Method for determining dynamic target in complex environment

Abstract

The present invention provides a method for determining a dynamic target in the complex environment. The method mainly comprises: defining the number of multiple sample pictures, performing first granularity grid processing on the sample pictures to form grid pictures containing multiple grids, and after adding geographical location information and environment description data for the grid pictures, saving the grid pictures to a database of a geographic information system and creating index association; performing grid processing on the to-be-determined picture based on the first granularity grid processing method, and comparing the to-be-determined picture with the grid pictures for the first time to filter out multiple grid pictures that have changed; and finally, comparing the grid pictures of the same geographical location information with the environment description data in the sample pictures for the second time to determine whether the target is a dynamic target. According to the method provided by the present invention, the external environment interference can be effectively eliminated, the accurate determination of the dynamic target in a complex scene is realized, and the advantage of the small computation overhead is achieved.

Description

technical field [0001] The invention relates to the technical field of multimedia content analysis, in particular to a method for judging a dynamic target in a complex environment. Background technique [0002] The border between countries needs to accurately determine the dynamic target, and judge the attributes of the dynamic target (for example, people, vehicles, objects, etc.). At present, borders are usually monitored or guarded by humans, which leads to the defect that the monitoring efficiency of dynamic targets in complex scenes is very low. Therefore, in the prior art, closed-circuit television systems are used to conduct centralized remote monitoring of the border, but this prior art still relies on manual judgment of dynamic targets appearing in the surveillance video, so there are also defects such as low monitoring efficiency. [0003] In addition, due to the limitations of video quality and traditional video content analysis techniques, the judgment of the att...

AI Technical Summary

Problems solved by technology

[0005] The problem to be solved by the present invention is to accurately determine the dynamic target in the complex scene, so as to reduce the interference of the external environment interference factors on the dynamic target determination, so as to accurately monitor and judge the dynamic target, and at the same time reduce the impact on the dynamic target in the complex scene. The time complexity and space complexity overhead required for the target to determine

Images