LBNet: A Lightweight Bilateral Network for Semantic Segmentation of Martian Rock

Rock segmentation on the Martian surface is particularly critical for rover navigation, obstacle avoidance, and scientific target detection. We propose a lightweight bilateral network for semantic segmentation of Martian rock (LBNet). The network consists of a shallow spatial detail branch (SDB) and...

Full description

Saved in:
Bibliographic Details
Main Authors: Pengfei Wei, Zezhou Sun, He Tian
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10777027/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850264746032365568
author Pengfei Wei
Zezhou Sun
He Tian
author_facet Pengfei Wei
Zezhou Sun
He Tian
author_sort Pengfei Wei
collection DOAJ
description Rock segmentation on the Martian surface is particularly critical for rover navigation, obstacle avoidance, and scientific target detection. We propose a lightweight bilateral network for semantic segmentation of Martian rock (LBNet). The network consists of a shallow spatial detail branch (SDB) and a deep semantic information branch (SIB). In the shallow spatial detail branch, dense connection channel aggregation convolution (CAConv) is adopted to establish local dependencies for each pixel and preserve detailed information. In the deep semantic information branch, channel split convolution (CSConv) is adopted to extract features by adopting different convolution kernels on different channel, reducing the similarity between different feature maps and increasing feature maps diversity. Finally, a feature fusion module (FFM) is designed to effectively fuse feature maps at different levels. With only 0.37M parameters, the model achieved 93.85% mIoU and 147.8 FPS on the dataset of Perseverance, and 88.62% mIoU and 152.5 FPS on the Curiosity dataset. Experiments show that the model achieves a good balance between segmentation accuracy and inference speed.
format Article
id doaj-art-d77555ed159a499bbc9d59f12dea19fb
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-d77555ed159a499bbc9d59f12dea19fb2025-08-20T01:54:38ZengIEEEIEEE Access2169-35362024-01-011218213718214410.1109/ACCESS.2024.351108410777027LBNet: A Lightweight Bilateral Network for Semantic Segmentation of Martian RockPengfei Wei0https://orcid.org/0009-0001-1888-6327Zezhou Sun1He Tian2School of Mechanical and Aerospace Engineering, Jilin University, Changchun, ChinaBeijing Institute of Spacecraft System Engineering, Beijing, ChinaBeijing Institute of Spacecraft System Engineering, Beijing, ChinaRock segmentation on the Martian surface is particularly critical for rover navigation, obstacle avoidance, and scientific target detection. We propose a lightweight bilateral network for semantic segmentation of Martian rock (LBNet). The network consists of a shallow spatial detail branch (SDB) and a deep semantic information branch (SIB). In the shallow spatial detail branch, dense connection channel aggregation convolution (CAConv) is adopted to establish local dependencies for each pixel and preserve detailed information. In the deep semantic information branch, channel split convolution (CSConv) is adopted to extract features by adopting different convolution kernels on different channel, reducing the similarity between different feature maps and increasing feature maps diversity. Finally, a feature fusion module (FFM) is designed to effectively fuse feature maps at different levels. With only 0.37M parameters, the model achieved 93.85% mIoU and 147.8 FPS on the dataset of Perseverance, and 88.62% mIoU and 152.5 FPS on the Curiosity dataset. Experiments show that the model achieves a good balance between segmentation accuracy and inference speed.https://ieeexplore.ieee.org/document/10777027/Semantic segmentationrock segmentationfeature fusiondeep learning
spellingShingle Pengfei Wei
Zezhou Sun
He Tian
LBNet: A Lightweight Bilateral Network for Semantic Segmentation of Martian Rock
IEEE Access
Semantic segmentation
rock segmentation
feature fusion
deep learning
title LBNet: A Lightweight Bilateral Network for Semantic Segmentation of Martian Rock
title_full LBNet: A Lightweight Bilateral Network for Semantic Segmentation of Martian Rock
title_fullStr LBNet: A Lightweight Bilateral Network for Semantic Segmentation of Martian Rock
title_full_unstemmed LBNet: A Lightweight Bilateral Network for Semantic Segmentation of Martian Rock
title_short LBNet: A Lightweight Bilateral Network for Semantic Segmentation of Martian Rock
title_sort lbnet a lightweight bilateral network for semantic segmentation of martian rock
topic Semantic segmentation
rock segmentation
feature fusion
deep learning
url https://ieeexplore.ieee.org/document/10777027/
work_keys_str_mv AT pengfeiwei lbnetalightweightbilateralnetworkforsemanticsegmentationofmartianrock
AT zezhousun lbnetalightweightbilateralnetworkforsemanticsegmentationofmartianrock
AT hetian lbnetalightweightbilateralnetworkforsemanticsegmentationofmartianrock