RGBT dual-modal Siamese tracking network with feature fusion

被引：0
|
作者：
Shen Y. [1 ]
机构：
[1] School of Mathematics and Information Technology, Yuncheng University, Yuncheng
来源：
Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering | 2021年 / 50卷 / 03期
关键词：
Dual-modal tracking; Feature fusing; RGB/Thermal infrared; Siamese network;
D O I：
10.3788/IRLA20200459
中图分类号：
学科分类号：
摘要：
Infrared imaging technology has been widely used for object tracking in military, remote sensing, security and other fields. However, thermal infrared images generally suffer from low contrast and blurry targets. Therefore, it has great importance of fusing infrared images with visible images. Compared with single-modal RGB trackers, dual-modal RGBT(RGB/Thermal infrared) trackers are more robust to illumination variation and fog. In this paper, a RGBT dual-modal siamese tracking network with feature fusion was proposed. Convolutional features extracted from the visible image and infrared image were fused to improve the appearance feature discrimination. The network can use the training data for end-to-end off-line training. Experimental results on the public RGBT234 dataset demonstrate that our tracker achieves robust and persistent tracking in complex scenarios. Copyright ©2021 Infrared and Laser Engineering. All rights reserved.
引用
收藏
相关论文
共 16 条
  • [1] Chen X J, Yang Y M., Realization of dual-band fire detector based on infrared video, Journal of Electronic Measurement and Instrumentation, 33, 3, pp. 473-479, (2016)
  • [2] Li C L, Liang X Y, Lu Y J, Et al., Rgb-t object tracking: benchmark and baseline, Pattern Recognition, 96, (2019)
  • [3] Guan H, Xue X Y, An Z Y., Online single object video tracking: A survey, Mini-Micro Systems, 38, 1, pp. 147-153, (2017)
  • [4] Yilmaz A, Javed O, Shah M., Object tracking: A survey, ACM Computing Surveys, 38, 4, pp. 1-45, (2006)
  • [5] Wu Y, Blasch E, Chen G S, Et al., Multiple source data fusion via sparse representation for robust visual tracking, International Conference on Information Fusion, (2011)
  • [6] Sun F, Liu H., Fusion tracking in color and infrared images using joint sparse representation, Science China Information Sciences, 55, 3, pp. 590-599, (2012)
  • [7] Li C, Cheng H, Hu S, Et al., Learning collaborative sparse representation for grayscale-thermal tracking, IEEE Transactions on Image Processing, 25, 12, pp. 5743-5756, (2016)
  • [8] Li C, Nan Z., Lu Y, Et al., Weighted sparse representation regularized graph learning for rgb-t object tracking, ACM on Multimedia Conference, (2017)
  • [9] Li C, Wu X, Zhao N, Et al., Fusing two-stream convolutional neural networks for rgb-t object tracking, Neurocomputing, 28, 1, pp. 78-85, (2018)
  • [10] Tao R, Gavves E, Smeulders A W M., Siamese instance search for tracking, IEEE Conference on Computer Vision and Pattern Recognition, pp. 1420-1429, (2016)
12