiency, key feature extraction ability, and multi-scale feature fusion ability of the model, thereby enhancing the model's ability to recognize indoor objects in complex environments while reducing model complexity. In addition, a training strategy based on prior knowledge was proposed. This training strategy significantly improves the model's generalization ability by training the model on an existing dataset to obtain prior knowledge and using it as part of the weights. The experimental results show that IOVRM achieves an effective balance between performance and efficiency, with corresponding numerical results of mAP50, mAP50-90, Params, and FLOPs of 64.0% and 45.8%, 10.64, and 25.7, respectively. IOVRM provides a solid foundation for task execution of home service robots. This study not only achieved the collaborative optimization of high-precision detection and lightweight deployment, but also supplemented the theoretical system of indoor object detection in the context of home rehabilitation, providing practical solutions for rehabilitation assisted intelligent devices and home health monitoring systems.