A multi-layer convolution feature self-adaptive fusion moving target tracking method

Abstract

The invention relates to a multi-layer convolution feature self-adaptive fusion moving target tracking method, and belongs to the field of computer vision. The method comprises the following steps: firstly, initializing a target area in a first frame of image, and utilizing a trained deep network framework VGG-19 to extract first and fifth layers of convolution features of the target image block,and obtaining two templates through learning and training of a related filter; Secondly, extracting features of a detection sample from the prediction position and the scale size of the next frame andthe previous frame of target, and carrying out convolution on the features of the detection sample and the two templates of the previous frame to obtain a response graph of the two-layer features; calculating the weight of the obtained response graph according to an APCE measurement method, and adaptively weighting and fusing the response graph to determine the final position of the target; And after the position is determined, estimating the target optimal scale by extracting the directional gradient histogram features of the multiple scales of the target. According to the method, the targetis positioned more accurately, and the tracking precision is improved.

Description

Technical field [0001] The invention discloses a moving target tracking method of adaptive fusion of multi-layer convolution features, which belongs to the field of computer vision. Background technique [0002] Moving target tracking is an important research direction in the field of computer vision. It has a very wide range of applications in military and civilian applications, such as battlefield surveillance, intelligent transportation systems, and human-computer interaction. [0003] Since AlexNet achieved great success in image classification in 2012, a series of CNN (Convolutional Neural Network, CNN) frameworks have continuously set new records. Compared with AlexNet, the biggest improvement of VGGNet is to replace a large-size convolution kernel with multiple 3×3 (3×3 is the smallest size that can capture the concept of up, down, left, and right, and center), which enhances the generalization ability of the network. , The Top-5 error rate is reduced to 7.3%. In the VOT20...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a moving target tracking method for adaptive fusion of multi-layer convolution features to solve traditional manual features such as histogram of oriented gradient (Histogram of Oriented Gradient, HOG), color feature (Color Name, CN) cannot fully express the target. These features are difficult to capture the semantic information of the target, and they are not robust to complex appearance changes such as deformation and rotation. They can track defects with large differences in performance in different scenarios, and can be based on reliable The performance judgment is based on APCE to calculate the weight of each convolutional layer, which improves the tracking accuracy

Images