PAINet: Toward Fast and Efficient Parking Lot Lane Detection
Parking lot lane detection is a critical component of automated driving technology, requiring high accuracy, speed, and ease of deployment. In this study, we aimed to develop a comprehensive dataset of parking lane lines and construct an innovative parking lot recognition model. The model, named the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10478535/ |
| _version_ | 1797231242221977600 |
|---|---|
| author | Qiming Cai Rong Yang Mingli Wen Wei Huang Jingxiao Gu |
| author_facet | Qiming Cai Rong Yang Mingli Wen Wei Huang Jingxiao Gu |
| author_sort | Qiming Cai |
| collection | DOAJ |
| description | Parking lot lane detection is a critical component of automated driving technology, requiring high accuracy, speed, and ease of deployment. In this study, we aimed to develop a comprehensive dataset of parking lane lines and construct an innovative parking lot recognition model. The model, named the Point Angle Instance Network (PAINet), effectively clusters each key point by embedding angle information, thus enhancing the stability and training efficiency. Additionally, we have developed an information collection module to address the issue of fault detection of the guidance arrow in parking lot environments. The performance of the model was tested and evaluated using the created parking lane dataset, and promising results were obtained. The model achieved an F1 score of 85.48%, an FPS of 164, and a GFLOPs of 4.1 in the task of parking lot lane detection in a surround-view situation. These results indicate the accuracy, practicality, and real-time performance of the model, highlighting its potential for use in automated driving systems. |
| first_indexed | 2024-04-24T15:41:16Z |
| format | Article |
| id | doaj.art-ff0c522f3b5449da87709614c2bb82e4 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T15:41:16Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ff0c522f3b5449da87709614c2bb82e42024-04-01T23:00:36ZengIEEEIEEE Access2169-35362024-01-0112452164522810.1109/ACCESS.2024.338148810478535PAINet: Toward Fast and Efficient Parking Lot Lane DetectionQiming Cai0https://orcid.org/0009-0008-1121-4086Rong Yang1https://orcid.org/0000-0002-6287-2854Mingli Wen2Wei Huang3Jingxiao Gu4School of Mechanical Engineering, Guangxi University, Guangxi, ChinaSchool of Mechanical Engineering, Guangxi University, Guangxi, ChinaSchool of Mechanical Engineering, Guangxi University, Guangxi, ChinaSchool of Mechanical Engineering, Guangxi University, Guangxi, ChinaSchool of Mechanical Engineering, Guangxi University, Guangxi, ChinaParking lot lane detection is a critical component of automated driving technology, requiring high accuracy, speed, and ease of deployment. In this study, we aimed to develop a comprehensive dataset of parking lane lines and construct an innovative parking lot recognition model. The model, named the Point Angle Instance Network (PAINet), effectively clusters each key point by embedding angle information, thus enhancing the stability and training efficiency. Additionally, we have developed an information collection module to address the issue of fault detection of the guidance arrow in parking lot environments. The performance of the model was tested and evaluated using the created parking lane dataset, and promising results were obtained. The model achieved an F1 score of 85.48%, an FPS of 164, and a GFLOPs of 4.1 in the task of parking lot lane detection in a surround-view situation. These results indicate the accuracy, practicality, and real-time performance of the model, highlighting its potential for use in automated driving systems.https://ieeexplore.ieee.org/document/10478535/Autonomous vehicleslane detectioncomputer visionneural networks |
| spellingShingle | Qiming Cai Rong Yang Mingli Wen Wei Huang Jingxiao Gu PAINet: Toward Fast and Efficient Parking Lot Lane Detection IEEE Access Autonomous vehicles lane detection computer vision neural networks |
| title | PAINet: Toward Fast and Efficient Parking Lot Lane Detection |
| title_full | PAINet: Toward Fast and Efficient Parking Lot Lane Detection |
| title_fullStr | PAINet: Toward Fast and Efficient Parking Lot Lane Detection |
| title_full_unstemmed | PAINet: Toward Fast and Efficient Parking Lot Lane Detection |
| title_short | PAINet: Toward Fast and Efficient Parking Lot Lane Detection |
| title_sort | painet toward fast and efficient parking lot lane detection |
| topic | Autonomous vehicles lane detection computer vision neural networks |
| url | https://ieeexplore.ieee.org/document/10478535/ |
| work_keys_str_mv | AT qimingcai painettowardfastandefficientparkinglotlanedetection AT rongyang painettowardfastandefficientparkinglotlanedetection AT mingliwen painettowardfastandefficientparkinglotlanedetection AT weihuang painettowardfastandefficientparkinglotlanedetection AT jingxiaogu painettowardfastandefficientparkinglotlanedetection |