Learning Modality-Consistency Feature Templates: A Robust RGB-Infrared Tracking System

Abstract

With a large number of video surveillance systems installed for the requirement from industrial security, the task of object tracking, which aims to locate objects of interest in videos, is very important. Although numerous tracking algorithms for RGB videos have been developed in the decade, the tracking performance and robustness of these systems may be degraded dramatically when the information from RGB video is unreliable (e.g. poor illumination conditions or very low resolution). To address this issue, this paper presents a new tracking system which aims to combine the information from RGB and infrared modalities for object tracking. The proposed tracking systems is based on our proposed machine learning model. Particularly, the learning model can alleviate the modality discrepancy issue under the proposed modality consistency constraint from both representation patterns and discriminability, and generate discriminative feature templates for collaborative representations and discrimination in heterogeneous modalities. Experiments on a variety of challenging RGB-infrared videos demonstrate the effectiveness of the proposed algorithm.

Robust visual tracking via samples ranking

“…Generally, most of existing tracking methods falls into either the non-CNN-based category or the CNN-based category according to whether CNN features are used. The non-CNN-based tracking methods usually employ the sparse coding framework to obtain effective image representations [17,[33][34][35][36][37][38]. In [17], spatial structure among selected local templates are enhanced to exclude distractors introduced by noisy templates.…”

Online non-negative discriminative dictionary learning for tracking

“…This paper [42] proposed to jointly learn heterogeneous features and classifiers for multi-modality tracking under discriminabilty-consistency constraint. In [43], they proposed to extract informative feature templates and exploit the modality consistency in discriminability and representation ability for modality fusion-based appearance modeling. Yang et al [44] explored the Fisher discriminant criterion to learn the discriminant dictionary.…”

Improved through-wall radar imaging using modified Green’s function-based multi-path exploitation method

“…The returned signal from the target and walls were separated and shown in the image by using a sparse reconstruction approach, which jointly uses the wall and target models. Moreover, the sparse reconstruction and representation methods are also widely used in various fields of image processing [15][16][17][18][19]. On the basis of the local maximum values extract method and the 1-D Kalman filter, the authors extracted the 1-D trajectories of the real target (2020) 2020:4…”