Rights statement: This is the author’s version of a work that was accepted for publication in Remote Sensing of Environment. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Remote Sensing of Environment, 274, 2022 DOI: 10.1016/j.rse.2022.113012
Accepted author manuscript, 3.9 MB, PDF document
Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - A deep learning model for incorporating temporal information in haze removal
AU - Ma, X.
AU - Wang, Q.
AU - Tong, X.
AU - Atkinson, P.M.
N1 - This is the author’s version of a work that was accepted for publication in Remote Sensing of Environment. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Remote Sensing of Environment, 274, 2022 DOI: 10.1016/j.rse.2022.113012
PY - 2022/6/1
Y1 - 2022/6/1
N2 - Haze contamination is a very common issue in remote sensing images, which inevitably limits data usability and further applications. Several methods have been developed for haze removal, which is an ill-posed problem. However, most of these methods involve various strong assumptions coupled with manually-determined parameters, which limit their generalization to different scenarios. Moreover, temporal information amongst time-series images has rarely been considered in haze removal. In this paper, the temporal information is proposed to be incorporated for more reliable haze removal, and guided by this general idea, a temporal information injection network (TIIN) is developed. The proposed TIIN solution for haze removal extracts the useful information in the temporally neighboring images provided by the regular revisit of satellite sensors. The TIIN method is suitable for images with various haze levels. Moreover, TIIN is also applicable for temporal neighbors with inherent haze or land cover changes due to a long-time interval between images. The proposed method was validated through experiments on both simulated and real haze images as well as comparison with five state-of-the-art benchmark methods. This research provides a new paradigm for enhancing haze removal by incorporating temporally neighboring images.
AB - Haze contamination is a very common issue in remote sensing images, which inevitably limits data usability and further applications. Several methods have been developed for haze removal, which is an ill-posed problem. However, most of these methods involve various strong assumptions coupled with manually-determined parameters, which limit their generalization to different scenarios. Moreover, temporal information amongst time-series images has rarely been considered in haze removal. In this paper, the temporal information is proposed to be incorporated for more reliable haze removal, and guided by this general idea, a temporal information injection network (TIIN) is developed. The proposed TIIN solution for haze removal extracts the useful information in the temporally neighboring images provided by the regular revisit of satellite sensors. The TIIN method is suitable for images with various haze levels. Moreover, TIIN is also applicable for temporal neighbors with inherent haze or land cover changes due to a long-time interval between images. The proposed method was validated through experiments on both simulated and real haze images as well as comparison with five state-of-the-art benchmark methods. This research provides a new paradigm for enhancing haze removal by incorporating temporally neighboring images.
KW - Haze removal
KW - Remote sensing images
KW - Temporal information
KW - Deep learning
KW - Convolutional neural network
U2 - 10.1016/j.rse.2022.113012
DO - 10.1016/j.rse.2022.113012
M3 - Journal article
VL - 274
JO - Remote Sensing of Environment
JF - Remote Sensing of Environment
SN - 0034-4257
M1 - 113012
ER -