Dynamic target detection method

Abstract

The invention discloses a dynamic target detection method, which comprises the following steps of: selecting a plurality of homonymy points in combination with a remote sensing image base map corresponding to a video frame image of a camera, and resolving a homography matrix and a vision field of the camera; calculating geographic coordinates of any pixel point position according to the homography matrix, and determining an actual peripheral contour in a geographic scene; according to an inverse matrix of the homography matrix, converting angular point geographic coordinates of the actual peripheral contour into image coordinates, and determining a target threshold range of any pixel point position; traversing each pixel point of the vision field, and determining a target threshold range of positions of all pixel points; performing dynamic target detection on a video frame image of a camera, regarding each detected dynamic target as a target dynamic block, obtaining a target dynamic block set, calculating the area of any target dynamic block and a target threshold range of a pixel point position corresponding to a centroid, and performing self-adaptive threshold target detection. The method realizes high-precision detection of the dynamic target under the high-altitude camera.

Description

technical field [0001] The invention relates to a dynamic target detection method and belongs to the technical field of geographic information. Background technique [0002] At present, surveillance video has become the mainstream tool for social and traffic safety monitoring. Combining geographic information technology to mine hidden information in video has become a research hotspot, and dynamic target detection is the basis of video information mining and behavior understanding. However, due to differences in the location, height, and field of view of surveillance cameras, the setting and accuracy of target detection thresholds will also vary. [0003] Due to the complex and diverse monitoring environment of high-altitude cameras, the accuracy of target detection is reduced, and the target detection is greatly disturbed by the external environment, and the farther the camera is, the larger the video field of view is, and the interference from the surrounding environment i...

AI Technical Summary

Problems solved by technology

[0004]Aiming at the problem that the existing target detection algorithm faces the high-altitude camera being greatly disturbed by the external environment, the present invention provides a dynamic target detection method, which realizes the threshold value based on the principle of the camera Based on the calculation of adaptive threshold, the high-precision detection of dynamic targets under high-altitude cameras is realized

Images