红外与毫米波学报2023，Vol.42Issue(6)：907-916,10.DOI:10.11972/j.issn.1001-9014.2023.06.024
基于自监督学习的热红外图像景深估计方法
Depth estimation of thermal infrared images based on self-supervised learning
摘要
Abstract
Depth estimation based on unsupervised learning is one of the important issues in the field of computer vi-sion.However,existing algorithms of depth estimation are mainly designed based on visible images.Compared with visible images,thermal infrared images have the disadvantages of low contrast and insufficient detailed information.To this end,a depth estimation network is constructed and an unsupervised depth estimation method is proposed for thermal infrared images according to their characteristics.The network consists of three parts:feature extraction module,fea-ture aggregation module,and feature fusion module.Firstly,a feature aggregation module is designed to improve net-work ability to acquire the edge information of target objects and the small object information of the image.Secondly,the channel attention mechanism is introduced in feature fusion module to effectively capture the interaction relationship between different channels.Finally,a depth estimation network for thermal infrared images is established.In this net-work,the model parameters are trained by thermal infrared sequence images to achieve the pixel-level depth estimation of a single thermal infrared image.The results of ablation studies and comparative experiments fully demonstrate that the performance of the proposed method in pixel-level depth estimation of thermal infrared image outperforms other rep-resentative methods.关键词
红外图像/无监督学习/单目深度估计/特征聚合/通道注意力机制Key words
thermal infrared image/self-supervised learning/monocular depth estimation/feature aggregation/channel attention mechanism分类
信息技术与安全科学引用本文复制引用
丁萌,关松,李帅,于快快,徐一鸣..基于自监督学习的热红外图像景深估计方法[J].红外与毫米波学报,2023,42(6):907-916,10.基金项目
光电信息控制和安全技术重点实验室开放基金(JCKY2022210C005),国家自然科学基金(U2033201),航空科学基金(20220058052001) Supported by the Open Foundation of Science and Technology on Electro-Optical Information Security Control Laboratory(JCKY2022210C005),the National Natural Science Foundation of China(U2033201),and Aeronautical Science Foundation of China(20220058052001) （JCKY2022210C005）
