Aerial photo video motion object detection method

Abstract

The present invention discloses an aerial photo video motion object detection method. The method comprises the steps of: performing image matching of an input video sequence, and obtaining a difference image after background compensation; performing energy accumulation of the difference image after the background compensation, and obtaining an accumulated difference image; performing morphologicalopening processing of the accumulated difference image, removing noise and capturing a general target area; and performing edge detection to obtain an edge of a target image, and performing marking of the target area. The aerial photo video motion object detection method is suitable for multi-motion object detection in different scenes and is high in detection accuracy.

Description

technical field [0001] The invention relates to the field of image technology, in particular to a moving target detection method for aerial video. Background technique [0002] With the rapid development and popularization of computer and information technology, the intelligent transportation system (ITS) has emerged as the times require. It is an important way to solve the current traffic problems, and it is also the main direction of the future development of intelligent transportation. Moving object detection is one of the basic technologies of intelligent transportation systems, and it is the basis for the measurement of traffic flow parameters such as vehicle count, vehicle speed, traffic flow and vehicle density. In moving object detection, only by accurately segmenting the vehicle from the image background can the moving object be identified and tracked, and then various traffic flow parameters can be measured and analyzed. Aerial photography is a non-contact, long-d...

AI Technical Summary

Problems solved by technology

[0003] Moving object detection algorithms based on fixed cameras, such as background difference method, frame difference method and optical flow method, these detection algorithms cannot be directly used in aerial video detection scenes where the camera moves, the main reason is that the image background becomes complicated due to the movement of the camera Changeable, so that it is impossible to accurately detect moving targets

[0004] The prior art discloses a rapid vehicle detection method for aerial traffic video. This method uses the global motion estimation method to segment the background area and the foreground area, and then combines the watershed segmentation technology to obtain the moving target. Its existence uses a two-parameter mo

Images