Image searching method and system based on motion acceleration and electronic equipment

Abstract

The invention relates to an image searching method and system based on motion acceleration and electronic equipment. The method comprises the following steps: step a, calculating the acceleration of ato-be-tracked target in a current frame image according to the displacements of the first two frames of images; b, determining a search range rectangular frame of a to-be-tracked target in the current frame image according to the acceleration calculation result; and step c, extracting a candidate box of a to-be-tracked target in the current frame image along the diagonal line of the search rangerectangular box through an RPN network, and carrying out feature analysis on the candidate box to obtain the position of the to-be-tracked target in the current frame image. According to the method, the limited search range rectangular frame is determined in an acceleration calculation mode, candidate frames of the tracking target are selected along the diagonal line of the search range rectangular frame, a smaller search range is determined, global search is not needed, the search range is greatly narrowed, the calculated amount is reduced, and the calculation speed is increased.

Description

technical field [0001] The present application belongs to the technical field of image search, and in particular relates to an image search method, system and electronic equipment based on motion acceleration. Background technique [0002] With the development of artificial intelligence technology, more and more cutting-edge knowledge has been implemented. Among them, the object (target) tracking technology in video has attracted extensive attention from universities and business circles. At present, for the target tracking in the video, the general technical solution is to mark the position of the target to be tracked in the first frame of the video, and then perform a global search in each next frame to find the target in the next frame. target to be tracked. It is usually implemented in the following ways: [0003] 1. Sliding window search for global images [Girshick R B, Donahue J, Darrell T, et al.Rich Feature Hierarchies for Accurate Object Detection and SemanticSegm...

AI Technical Summary

Problems solved by technology

[0005] As mentioned above, the existing image search technologies are all global range searches, which will result in longer retrieval time and more computational redundancy.

Images