Semantic Loop Closure Detection for Intelligent Vehicles Using Panoramas

doi:10.1109/TIV.2023.3298608

科研成果详情

题名	Semantic Loop Closure Detection for Intelligent Vehicles Using Panoramas
作者	Xiao，Dingwen; Li，Sirui; Xuanyuan，Zhe
发表日期	2023-10-01
发表期刊	IEEE Transactions on Intelligent Vehicles
卷号	8 期号:10 页码:4395-4405
摘要	Loop Closure Detection is of great significance in the field of intelligent driving systems, as it reduces the cumulative error of the estimated position of the system and assists in generating a consistent global map. Existing methods differ in frame representation methods and the corresponding frame-matching strategy. Traditionally, local feature points and descriptors are studied extensively while recently global descriptors and semantic information extracted from deep learning methods are considered superior in terms of promoting a high-level understanding of the surrounding environments of robots. However, one of the most challenging problems of using semantic information for loop detection is how to deal with inconsistent visual contents from different viewpoints in the same place. In this article, a semantic loop closure detection method using panoramas is proposed to address this issue. We design a pipeline for efficiently extracting and matching semantic information between frames to identify loops. Most importantly we propose a novel polar coordinate-based panorama representation to address the inconsistent visual appearance problem caused by viewpoint differences. Experiment results show that our proposed method can significantly increase the accuracy of loop closure detection tasks in challenging scenarios where traditional methods may fail.
关键词	Autonomous driving loop closure detection panoramic segmentation semantic segmentation
DOI	10.1109/TIV.2023.3298608
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-85165898177
引用统计
文献类型	期刊论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/11565
专题	北师香港浸会大学
通讯作者	Xuanyuan，Zhe
作者单位	BNU-HKBU United International College,Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science,Zhuhai,519087,China
第一作者单位	北师香港浸会大学
通讯作者单位	北师香港浸会大学
推荐引用方式 GB/T 7714	Xiao，Dingwen,Li，Sirui,Xuanyuan，Zhe. Semantic Loop Closure Detection for Intelligent Vehicles Using Panoramas[J]. IEEE Transactions on Intelligent Vehicles, 2023, 8(10): 4395-4405.
APA	Xiao，Dingwen, Li，Sirui, & Xuanyuan，Zhe. (2023). Semantic Loop Closure Detection for Intelligent Vehicles Using Panoramas. IEEE Transactions on Intelligent Vehicles, 8(10), 4395-4405.
MLA	Xiao，Dingwen,et al."Semantic Loop Closure Detection for Intelligent Vehicles Using Panoramas". IEEE Transactions on Intelligent Vehicles 8.10(2023): 4395-4405.