@inproceedings{79923a21eaf84858b4950d7659f8d822,
title = "Real-Time LiDAR Point Cloud Semantic Segmentation for Unstructured Road Autonomous Driving",
abstract = "Lidar-based semantic segmentation is critical for autonomous driving, but existing methods struggle with real-time performance in unstructured environments like open-pit mining areas. This paper proposes a real-time semantic segmentation network leveraging an attention mechanism to improve accuracy and speed. Key innovations include a global contextual information extraction module, bilinear upsampling layers to reduce channel redundancy, and coordinate attention-based upsampling to alleviate structural redundancy. This paper tested the proposed method on an unstructured road open-pit mining dataset, achieving an average IoU of 85.6\% and an inference speed of 5.90ms, which is 4.3\% and 14.6\% higher than the baseline (SalsaNext) in terms of accuracy and speed, respectively.",
keywords = "Point cloud, attention mechanism, semantic segmentation, unstructured road",
author = "Huazhi Li and Guizhen Yu and Zhangyu Wang and Yang Chen and Fei Zhao",
note = "Publisher Copyright: {\textcopyright} Beijing Paike Culture Commu. Co., Ltd. 2025.; International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024 ; Conference date: 06-12-2024 Through 08-12-2024",
year = "2025",
doi = "10.1007/978-981-96-3973-1\_22",
language = "英语",
isbn = "9789819639724",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "198--208",
editor = "Jun Liu and Yongcai Wang and Bin Wu and Zehao Jiang and Yao Xiao",
booktitle = "The Proceedings of 2024 International Conference on Artificial Intelligence and Autonomous Transportation - Volume V",
address = "德国",
}