Adaptive anti-occlusion infrared target tracking method based on multi-layer depth feature fusion

Abstract

The invention discloses an adaptive anti-occlusion infrared target tracking method based on multi-layer depth feature fusion. Firstly, a series of multi-layer depth feature maps of the same size and different levels are obtained; the multi-layer depth feature map is then converted from a time domain to a frequency domain according to correlation filtering, a filter is trained and the response mapis calculated according to the fast Fourier transformation, and then the multi-layer depth feature map is merged and dimensionally reduced according to the weighted fusion of the intra-layer features,so that the feature response map of different levels is constructed and the maximum correlation response value is obtained, which is the estimated position of the target; at last, that dense featuresof the target are extracted, and the response confidence of the target center position estimated by the depth convolution feature is obtained according to the maximum response value of the feature obtained by the correlation filtering; when the response confidence of the target center position is less than the re-detection threshold T0, the obtained target estimated position is evaluated by on-line target re-detection and the position of the target is adaptively updated according to the evaluation result.

Description

technical field [0001] The invention belongs to the technical field of video processing, and in particular relates to an adaptive anti-occlusion infrared target tracking method for multi-layer depth feature fusion. Background technique [0002] Visual tracking is one of the research hotspots in the field of computer vision, and it is widely used in civilian fields such as video surveillance and intelligent transportation. In recent years, with the rapid development of the field of computer vision, the comprehensive performance of tracking algorithms has been significantly improved. At the same time, because the infrared imaging system uses the energy generated by the target to detect and identify the target by obtaining the energy information of the target, it has the ability of passive detection and all-day detection and is widely used in target perception equipment; among them, the Tracking the target of interest is the main task of the infrared detection system, so the t...

AI Technical Summary

Problems solved by technology

[0009] The current target tracking method based on deep learning focuses on training a network model that can distinguish target and background information, and obviously suppresses non-target similar objects in the background; therefore, when the target is blocked by a complex scene for a long time, there is a phenomenon of tracking target loss. It reduces the stability of target tracking and is not robust to re-tracking after the target itself reappears

Images