收藏切换
Self-Supervised Monocular Depth Estimation Method for Joint Semantic Segmentation
收藏切换
Xiaogang Song1, 2, Haoyue Hu1, Jingyu Ning1, Li Liang1, Xiaofeng Lu1, 2, Xinhong Hei1, 2
Journal of Computer Research and Development | 2024, 61(5) : 1336 - 1347
Less
收藏切换
Journal of Computer Research and Development | 2024, 61(5): 1336-1347
• Artificial Intelligence •
Self-Supervised Monocular Depth Estimation Method for Joint Semantic Segmentation
Full
Xiaogang Song1, 2, Haoyue Hu1, Jingyu Ning1, Li Liang1, Xiaofeng Lu1, 2, Xinhong Hei1, 2
Affiliations
  • 1School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048
  • 2Human Machine Integration Intelligent Robot Shaanxi Provincial University Engineering Research Center (Xi’an University of Technology), Xi’an 710048
  • born in 1987. PhD, associate professor. His main research interests include autonomous navigation of unmanned aerial vehicles, computer vision, and image processing

    born in 1997. Master. Her main research interests include computer vision, image processing, and depth estimation

    born in 1997. Master candidate. His main research interests include depth estimation and semantic segmentation

    born in 1964. Master, associate professor. Her main research interests include computer vision and image processing, embedded computer control, and intelligent control

    born in 1976. PhD, professor. His main research interests include computer vision, intelligent computing, and pattern recognition

    born in 1976. PhD, professor. His main research interests include computer vision and artificial intelligence

About Author:

born in 1987. PhD, associate professor. His main research interests include autonomous navigation of unmanned aerial vehicles, computer vision, and image processing

born in 1997. Master. Her main research interests include computer vision, image processing, and depth estimation

born in 1997. Master candidate. His main research interests include depth estimation and semantic segmentation

born in 1964. Master, associate professor. Her main research interests include computer vision and image processing, embedded computer control, and intelligent control

born in 1976. PhD, professor. His main research interests include computer vision, intelligent computing, and pattern recognition

born in 1976. PhD, professor. His main research interests include computer vision and artificial intelligence

Published: 2024-05-01 doi: 10.7544/issn1000-1239.202330485
Outline
收藏切换

In this paper, the mutually beneficial relationship between depth estimation and semantic segmentation is investigated, and a self-supervised monocular depth estimation method for joint semantic segmentation USegDepth is proposed. The shared encoder for semantic segmentation and depth estimation is implemented to achieve semantic guidance. To further improve the across multiple tasks performance of the encoder, a multi-task feature extraction module is designed. The module is stacked to generate the shared encoder, solving the poor feature representation problem of the model due to limited receptive field and lack of cross-channel interaction, and the model accuracy is improved further. And a cross-task interaction module is proposed for bidirectional cross-domain information interaction to refine the depth features, improving depth estimation performance, especially in weak texture regions and object boundaries with limited luminosity consistency supervision. Through training and evaluation on KITTI dataset, the experimental results show that the mean square relative error of USegDepth is reduced by 0.176 percentage points compared with that of SGDepth, and the threshold accuracy reaches 98.4% at a threshold value of 1.253, proving the high accuracy of USegDepth in depth prediction.

self-supervised deep learning  /  depth estimation  /  semantic segmentation  /  multi-task association  /  shared encoder
宋霄罡, 胡浩越, 宁靖宇, 梁莉, 鲁晓锋, 黑新宏. 联合语义分割的自监督单目深度估计方法. 计算机研究与发展, 2024 , 61 (5) : 1336 -1347 . DOI: 10.7544/issn1000-1239.202330485
Xiaogang Song, Haoyue Hu, Jingyu Ning, Li Liang, Xiaofeng Lu, Xinhong Hei. Self-Supervised Monocular Depth Estimation Method for Joint Semantic Segmentation[J]. Journal of Computer Research and Development, 2024 , 61 (5) : 1336 -1347 . DOI: 10.7544/issn1000-1239.202330485
Year 2024 volume 61 Issue 5
73
34
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202330485
  • Receive Date:2023-06-12
  • Online Date:2026-11-17
  • Published:2024-05-01
Article Data
Affiliations
History
  • Received:2023-06-12
  • Revised:2024-01-03
  • Accepted:2024-03-06
Affiliations
    1School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048
    2Human Machine Integration Intelligent Robot Shaanxi Provincial University Engineering Research Center (Xi’an University of Technology), Xi’an 710048
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202330485
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT