BIMII-Net: Brain-Inspired Multi-Iterative Interactive Network for RGB-T Road Scene Semantic Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qiu, Hanshuo, Jiang, Jie, Yang, Ruoli, Zhan, Lixin, Liu, Jizhao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915213011320832
author Qiu, Hanshuo
Jiang, Jie
Yang, Ruoli
Zhan, Lixin
Liu, Jizhao
author_facet Qiu, Hanshuo
Jiang, Jie
Yang, Ruoli
Zhan, Lixin
Liu, Jizhao
contents RGB-T road scene semantic segmentation enhances visual scene understanding in complex environments characterized by inadequate illumination or occlusion by fusing information from RGB and thermal images. Nevertheless, existing RGB-T semantic segmentation models typically depend on simple addition or concatenation strategies or ignore the differences between information at different levels. To address these issues, we proposed a novel RGB-T road scene semantic segmentation network called Brain-Inspired Multi-Iteration Interaction Network (BIMII-Net). First, to meet the requirements of accurate texture and local information extraction in road scenarios like autonomous driving, we proposed a deep continuous-coupled neural network (DCCNN) architecture based on a brain-inspired model. Second, to enhance the interaction and expression capabilities among multi-modal information, we designed a cross explicit attention-enhanced fusion module (CEAEF-Module) in the feature fusion stage of BIMII-Net to effectively integrate features at different levels. Finally, we constructed a complementary interactive multi-layer decoder structure, incorporating the shallow-level feature iteration module (SFI-Module), the deep-level feature iteration module (DFI-Module), and the multi-feature enhancement module (MFE-Module) to collaboratively extract texture details and global skeleton information, with multi-module joint supervision further optimizing the segmentation results. Experimental results demonstrate that BIMII-Net achieves state-of-the-art (SOTA) performance in the brain-inspired computing domain and outperforms most existing RGB-T semantic segmentation methods. It also exhibits strong generalization capabilities on multiple RGB-T datasets, proving the effectiveness of brain-inspired computer models in multi-modal image segmentation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2503_19303
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BIMII-Net: Brain-Inspired Multi-Iterative Interactive Network for RGB-T Road Scene Semantic Segmentation
Qiu, Hanshuo
Jiang, Jie
Yang, Ruoli
Zhan, Lixin
Liu, Jizhao
Computer Vision and Pattern Recognition
RGB-T road scene semantic segmentation enhances visual scene understanding in complex environments characterized by inadequate illumination or occlusion by fusing information from RGB and thermal images. Nevertheless, existing RGB-T semantic segmentation models typically depend on simple addition or concatenation strategies or ignore the differences between information at different levels. To address these issues, we proposed a novel RGB-T road scene semantic segmentation network called Brain-Inspired Multi-Iteration Interaction Network (BIMII-Net). First, to meet the requirements of accurate texture and local information extraction in road scenarios like autonomous driving, we proposed a deep continuous-coupled neural network (DCCNN) architecture based on a brain-inspired model. Second, to enhance the interaction and expression capabilities among multi-modal information, we designed a cross explicit attention-enhanced fusion module (CEAEF-Module) in the feature fusion stage of BIMII-Net to effectively integrate features at different levels. Finally, we constructed a complementary interactive multi-layer decoder structure, incorporating the shallow-level feature iteration module (SFI-Module), the deep-level feature iteration module (DFI-Module), and the multi-feature enhancement module (MFE-Module) to collaboratively extract texture details and global skeleton information, with multi-module joint supervision further optimizing the segmentation results. Experimental results demonstrate that BIMII-Net achieves state-of-the-art (SOTA) performance in the brain-inspired computing domain and outperforms most existing RGB-T semantic segmentation methods. It also exhibits strong generalization capabilities on multiple RGB-T datasets, proving the effectiveness of brain-inspired computer models in multi-modal image segmentation tasks.
title BIMII-Net: Brain-Inspired Multi-Iterative Interactive Network for RGB-T Road Scene Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.19303