Unsupervised hyperspectral video target tracking method based on spatial-spectral feature fusion

Abstract

The invention relates to an unsupervised hyperspectral video target tracking method based on spatial-spectral feature fusion. The hyperspectral target tracking method based on deep learning is designed in combination with a cyclic consistency theory method, a hyperspectral target tracking deep learning model can be trained in an unsupervised manner, and the cost of manual labeling is saved. On the basis of a Siamese tracking framework, an RGB branch (space branch) and a hyperspectral branch are designed; RGB video data is used for training a space branch, a trained RGB model is loaded into network fixed parameters, meanwhile, a hyperspectral branch is trained, and the fused features with higher robustness and discrimination capability are obtained; and finally, the fused features are input into a correlation filter (DCF) to obtain a tracking result. According to the method, the problem of manual labeling of the hyperspectral video data and the problem of few hyperspectral training samples for deep learning model training can be solved, and the precision and speed of a hyperspectral video tracking model can be effectively improved.

Description

technical field [0001] The present invention is based on the field of computational vision technology processing, and in particular relates to an unsupervised hyperspectral video target tracking method based on spatial spectral feature fusion. Background technique [0002] Hyperspectral video (high spatial resolution-high temporal resolution-hyperspectral resolution) target tracking is an emerging direction, which aims to use the target information of a given initial frame in hyperspectral video to predict the state of the target in subsequent frames. Compared with RGB video target tracking, hyperspectral video target tracking can provide spectral information to distinguish different materials in addition to spatial information. Even if the target shape is the same, as long as the material is different, the hyperspectral video can be used to track the target, which is an advantage that RGB video target tracking does not have. Therefore, hyperspectral video target tracking c...

AI Technical Summary

Problems solved by technology

The second is to design a correlation filter hyperspectral video target tracking framework for spatial spectral feature fusion, which solves the problem of few training samples in hyperspectral video to a certain extent, and at the same time, fusing RGB and hyperspectral features can obtain more robust and recognizable images. feature

Images