Video frequency object tracking method, device and automatic video frequency following system

Abstract

The invention discloses a method for tracking a video target. The method comprises the following steps that: gradient vector flow (GVF) deformation is carried out to each candidate position in a current frame to obtain each deformation curve; the video characteristic of the deformation curve is calculated; according to the calculated video characteristic, a candidate position is determined as a target position. The invention also discloses a video target tracking device and an automatic video tracking system, which can improve the accuracy of target tracking.

Description

Video target tracking method, device and automatic video tracking system technical field The invention relates to the technical field of image processing, in particular to a video target tracking method, device and automatic video tracking system. Background technique The so-called automatic video tracking is to use the image signal of the video to automatically detect, identify and locate the target, automatically control the movement of the pan / tilt and the camera, and track and lock the target. The process of video target tracking can be generally described as: the imaging system collects and records the images formed by the three-dimensional scenes of the objective world in the form of two-dimensional arrays and saves them in the computer. The computer analyzes and interprets the input image, and through preprocessing, feature extraction, feature selection, feature tracking and other algorithm processing, the obtained target information, including the structure, shape,...

AI Technical Summary

Problems solved by technology

Since the ellipse cannot accurately describe the outline of the human head, it is not accurate enough to calculate its perimeter gradient, and when calculating its color distribution function,

Images