Dual-model image decision fusion tracking method based on mutual updating of models

Abstract

The invention discloses a dual-model image decision fusion tracking method based on mutual updating of models. The dual-model image decision fusion tracking method based on the mutual updating of the models comprises the steps that according to the characteristics of infrared images and visible images, firstly characteristic description vectors of the infrared images and the characteristic description vectors of the visible images are extracted, so that complementary information can be provided by the characteristic description vectors, and description of the amount of the information of the images can be increased; then, an infrared classifier model and a visible classifier model are established respectively by adopting a GentleAdaboost learning algorithm, and a tracking problem is converted into two classification problems of a target and a background; cooperative training is carried out in a semi-supervised learning frame, mutual model updating is carried out at the same time, and thus the problem of accumulation of model errors is solved effectively; final likelihood images are obtained by using training results and respective confidence coefficients of the training results for carrying out decision fusion, and the position of the target is located in the final likelihood images through a mean value drifting algorithm. The dual-model image decision fusion tracking method based on the mutual updating of the models can effectively solve the problem of tracking missing caused by model error accumulation and the limitation of single-model images in describing the information of the target, and improves tracking robustness.

Description

technical field [0001] The invention belongs to the technical field of image fusion tracking, and relates to a dual-mode image decision-level fusion tracking method based on mutual update of models. Background technique [0002] Image fusion is a technical means of image processing, which belongs to a branch of information fusion. It is based on a certain algorithm to comprehensively process the image or image sequence information of a specific scene obtained from two or more sensors at the same time (or at different times or at different viewing angles), so as to obtain a new for an explanation of this scenario. This explanation cannot be obtained from the information obtained by a single sensor. It can provide complementary information, increase the information description of the image, improve the adaptability to the environment, and at the same time better meet certain requirements, and the description of the target or scene is more accurate. Accurate, comprehensive an...

AI Technical Summary

Problems solved by technology

[0004] Since the visible light sensor is imaged by using light reflectivity, it has the characteristics of rich spectral information, high resolution, and large dynamic range, but it is easily affected by illumination changes and shadows.

The imaging of the infrared sensor uses the radiant energy of the object, which is robust to light and shadow changes, and has a certain ability to penetrate smoke, etc., but its signal-to-noise ratio is low, the imaging quality is poor, and it lacks texture features.

Images