Multi-scale target tracking method based on background suppression and foreground anti-jamming

Abstract

The invention discloses a multi-scale target tracking method based on background suppression and foreground anti-jamming, which relates to the technical field of target tracking. The method includes the following steps: constructing and initializing a color probability model and a DCF tracking model; using an adaptive Gaussian window function to suppress the background in the previous frame of image, calculating the filter response map of a target position based on FHOG features in the previous frame of image, calculating the color probability distribution of the previous frame of image, obtaining the color response map of the target position, linearly fitting the filter response map and the color response map, and predicting a target position of next frame of image; updating the scale information of the target in the next frame of image according to the predicted target position of the next frame of image and based on a scale pyramid model; and carrying out adaptive dense sampling according to the target position and scale information of the next frame of image, calculating the FHOG features and color histogram of the next frame of image, and updating the DCF tracking model and the color probability model.

Description

technical field [0001] The invention relates to the technical field of target tracking, in particular to a multi-scale target tracking method based on background suppression and foreground anti-interference. Background technique [0002] Object tracking is an important branch of the field of computer vision, widely used in people flow counting, video surveillance, robotics and unmanned driving and other fields. Target tracking methods are mainly divided into two types: generative and discriminative. The former models the target area in the current frame, and the area most similar to the model is found in the next frame to predict the position. The more famous ones are Kalman filter, particle filter, and mean -shift, etc., while the latter uses the target area as a positive sample and the background area as a negative sample in the current frame, using machine learning methods to train the classifier, and using the trained classifier to find the optimal area in the next frame...

AI Technical Summary

Problems solved by technology

[0006] In view of the defects in the prior art, the purpose of the present invention is to provide a multi-scale target tracking method based on background suppression and foreground anti-interference, which not only has good tracking effect, but also can effectively suppress the influence of the background, and has strong anti-deformation interference ability, and It can solve the multi-scale problem in the tracking process

Images