A Novel Loop Closure Detection Method Using Line Features
Loop closure detection is a significant requirement for simultaneous localization and mapping (SLAM) to recognize revisited place. This paper presents a novel line-based loop closure detection method for vision-based SLAM that allows reliable loop closure detections, especial under structural enviro...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8794488/ |
| _version_ | 1819078716737716224 |
|---|---|
| author | Ruifang Dong Zhan-guo Wei Changan Liu Jiangming Kan |
| author_facet | Ruifang Dong Zhan-guo Wei Changan Liu Jiangming Kan |
| author_sort | Ruifang Dong |
| collection | DOAJ |
| description | Loop closure detection is a significant requirement for simultaneous localization and mapping (SLAM) to recognize revisited place. This paper presents a novel line-based loop closure detection method for vision-based SLAM that allows reliable loop closure detections, especial under structural environment. The performance of coping with perceptual aliasing conditions is more competitive than point based methods. The bag of words model is extended in this work which uses only line features. A variant of TF-IDF (term frequency & inverse document frequency) scoring scheme is proposed by adding a discrimination coefficient to improve the discrimination of image similarity scores, further to reinforce the similarity evaluation of two images. LBD (Line Band Descriptor) and binary LBD features are extracted to build visual vocabularies. Temporal consistency and spatial continuity checks enhance detection reliability. The performance of proposed scoring scheme was compared with original TF-IDF, results show that our proposed scheme has competitive discrimination ability. We also compared the query performance of our vocabularies with ORB-based, MSLD (mean standard-deviation line descriptor)-based, and PL (Point-and-Line)-based vocabularies, results indicate that our vocabularies obtain the highest successful retrieval rate. The performance of the whole loop closure detection algorithm was also evaluated in terms of precision, recall and efficiency, which were compared with ORB, MSLD, PL-based methods, and also with CNN-based method, results demonstrate that our method is superior to others with satisfactory precision and efficiency. |
| first_indexed | 2024-12-21T19:17:31Z |
| format | Article |
| id | doaj.art-671da675a38b4ffc8f1743b09884ca1c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-21T19:17:31Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-671da675a38b4ffc8f1743b09884ca1c2022-12-21T18:53:02ZengIEEEIEEE Access2169-35362019-01-01711124511125610.1109/ACCESS.2019.29345218794488A Novel Loop Closure Detection Method Using Line FeaturesRuifang Dong0https://orcid.org/0000-0001-7247-4131Zhan-guo Wei1Changan Liu2Jiangming Kan3Key Lab of State Forestry Administration for Forestry Equipment and Automation, School of Technology, Beijing Forestry University, Beijing, ChinaSchool of Transportation and Logistics, Central South University of Forestry and Technology, Changsha, ChinaSchool of Control and Computer Engineering, North China Electric Power University, Beijing, ChinaKey Lab of State Forestry Administration for Forestry Equipment and Automation, School of Technology, Beijing Forestry University, Beijing, ChinaLoop closure detection is a significant requirement for simultaneous localization and mapping (SLAM) to recognize revisited place. This paper presents a novel line-based loop closure detection method for vision-based SLAM that allows reliable loop closure detections, especial under structural environment. The performance of coping with perceptual aliasing conditions is more competitive than point based methods. The bag of words model is extended in this work which uses only line features. A variant of TF-IDF (term frequency & inverse document frequency) scoring scheme is proposed by adding a discrimination coefficient to improve the discrimination of image similarity scores, further to reinforce the similarity evaluation of two images. LBD (Line Band Descriptor) and binary LBD features are extracted to build visual vocabularies. Temporal consistency and spatial continuity checks enhance detection reliability. The performance of proposed scoring scheme was compared with original TF-IDF, results show that our proposed scheme has competitive discrimination ability. We also compared the query performance of our vocabularies with ORB-based, MSLD (mean standard-deviation line descriptor)-based, and PL (Point-and-Line)-based vocabularies, results indicate that our vocabularies obtain the highest successful retrieval rate. The performance of the whole loop closure detection algorithm was also evaluated in terms of precision, recall and efficiency, which were compared with ORB, MSLD, PL-based methods, and also with CNN-based method, results demonstrate that our method is superior to others with satisfactory precision and efficiency.https://ieeexplore.ieee.org/document/8794488/Vision-based SLAMbag of wordsbinary LBDLBDa variant of TF-IDF scoring scheme |
| spellingShingle | Ruifang Dong Zhan-guo Wei Changan Liu Jiangming Kan A Novel Loop Closure Detection Method Using Line Features IEEE Access Vision-based SLAM bag of words binary LBD LBD a variant of TF-IDF scoring scheme |
| title | A Novel Loop Closure Detection Method Using Line Features |
| title_full | A Novel Loop Closure Detection Method Using Line Features |
| title_fullStr | A Novel Loop Closure Detection Method Using Line Features |
| title_full_unstemmed | A Novel Loop Closure Detection Method Using Line Features |
| title_short | A Novel Loop Closure Detection Method Using Line Features |
| title_sort | novel loop closure detection method using line features |
| topic | Vision-based SLAM bag of words binary LBD LBD a variant of TF-IDF scoring scheme |
| url | https://ieeexplore.ieee.org/document/8794488/ |
| work_keys_str_mv | AT ruifangdong anovelloopclosuredetectionmethodusinglinefeatures AT zhanguowei anovelloopclosuredetectionmethodusinglinefeatures AT changanliu anovelloopclosuredetectionmethodusinglinefeatures AT jiangmingkan anovelloopclosuredetectionmethodusinglinefeatures AT ruifangdong novelloopclosuredetectionmethodusinglinefeatures AT zhanguowei novelloopclosuredetectionmethodusinglinefeatures AT changanliu novelloopclosuredetectionmethodusinglinefeatures AT jiangmingkan novelloopclosuredetectionmethodusinglinefeatures |