Video monitoring system and moving target detecting and tracking method thereof

Abstract

The invention discloses a video monitoring system and a moving target detecting and tracking method thereof. The method is applied to the video monitoring system on the condition that a camera is in a moving state. The method comprises the following steps: a moving target detection step, in which combination of a Harris corner and an HOG descriptor is employed as an image feature as well as processing including image feature extraction, image projection conversion, and image subtraction operation and the like is carried out to obtain a plurality of moving targets; a moving target model establishment step, in which moving target models are established for all the moving targets as well as a combination mode of a Harris corner, an extreme point and an HOG descriptor is employed to express features of the moving targets; and a target tracking step, in which target tracking is carried out according to the moving target models. According to the invention, corner feature matching is employed to reduce the calculated amount and precision of moving target detection is ensured; a corner and an extreme point are employed as target features, so that target identification has high robustness and tracking sustainability is strong; and a target motion estimation method is employed to reduce the calculated amount.

Description

technical field [0001] The invention relates to the technical field of video monitoring, in particular to a video monitoring system and a moving target detection and tracking method applied in the case of camera movement. Background technique [0002] In the traditional intelligent video monitoring system, most of the monitoring cameras are fixed cameras, the background image is fixed, and the foreground target is moving. The problem existing in the application of this system is: in the cyclic monitoring of certain preset positions, the moving target is easy to exceed Monitoring the field of view but not continuous tracking, these conditions make the application of traditional intelligent video surveillance greatly restricted. The motion camera monitoring can overcome the defects of the above-mentioned traditional camera monitoring, and it can be applied to vehicle monitoring, PTZ (Pan Tilt Zoom, camera pan tilt rotation, pitch movement and lens zoom) target tracking, intell...

AI Technical Summary

Problems solved by technology

[0002] In the traditional intelligent video monitoring system, most of the monitoring cameras are fixed cameras, the background image is fixed, and the foreground target is moving. The problem existing in the application of this system is: in some pre-set positions, the moving target is easily exceeded. Monitoring the field of view but not continuous tracking, these conditions make the application of traditional intelligent video surveillance greatly restricted

Although the color feature is a very useful feature, when the color of the object and the background color are similar, it is often difficult to use only the color to track, and it is easy to cause tracking errors. Some researchers use a variety of feature fusion methods to select features; Using SIFT, the SURF feature is relatively stable as the feature information of the tracked target, and has strong adaptability to changes in background color and illumination. It is an ideal target feature expression method. The disadvantage is that it may be difficult to extract for a small number of targets. Stable feature points or even feature points cannot be extracted

Images