Real-time robustness tracking device of moving target or dim small target under complex background

Abstract

The invention relates to a real-time robustness tracking device of a moving target or a dim small target under a complex background, a target image preprocessing unit of the device is used for performing preprocessing on an input image; a histogram statistical unit is used for performing calculation and processing to get a gray level histogram of the image; a calculation gray level image feature unit is used for calculating the difference delta x between the maximum gray level value xmax and the non-zero minimum gray level value xmin in the gray level histogram and calculating the different delta y between the number of pixels ymax of the maximum gray level value and the number of the pixels ymin of the non-zero minimum gray level value; a judging unit is used for autonomously judging whether the image belongs to the low-contrast dim small target situation or the complex background condition situation according to the delta x and the delta y; and then the device is used for autonomously deciding the adoption of the corresponding tracking method to perform target tracking and output the tracking result. The two features, namely the contrast and the gray level complexity, which can effectively represent the image in the gray level histogram of the image are adopted for comprehensive judgment, and then the great judgment result can be obtained.

Description

technical field [0001] The invention belongs to the technical field of digital image processing and electronics, and relates to a real-time robust tracking device for high-speed moving targets or small and weak targets under complex backgrounds. Background technique [0002] Target tracking is a complex subject that integrates multiple disciplines such as image processing, pattern recognition, probability theory, stochastic process, functional and optimization, and partial differential equations. It has always been an important research topic in the field of computer vision and is widely used in intelligent humans. Computer interaction, medical diagnosis, security monitoring, automotive intelligent transportation, etc. [0003] The challenges of object tracking are: [0004] 1) Illumination changes due to changes in viewing angle, time, etc., and uneven illumination due to shadows of objects next to the target; [0005] 2) Target scaling, rotation, deformation and other ch...

AI Technical Summary

Problems solved by technology

Although SIFT feature point matching has good robustness to target rotation, scaling, deformation, etc., it has a large amount of calculation and requires a large storage space; MeanShiff is the mean shift method, using the kernel histogram as the target model. Partial edge occlusion, but loses robustness to all occlusions; the particle filter method uses probability theory to predict the target position, which is robust to occlusions, but its calculation is large and the positioning is not accurate enough

Images