Method and system for tracking targets in video based on PTZ

Abstract

The invention discloses a method and system for tracking targets in a video based on the PTZ. The method comprises the following steps: 100, utilizing a Gaussian mixture modeling method for setting up a background model for a video image obtained by a camera in a preset position scene, and detecting the motion targets in a monitored video image immediately obtained by the camera in the preset position scene; 200, calculating a grey level histogram of the motion targets of the monitored video image, recording template information of the motion targets, and updating parameter information of the motion targets according to the video image immediately obtained by the camera; 300, conducting judgment according to the parameter information and controlling the camera to conduct the corresponding adjustment according to the judged result. The method and system for tracking the targets in the video based on the PTZ can initially and accurately track the motion targets and accurately distinguish the motion targets of the video image.

Description

technical field [0001] The invention relates to the field of video surveillance, in particular to a PTZ-based video target tracking method and system. Background technique [0002] PTZ is the abbreviation of Pan / Tilt / Zoom. PTZ tracking technology refers to the all-round (up and down, left and right) monitoring of the pan / tilt and the ball camera according to the control command in the video surveillance system with the pan / tilt / zoom (referred to as the dome camera). A method for moving, zooming and zooming the lens. It conducts real-time analysis of the video of a large-scale scene monitored in the video surveillance system composed of pan / tilt, ball machine, etc., detects moving objects entering the scene, and sends control commands to the pan / tilt, ball machine to make Pan (up and down), Tilt (left and right), Zoom (zoom) movement to ensure that the target is always within the monitoring range with a suitable size. [0003] In the prior art, methods commonly used in real...

AI Technical Summary

Problems solved by technology

[0009] However, in the prior art, the ideal condition for the histogram back-projection method to track the target is that the color frequency bands of the target and the background do not overlap. This strict conditional assumption makes it difficult for this tracking method to be used in real conditions.

Although the existing technology has also improved the algorithm and weakened this condition to require the target color band to be narrow and the background color band to be wide, the performance of this algorithm is still difficult to meet user needs under realistic conditions.

[0010] Therefore, in the prior art, how to accurately carry out the tracking of the moving target under the continuous translation of the pan-tilt and the continuous zooming of the camera lens, and ensure the continuous acquisition of monitoring video images of the moving target, and provide a more accurate method for discriminating the moving target of the video image is a very important problem. intractable problem

Images