An Encoder-Decoder Network Trained with Multi-Branch Auxiliary Learning for Extracting Transverse Aeolian Ridge Morphological Parameters from High-Resolution Mars Imagery

Transverse aeolian ridges (TARs) are the most widely distributed and enigmatic aeolian landforms on the surface of Mars, holding significant research value and implications for interpreting ancient wind fields and environments, searching for water and life, and selecting landing sites. However, accu...

Full description

Saved in:
Bibliographic Details
Main Authors: J. Sun, Z. Cao, Z. Kang, J. Li, J. Jiang, B. Song, X. Zhang
Format: Article
Language:English
Published: Copernicus Publications 2025-08-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1415/2025/isprs-archives-XLVIII-G-2025-1415-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1839605727344197632
author J. Sun
J. Sun
Z. Cao
Z. Cao
Z. Kang
Z. Kang
Z. Kang
J. Li
J. Jiang
B. Song
X. Zhang
author_facet J. Sun
J. Sun
Z. Cao
Z. Cao
Z. Kang
Z. Kang
Z. Kang
J. Li
J. Jiang
B. Song
X. Zhang
author_sort J. Sun
collection DOAJ
description Transverse aeolian ridges (TARs) are the most widely distributed and enigmatic aeolian landforms on the surface of Mars, holding significant research value and implications for interpreting ancient wind fields and environments, searching for water and life, and selecting landing sites. However, accurately interpreting the morphological parameters of TARs, including their edge contours and ridge lines, remains a challenge. To tackle this issue, this paper proposes a Multi-branch Auxiliary Training Encoder-Decoder Network (MATED-Net) for detecting the edge contours and ridge lines of TARs on Mars. Built upon the Unet architecture, MATED-Net incorporates four auxiliary training losses to perceive features at different scales. Then, We introduce a lightweight attention mechanism to guide the fusion of multi-scale features. Finally, an edge tracing loss is introduced to enhance the distinction between edge pixels and surrounding confusing pixels, thereby accurately tracking the true positions of edges. To verify the effectiveness of the MATED-Net in detecting TARs’ contours and ridge lines, this paper constructs a dataset of TAR ridge lines based on HiRISE and HiRIC imagery. To facilitate subsequent training and testing, all images were clipped to a size of 512 × 512and converted to the VOC dataset format, resulting in a total of 1000 images and corresponding label data. The experimental results demonstrate a precision of 0.72, a recall of 0.67, and a mean Intersection over Union (MIoU) of 0.57 for edge extraction.
format Article
id doaj-art-df1db809e3774d2fb896e6f4b3a5dcc5
institution Matheson Library
issn 1682-1750
2194-9034
language English
publishDate 2025-08-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-df1db809e3774d2fb896e6f4b3a5dcc52025-08-01T16:35:15ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-08-01XLVIII-G-20251415142010.5194/isprs-archives-XLVIII-G-2025-1415-2025An Encoder-Decoder Network Trained with Multi-Branch Auxiliary Learning for Extracting Transverse Aeolian Ridge Morphological Parameters from High-Resolution Mars ImageryJ. Sun0J. Sun1Z. Cao2Z. Cao3Z. Kang4Z. Kang5Z. Kang6J. Li7J. Jiang8B. Song9X. Zhang10College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, ChinaSubcenter of International Cooperation and Research on Lunar and Planetary Exploration, Center of Space Exploration, Ministry of Education of The People’s Republic of China, No. 29 Xueyuan Road, Haidian District, Beijing 100083, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, ChinaSubcenter of International Cooperation and Research on Lunar and Planetary Exploration, Center of Space Exploration, Ministry of Education of The People’s Republic of China, No. 29 Xueyuan Road, Haidian District, Beijing 100083, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, ChinaSchool of Land Science and Technology, China University of Geosciences, Xueyuan Road, Beijing, 100083, ChinaSubcenter of International Cooperation and Research on Lunar and Planetary Exploration, Center of Space Exploration, Ministry of Education of The People’s Republic of China, No. 29 Xueyuan Road, Haidian District, Beijing 100083, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, ChinaTransverse aeolian ridges (TARs) are the most widely distributed and enigmatic aeolian landforms on the surface of Mars, holding significant research value and implications for interpreting ancient wind fields and environments, searching for water and life, and selecting landing sites. However, accurately interpreting the morphological parameters of TARs, including their edge contours and ridge lines, remains a challenge. To tackle this issue, this paper proposes a Multi-branch Auxiliary Training Encoder-Decoder Network (MATED-Net) for detecting the edge contours and ridge lines of TARs on Mars. Built upon the Unet architecture, MATED-Net incorporates four auxiliary training losses to perceive features at different scales. Then, We introduce a lightweight attention mechanism to guide the fusion of multi-scale features. Finally, an edge tracing loss is introduced to enhance the distinction between edge pixels and surrounding confusing pixels, thereby accurately tracking the true positions of edges. To verify the effectiveness of the MATED-Net in detecting TARs’ contours and ridge lines, this paper constructs a dataset of TAR ridge lines based on HiRISE and HiRIC imagery. To facilitate subsequent training and testing, all images were clipped to a size of 512 × 512and converted to the VOC dataset format, resulting in a total of 1000 images and corresponding label data. The experimental results demonstrate a precision of 0.72, a recall of 0.67, and a mean Intersection over Union (MIoU) of 0.57 for edge extraction.https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1415/2025/isprs-archives-XLVIII-G-2025-1415-2025.pdf
spellingShingle J. Sun
J. Sun
Z. Cao
Z. Cao
Z. Kang
Z. Kang
Z. Kang
J. Li
J. Jiang
B. Song
X. Zhang
An Encoder-Decoder Network Trained with Multi-Branch Auxiliary Learning for Extracting Transverse Aeolian Ridge Morphological Parameters from High-Resolution Mars Imagery
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title An Encoder-Decoder Network Trained with Multi-Branch Auxiliary Learning for Extracting Transverse Aeolian Ridge Morphological Parameters from High-Resolution Mars Imagery
title_full An Encoder-Decoder Network Trained with Multi-Branch Auxiliary Learning for Extracting Transverse Aeolian Ridge Morphological Parameters from High-Resolution Mars Imagery
title_fullStr An Encoder-Decoder Network Trained with Multi-Branch Auxiliary Learning for Extracting Transverse Aeolian Ridge Morphological Parameters from High-Resolution Mars Imagery
title_full_unstemmed An Encoder-Decoder Network Trained with Multi-Branch Auxiliary Learning for Extracting Transverse Aeolian Ridge Morphological Parameters from High-Resolution Mars Imagery
title_short An Encoder-Decoder Network Trained with Multi-Branch Auxiliary Learning for Extracting Transverse Aeolian Ridge Morphological Parameters from High-Resolution Mars Imagery
title_sort encoder decoder network trained with multi branch auxiliary learning for extracting transverse aeolian ridge morphological parameters from high resolution mars imagery
url https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1415/2025/isprs-archives-XLVIII-G-2025-1415-2025.pdf
work_keys_str_mv AT jsun anencoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT jsun anencoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT zcao anencoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT zcao anencoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT zkang anencoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT zkang anencoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT zkang anencoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT jli anencoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT jjiang anencoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT bsong anencoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT xzhang anencoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT jsun encoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT jsun encoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT zcao encoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT zcao encoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT zkang encoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT zkang encoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT zkang encoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT jli encoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT jjiang encoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT bsong encoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery
AT xzhang encoderdecodernetworktrainedwithmultibranchauxiliarylearningforextractingtransverseaeolianridgemorphologicalparametersfromhighresolutionmarsimagery