Video moving target detection method and device based on structured decomposition

Abstract

The invention relates to a video moving target detection method and device based on structured decomposition, and the method comprises the following steps: 1), acquiring a frame of image, and carryingout superpixel segmentation; 2) vectorizing the frame of image, and constructing a structured coding matrix according to the superpixel units; 3) completing the processing on each frame of image of athree-dimensional video sequence; 4) stacking each vectorized frame of image to form an observation matrix; 5) presetting an augmented Lagrange equation according to the observation matrix and the structured coding matrix; wherein the augmented Lagrange equation comprises a moving target matrix, a background matrix, a noise matrix and an auxiliary matrix; and 6) performing iterative solution to obtain an optimal solution of the moving target matrix; thus detecting the moving object. Compared with the prior art, the method has the advantages that the problems that the existing detection technology is influenced by factors like weather, illumination and shadows and the robustness is weak under the conditions of dynamic background and noise interference are solved, and the detection precision of the moving target area is improved.

Description

technical field [0001] The invention relates to the field of video moving target detection, in particular to a method and device for video moving target detection based on structured decomposition. Background technique [0002] Video moving object detection refers to the technology of detecting the area where the moving object is located in the video sequence and separating it from the static background or dynamic background. Traditional moving target detection methods mainly include frame difference method, optical flow method, background subtraction method, etc. The frame difference method subtracts the image pixel values ​​of the front and back frames in the video sequence, and extracts the area with a large difference as the moving target area through threshold segmentation. This type of method is mainly suitable for occasions with good video imaging quality. When external conditions such as weather, light, and shadow interfere with video information, its detection perf...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method and device for detecting video moving objects based on structured decomposition in order to overcome the defect that the existing detection technology is affected by factors such as weather, illumination, and shadows, and the detection performance drops in the above-mentioned prior art.

Images