2results about How to "Avoid tracking" patented technology

This invention provides a deep learning-based method for multi-target pedestrian tracking, relating to the field of computer vision technology. The method includes: S1 acquiring video data, extracting frames from the video data to convert them into image frames, and preprocessing the image frames; S2 using an improved YOLOv5-s model to detect pedestrian targets in the image frames, obtaining the pedestrian targets; S3 using an improved Strong SORT model to track the pedestrian targets in each frame, assigning an ID to each tracked pedestrian, and generating pedestrian tracking results. This invention can accurately locate each pedestrian in a video and track their trajectory.

The application discloses a kind of multi-interface adaptive switching control method and system suitable for vehicle charging, after vehicle gun is inserted, the electrical characteristic vector of all physical interfaces is synchronously collected and input one-dimensional convolution neural network, the activation probability of each interface is calculated, if the maximum probability exceeds threshold value, corresponding protocol stack is preloaded and polling is skipped;If confidence is insufficient, a multi-armed bandit model based on Thompson sampling is used to dynamically select the optimal protocol for handshaking;After successful handshaking, the vehicle digital identity is extracted through VIN hash value or physical layer timing fingerprint, the cross-interface shared cache is queried, if hit, the historical charging strategy is directly inherited, otherwise, complete negotiation is performed and a file is created, and the current is output according to the established or negotiated strategy during charging.The application overcomes the inherent defects of existing multi-interface charging pile protocol selection, such as low efficiency and inability to share cross-interface information, and has made significant progress in charging start speed, adaptive ability, user experience and the like.