Importance-Aware Image Segmentation-based Semantic Communication for Autonomous Driving
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909076769734656 |
|---|---|
| author | Lv, Jie Tong, Haonan Pan, Qiang Zhang, Zhilong He, Xinxin Luo, Tao Yin, Changchuan |
| author_facet | Lv, Jie Tong, Haonan Pan, Qiang Zhang, Zhilong He, Xinxin Luo, Tao Yin, Changchuan |
| contents | This article studies the problem of image segmentation-based semantic communication in autonomous driving. In real traffic scenes, detecting the key objects (e.g., vehicles, pedestrians and obstacles) is more crucial than that of other objects to guarantee driving safety. Therefore, we propose a vehicular image segmentation-oriented semantic communication system, termed VIS-SemCom, where image segmentation features of important objects are transmitted to reduce transmission redundancy. First, to accurately extract image semantics, we develop a semantic codec based on Swin Transformer architecture, which expands the perceptual field thus improving the segmentation accuracy. Next, we propose a multi-scale semantic extraction scheme via assigning the number of Swin Transformer blocks for diverse resolution features, thus highlighting the important objects' accuracy. Furthermore, the importance-aware loss is invoked to emphasize the important objects, and an online hard sample mining (OHEM) strategy is proposed to handle small sample issues in the dataset. Experimental results demonstrate that the proposed VIS-SemCom can achieve a coding gain of nearly 6 dB with a 60% mean intersection over union (mIoU), reduce the transmitted data amount by up to 70% with a 60% mIoU, and improve the segmentation intersection over union (IoU) of important objects by 4%, compared to traditional transmission scheme. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10153 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Importance-Aware Image Segmentation-based Semantic Communication for Autonomous Driving Lv, Jie Tong, Haonan Pan, Qiang Zhang, Zhilong He, Xinxin Luo, Tao Yin, Changchuan Networking and Internet Architecture Computer Vision and Pattern Recognition This article studies the problem of image segmentation-based semantic communication in autonomous driving. In real traffic scenes, detecting the key objects (e.g., vehicles, pedestrians and obstacles) is more crucial than that of other objects to guarantee driving safety. Therefore, we propose a vehicular image segmentation-oriented semantic communication system, termed VIS-SemCom, where image segmentation features of important objects are transmitted to reduce transmission redundancy. First, to accurately extract image semantics, we develop a semantic codec based on Swin Transformer architecture, which expands the perceptual field thus improving the segmentation accuracy. Next, we propose a multi-scale semantic extraction scheme via assigning the number of Swin Transformer blocks for diverse resolution features, thus highlighting the important objects' accuracy. Furthermore, the importance-aware loss is invoked to emphasize the important objects, and an online hard sample mining (OHEM) strategy is proposed to handle small sample issues in the dataset. Experimental results demonstrate that the proposed VIS-SemCom can achieve a coding gain of nearly 6 dB with a 60% mean intersection over union (mIoU), reduce the transmitted data amount by up to 70% with a 60% mIoU, and improve the segmentation intersection over union (IoU) of important objects by 4%, compared to traditional transmission scheme. |
| title | Importance-Aware Image Segmentation-based Semantic Communication for Autonomous Driving |
| topic | Networking and Internet Architecture Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.10153 |