3results about How to "Strong response" patented technology

The invention provides a multi-modal semantic guided three-dimensional target positioning method, a medium and equipment. The method is realized based on a multi-modal semantic guided three-dimensional target positioning model, and comprises a multi-view semantic prior module, a text coding module, a double-branch point cloud coding and multi-source comparison supervision module, a sparse scene graph construction and graph relationship learning module and a positioning decoding module. The multi-view semantic prior module is used for segmenting the 3D scene point cloud into a 3D object point cloud, generating a multi-view 2D visual representation and encoding the semantics of the multi-view 2D visual representation; the double-branch point cloud coding and multi-source comparison supervision module is used for injecting semantic features into a 3D object point cloud to obtain 3D fusion features and realizing multi-source feature alignment through multi-source comparison supervision; the sparse scene graph construction and graph relation learning module is used for constructing a sparse scene graph and optimizing the sparse scene graph through a graph attention network; and the positioning decoding module is used for decoding and outputting a positioning result. The method can improve the target positioning capability of the model in a complex scene.

This invention discloses a training-free neurorehabilitation system combining peripheral visual stimulation and motor imagery, and its usage method. The system includes: a stimulation module, an SSVEP data acquisition module, an SSVEP classification and recognition module, a motor imagery data acquisition module, a motor imagery decoding model training module, a comparison module, and a motor imagery recognition accuracy statistics module. The system uses peripheral visual stimulation as the SSVEP signal induction paradigm. After each visual stimulus, SSVEP signal classification and recognition are performed, and the classification results are converted into control commands for rehabilitation equipment to drive limb training. Within 5 seconds thereafter, an active motor imagery task is performed, while motor imagery data is collected. The SSVEP signal classification results are used as training sample labels. Once the motor imagery data meets the training sample size, the motor imagery decoding model is trained, and the model's performance in recognizing motor intentions is evaluated, gradually reducing its dependence on peripheral visual stimulation.

The utility model relates to the technical field of smoke sensor, specifically relates to a power battery smoke sensor, and technical scheme main points include casing, circuit mainboard and top cap, set up the mounting surface on the casing, set up the side window on the opposite side of mounting surface, set up the emission seat, receiving seat, maze structure and bottom window on the casing, the emission seat is used for infrared emission pipe joint, receiving seat is used for infrared receiving pipe joint, based on emission and receiving route, the included angle of emission seat and receiving seat is greater than 90 degrees, the area between emission seat and receiving seat sets up maze structure, bottom window is close to maze structure, and the main circuit board covers the top of maze structure and is set up with the through -hole of position directly opposite bottom window in the middle, the top cap is buckled on the casing and covers circuit mainboard, and the top window of position directly opposite through -hole is set up on the top cap. The utility model discloses through adopt greater than 90 degrees infrared emission receiving route, adopt maze structure, improve the inductive accuracy.