PLSAV: Parallel loop searching and verifying for loop closure detection
Abstract Visual simultaneous localization and mapping (vSLAM), one of the most important applications in autonomous vehicles and robots to estimate the position and pose using inexpensive visual sensors, suffers from error accumulation for long‐term navigation without loop closure detection. Recentl...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-05-01
|
| Series: | IET Intelligent Transport Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/itr2.12054 |
| _version_ | 1811266463738101760 |
|---|---|
| author | Zhe Yang Yun Pan Lei Deng Yuan Xie Ruohong Huan |
| author_facet | Zhe Yang Yun Pan Lei Deng Yuan Xie Ruohong Huan |
| author_sort | Zhe Yang |
| collection | DOAJ |
| description | Abstract Visual simultaneous localization and mapping (vSLAM), one of the most important applications in autonomous vehicles and robots to estimate the position and pose using inexpensive visual sensors, suffers from error accumulation for long‐term navigation without loop closure detection. Recently, deep neural networks (DNNs) are leveraged to achieve high accuracy for loop closure detection, however the execution time is much slower than those employing handcrafted visual features. In this paper, a parallel loop searching and verifying method for loop closure detection with both high accuracy and high speed, which combines two parallel tasks using handcrafted and DNN features, respectively, is proposed. A fast loop searching is proposed to link the bag‐of‐words features and histogram for higher accuracy, and it splits the images into multiple grids for high parallelism; meanwhile, a DNN feature extractor is utilized for further verification. A loop state control method based on a finite state machine to control these tasks is designed, wherein the loop closure detection is described as a context‐related procedure. The framework is implemented on a real machine, and the top‐2 best accuracy and fastest execution time of 80‐543 frames per second (min: 1.84ms, and max: 12.45ms) are achieved on several public benchmarks compared with some existing algorithms. |
| first_indexed | 2024-04-12T20:43:44Z |
| format | Article |
| id | doaj.art-4f9e528b4344492688de9eb38796506b |
| institution | Directory Open Access Journal |
| issn | 1751-956X 1751-9578 |
| language | English |
| last_indexed | 2024-04-12T20:43:44Z |
| publishDate | 2021-05-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Intelligent Transport Systems |
| spelling | doaj.art-4f9e528b4344492688de9eb38796506b2022-12-22T03:17:21ZengWileyIET Intelligent Transport Systems1751-956X1751-95782021-05-0115568369810.1049/itr2.12054PLSAV: Parallel loop searching and verifying for loop closure detectionZhe Yang0Yun Pan1Lei Deng2Yuan Xie3Ruohong Huan4College of Information Science and Electronic Engineering Zhejiang University Hangzhou ChinaCollege of Information Science and Electronic Engineering Zhejiang University Hangzhou ChinaDepartment of Electrical and Computer Engineering University of California Santa Barbara California USADepartment of Electrical and Computer Engineering University of California Santa Barbara California USACollege of Computer Science and Technology Zhejiang University of Technology Hangzhou ChinaAbstract Visual simultaneous localization and mapping (vSLAM), one of the most important applications in autonomous vehicles and robots to estimate the position and pose using inexpensive visual sensors, suffers from error accumulation for long‐term navigation without loop closure detection. Recently, deep neural networks (DNNs) are leveraged to achieve high accuracy for loop closure detection, however the execution time is much slower than those employing handcrafted visual features. In this paper, a parallel loop searching and verifying method for loop closure detection with both high accuracy and high speed, which combines two parallel tasks using handcrafted and DNN features, respectively, is proposed. A fast loop searching is proposed to link the bag‐of‐words features and histogram for higher accuracy, and it splits the images into multiple grids for high parallelism; meanwhile, a DNN feature extractor is utilized for further verification. A loop state control method based on a finite state machine to control these tasks is designed, wherein the loop closure detection is described as a context‐related procedure. The framework is implemented on a real machine, and the top‐2 best accuracy and fastest execution time of 80‐543 frames per second (min: 1.84ms, and max: 12.45ms) are achieved on several public benchmarks compared with some existing algorithms.https://doi.org/10.1049/itr2.12054Image recognitionMobile robotsAutomata theoryComputer vision and image processing techniquesMachine learning (artificial intelligence)Neural nets |
| spellingShingle | Zhe Yang Yun Pan Lei Deng Yuan Xie Ruohong Huan PLSAV: Parallel loop searching and verifying for loop closure detection IET Intelligent Transport Systems Image recognition Mobile robots Automata theory Computer vision and image processing techniques Machine learning (artificial intelligence) Neural nets |
| title | PLSAV: Parallel loop searching and verifying for loop closure detection |
| title_full | PLSAV: Parallel loop searching and verifying for loop closure detection |
| title_fullStr | PLSAV: Parallel loop searching and verifying for loop closure detection |
| title_full_unstemmed | PLSAV: Parallel loop searching and verifying for loop closure detection |
| title_short | PLSAV: Parallel loop searching and verifying for loop closure detection |
| title_sort | plsav parallel loop searching and verifying for loop closure detection |
| topic | Image recognition Mobile robots Automata theory Computer vision and image processing techniques Machine learning (artificial intelligence) Neural nets |
| url | https://doi.org/10.1049/itr2.12054 |
| work_keys_str_mv | AT zheyang plsavparallelloopsearchingandverifyingforloopclosuredetection AT yunpan plsavparallelloopsearchingandverifyingforloopclosuredetection AT leideng plsavparallelloopsearchingandverifyingforloopclosuredetection AT yuanxie plsavparallelloopsearchingandverifyingforloopclosuredetection AT ruohonghuan plsavparallelloopsearchingandverifyingforloopclosuredetection |