A RGB-Thermal Image Segmentation Method Based on Parameter Sharing and Attention Fusion for Safe Autonomous Driving

In this paper, we propose a new RGB-thermal image segmentation method based on parameter sharing and attention fusion for safe autonomous driving. An encoder-decoder network structure is adopted. The encoder, which has shared convolution layer parameters and private batch normalization layer paramet...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on intelligent transportation systems Ročník 25; číslo 6; s. 5122 - 5137
Hlavní autoři: Li, Guofa, Lin, Yongjie, Ouyang, Delin, Li, Shen, Luo, Xiao, Qu, Xingda, Pi, Dawei, Li, Shengbo Eben
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.06.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Autonomous driving
Autonomous vehicles
Convolutional neural networks
Decoding
Encoders-Decoders
Feature extraction
image fusion
Image segmentation
Parameters
RGB image
Semantic segmentation
Semantics
thermal image
Thermal imaging
Transformers
ISSN:1524-9050, 1558-0016
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we propose a new RGB-thermal image segmentation method based on parameter sharing and attention fusion for safe autonomous driving. An encoder-decoder network structure is adopted. The encoder, which has shared convolution layer parameters and private batch normalization layer parameters (parameter sharing scheme), is used to extract features from RGB and thermal images. The extracted features are then fused by spatial and channel attention. The output of each residual block is fused, and the self-learning weight is used to integrate the fusion information of all residual blocks of the same levels. Subsequently, the fused features are integrated through a feature integration (FI) module in the decoder. Cross-entropy supervision of segmentation and edge is performed on the outputs of the decoders. Our proposed method is evaluated and compared with 17 state-of-the-art image segmentation methods, both qualitatively and quantitatively on the MFNet dataset which includes various objects in urban scenes. The results show that the proposed method outperforms previous methods by at least 0.3% and 1.8% in MRecall and MIoU, respectively, providing foundations for the development of autonomous driving technologies for safety enhancement.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1524-9050
1558-0016
DOI:10.1109/TITS.2023.3332350