Image processing method based on fed back moving object segmentation

Abstract

The invention discloses an image processing method based on fed back moving object segmentation. The method comprises the steps that a background is modeled, a model is updated through the dual-layer background, the background is updated with the low updating rate in the first layer to adapt to the slow change of the background, and acceleration and compensation operations are carried out on the background according to the feedback of the high-layer information in the second layer to adapt to the sudden change of the object movement in a scene; a foreground is segmented, predicated moving object blocks are combined according to the feedback of the high-layer information, the segmentation threshold values are adjusted in a self-adaptation mode in a predicated object area, and the purposes of restraining noise and preventing the segmented foreground object from forming a cavity and separation are achieved. According to the processing method, the robustness of the model can be kept and the sensibility of the model to the foreground object abnormal movement can be kept through the background modeling, the noise can be restrained well and foreground cavity and segmentation can be prevented through the foreground segmentation.

Description

technical field [0001] The invention relates to an image processing method for segmentation of moving objects based on feedback, and belongs to the technical field of intelligent traffic pattern recognition. Background technique [0002] Background modeling and foreground segmentation in moving object image processing methods are the basis of intelligent video surveillance systems. The accuracy of the background model and foreground segmentation will directly affect the subsequent processing of the system, including moving object segmentation, recognition and behavior understanding. There are two difficult trade-offs in traditional background modeling and foreground segmentation techniques: one is the trade-off between maintaining the robustness and sensitivity of the model during background modeling; the other is suppressing noise and preventing foreground objects from appearing during foreground segmentation. The trade-off between void and fragmented situations. [0003]...

AI Technical Summary

Problems solved by technology

There are two difficult trade-offs in traditional background modeling and foreground segmentation techniques: one is the trade-off between maintaining the robustness and sensitivity of the model during background modeling; the other is suppressing noise and preventing foreground objects from appearing during foreground segmentation. Tradeoffs between Hollow and Fragmented Cases

However, there are still some problems in these methods: first, as mentioned in the literature [4][5], the wrong classification of pixel categories in the current frame will damage the operation of subsequent frames

[0013] In summary, there are the following deficiencies in the prior art: (1) the traditional ( figure 1 As shown) the background modeling method adopts a unified background update rate. When the update rate is not obtained properly, many false alarms will be introduced.

This method will first blur the boundary of the segmented object; secondly, this method cannot solve the situation where the foreground hole is relatively large.

Images