Infrared Monocular Depth Estimation Based on Radiation Field Detail Enhancement

Monocular depth estimation (MDE) offers cost-effective approach to 3D perception, while thermal infrared sensors show high robustness under varying illumination conditions. Their combination is crucial for day and night 3D perception, yet it faces two key challenges: 1) inadequate processing of 14-b...

Full description

Saved in:
Bibliographic Details
Main Authors: Rihua Hao, Chao Xu, Chonghao Zhong
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11017611/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850124707275210752
author Rihua Hao
Chao Xu
Chonghao Zhong
author_facet Rihua Hao
Chao Xu
Chonghao Zhong
author_sort Rihua Hao
collection DOAJ
description Monocular depth estimation (MDE) offers cost-effective approach to 3D perception, while thermal infrared sensors show high robustness under varying illumination conditions. Their combination is crucial for day and night 3D perception, yet it faces two key challenges: 1) inadequate processing of 14-bit RAW data, leading to loss of subtle infrared information, and 2) the resolution limitation of current infrared datasets (existing <inline-formula> <tex-math notation="LaTeX">$640\times 512$ </tex-math></inline-formula> sensor collections restrict the camera&#x2019;s ability to capture critical scene details). To this end, in this paper, we introduce the IRSL dataset, which integrates infrared, stereo RGB, and LiDAR modalities. Data were acquired using a high-resolution thermal infrared camera (<inline-formula> <tex-math notation="LaTeX">$1280\times 1024$ </tex-math></inline-formula> pixels), synchronized stereo cameras, and LiDAR (500K points per frame). The dataset aims to enhance the precision and robustness of depth estimation in both daytime and nighttime environments. Secondly, this paper proposes Radiation Field Detail Enhancement (RFDE), a novel method for enhancing infrared radiation field details in RAW data. This method performs gray mapping based on radiation field intensity and spatial context awareness and uses a bilateral filter to enhance the details in the image. Experimental results show that the proposed RFDE method fully leverages the advantages of high-resolution infrared images, effectively improving the quantitative and qualitative performance of the MDE model (<inline-formula> <tex-math notation="LaTeX">$\delta _{1}$ </tex-math></inline-formula> =0.964, SqRel = 0.441).
format Article
id doaj-art-de84262d2bbe4cc2981edecd15694784
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-de84262d2bbe4cc2981edecd156947842025-08-20T02:34:15ZengIEEEIEEE Access2169-35362025-01-0113977519776410.1109/ACCESS.2025.357493211017611Infrared Monocular Depth Estimation Based on Radiation Field Detail EnhancementRihua Hao0https://orcid.org/0009-0005-2243-3397Chao Xu1https://orcid.org/0000-0002-5696-6301Chonghao Zhong2https://orcid.org/0009-0000-7910-9970Key Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education of China, School of Optics and Photonics, Beijing Institute of Technology, Beijing, ChinaKey Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education of China, School of Optics and Photonics, Beijing Institute of Technology, Beijing, ChinaKey Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education of China, School of Optics and Photonics, Beijing Institute of Technology, Beijing, ChinaMonocular depth estimation (MDE) offers cost-effective approach to 3D perception, while thermal infrared sensors show high robustness under varying illumination conditions. Their combination is crucial for day and night 3D perception, yet it faces two key challenges: 1) inadequate processing of 14-bit RAW data, leading to loss of subtle infrared information, and 2) the resolution limitation of current infrared datasets (existing <inline-formula> <tex-math notation="LaTeX">$640\times 512$ </tex-math></inline-formula> sensor collections restrict the camera&#x2019;s ability to capture critical scene details). To this end, in this paper, we introduce the IRSL dataset, which integrates infrared, stereo RGB, and LiDAR modalities. Data were acquired using a high-resolution thermal infrared camera (<inline-formula> <tex-math notation="LaTeX">$1280\times 1024$ </tex-math></inline-formula> pixels), synchronized stereo cameras, and LiDAR (500K points per frame). The dataset aims to enhance the precision and robustness of depth estimation in both daytime and nighttime environments. Secondly, this paper proposes Radiation Field Detail Enhancement (RFDE), a novel method for enhancing infrared radiation field details in RAW data. This method performs gray mapping based on radiation field intensity and spatial context awareness and uses a bilateral filter to enhance the details in the image. Experimental results show that the proposed RFDE method fully leverages the advantages of high-resolution infrared images, effectively improving the quantitative and qualitative performance of the MDE model (<inline-formula> <tex-math notation="LaTeX">$\delta _{1}$ </tex-math></inline-formula> =0.964, SqRel = 0.441).https://ieeexplore.ieee.org/document/11017611/Thermal infrared imagemonocular depth estimationhigh-resolution dataset
spellingShingle Rihua Hao
Chao Xu
Chonghao Zhong
Infrared Monocular Depth Estimation Based on Radiation Field Detail Enhancement
IEEE Access
Thermal infrared image
monocular depth estimation
high-resolution dataset
title Infrared Monocular Depth Estimation Based on Radiation Field Detail Enhancement
title_full Infrared Monocular Depth Estimation Based on Radiation Field Detail Enhancement
title_fullStr Infrared Monocular Depth Estimation Based on Radiation Field Detail Enhancement
title_full_unstemmed Infrared Monocular Depth Estimation Based on Radiation Field Detail Enhancement
title_short Infrared Monocular Depth Estimation Based on Radiation Field Detail Enhancement
title_sort infrared monocular depth estimation based on radiation field detail enhancement
topic Thermal infrared image
monocular depth estimation
high-resolution dataset
url https://ieeexplore.ieee.org/document/11017611/
work_keys_str_mv AT rihuahao infraredmonoculardepthestimationbasedonradiationfielddetailenhancement
AT chaoxu infraredmonoculardepthestimationbasedonradiationfielddetailenhancement
AT chonghaozhong infraredmonoculardepthestimationbasedonradiationfielddetailenhancement