File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.3390/s22228604
- Scopus: eid_2-s2.0-85142739103
- PMID: 36433200
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: STV-SC: Segmentation and Temporal Verification Enhanced Scan Context for Place Recognition in Unstructured Environment
Title | STV-SC: Segmentation and Temporal Verification Enhanced Scan Context for Place Recognition in Unstructured Environment |
---|---|
Authors | |
Keywords | loop closure place recognition point cloud segmentation simultaneous localization and mapping (SLAM) temporal verification unstructured objects |
Issue Date | 8-Nov-2022 |
Publisher | MDPI |
Citation | Sensors, 2022, v. 22, n. 22 How to Cite? |
Abstract | Place recognition is an essential part of simultaneous localization and mapping (SLAM). LiDAR-based place recognition relies almost exclusively on geometric information. However, geometric information may become unreliable when faced with environments dominated by unstructured objects. In this paper, we explore the role of segmentation for extracting key structured information. We propose STV-SC, a novel segmentation and temporal verification enhanced place recognition method for unstructured environments. It contains a range image-based 3D point segmentation algorithm and a three-stage process to detect a loop. The three-stage method consists of a two-stage candidate loop search process and a one-stage segmentation and temporal verification (STV) process. Our STV process utilizes the time-continuous feature of SLAM to determine whether there is an occasional mismatch. We quantitatively demonstrate that the STV process can trigger false detections caused by unstructured objects and effectively extract structured objects to avoid outliers. Comparison with state-of-art algorithms on public datasets shows that STV-SC can run online and achieve improved performance in unstructured environments (Under the same precision, the recall rate is 1.4∼16% higher than Scan context). Therefore, our algorithm can effectively avoid the mismatching caused by the original algorithm in unstructured environment and improve the environmental adaptability of mobile agents. |
Persistent Identifier | http://hdl.handle.net/10722/344944 |
ISSN | 2020 SCImago Journal Rankings: 0.636 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Tian, Xiaojie | - |
dc.contributor.author | Yi, Peng | - |
dc.contributor.author | Zhang, Fu | - |
dc.contributor.author | Lei, Jinlong | - |
dc.contributor.author | Hong, Yiguang | - |
dc.date.accessioned | 2024-08-14T08:56:26Z | - |
dc.date.available | 2024-08-14T08:56:26Z | - |
dc.date.issued | 2022-11-08 | - |
dc.identifier.citation | Sensors, 2022, v. 22, n. 22 | - |
dc.identifier.issn | 1424-3210 | - |
dc.identifier.uri | http://hdl.handle.net/10722/344944 | - |
dc.description.abstract | Place recognition is an essential part of simultaneous localization and mapping (SLAM). LiDAR-based place recognition relies almost exclusively on geometric information. However, geometric information may become unreliable when faced with environments dominated by unstructured objects. In this paper, we explore the role of segmentation for extracting key structured information. We propose STV-SC, a novel segmentation and temporal verification enhanced place recognition method for unstructured environments. It contains a range image-based 3D point segmentation algorithm and a three-stage process to detect a loop. The three-stage method consists of a two-stage candidate loop search process and a one-stage segmentation and temporal verification (STV) process. Our STV process utilizes the time-continuous feature of SLAM to determine whether there is an occasional mismatch. We quantitatively demonstrate that the STV process can trigger false detections caused by unstructured objects and effectively extract structured objects to avoid outliers. Comparison with state-of-art algorithms on public datasets shows that STV-SC can run online and achieve improved performance in unstructured environments (Under the same precision, the recall rate is 1.4∼16% higher than Scan context). Therefore, our algorithm can effectively avoid the mismatching caused by the original algorithm in unstructured environment and improve the environmental adaptability of mobile agents. | - |
dc.language | eng | - |
dc.publisher | MDPI | - |
dc.relation.ispartof | Sensors | - |
dc.subject | loop closure | - |
dc.subject | place recognition | - |
dc.subject | point cloud segmentation | - |
dc.subject | simultaneous localization and mapping (SLAM) | - |
dc.subject | temporal verification | - |
dc.subject | unstructured objects | - |
dc.title | STV-SC: Segmentation and Temporal Verification Enhanced Scan Context for Place Recognition in Unstructured Environment | - |
dc.type | Article | - |
dc.identifier.doi | 10.3390/s22228604 | - |
dc.identifier.pmid | 36433200 | - |
dc.identifier.scopus | eid_2-s2.0-85142739103 | - |
dc.identifier.volume | 22 | - |
dc.identifier.issue | 22 | - |
dc.identifier.eissn | 1424-8220 | - |
dc.identifier.issnl | 1424-8220 | - |