Vacant Parking Slot Detection in the Around View Image Based on Deep Learning
Due to the complex visual environment, such as lighting variations, shadows, and limitations of vision, the accuracy of vacant parking slot detection for the park assist system (PAS) with a standalone around view monitor (AVM) needs to be improved. To address this problem, we propose a vacant parkin...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/7/2138 |
| _version_ | 1797570971455979520 |
|---|---|
| author | Wei Li Libo Cao Lingbo Yan Chaohui Li Xiexing Feng Peijie Zhao |
| author_facet | Wei Li Libo Cao Lingbo Yan Chaohui Li Xiexing Feng Peijie Zhao |
| author_sort | Wei Li |
| collection | DOAJ |
| description | Due to the complex visual environment, such as lighting variations, shadows, and limitations of vision, the accuracy of vacant parking slot detection for the park assist system (PAS) with a standalone around view monitor (AVM) needs to be improved. To address this problem, we propose a vacant parking slot detection method based on deep learning, namely VPS-Net. VPS-Net converts the vacant parking slot detection into a two-step problem, including parking slot detection and occupancy classification. In the parking slot detection stage, we propose a parking slot detection method based on YOLOv3, which combines the classification of the parking slot with the localization of marking points so that various parking slots can be directly inferred using geometric cues. In the occupancy classification stage, we design a customized network whose size of convolution kernel and number of layers are adjusted according to the characteristics of the parking slot. Experiments show that VPS-Net can detect various vacant parking slots with a precision rate of 99.63% and a recall rate of 99.31% in the ps2.0 dataset, and has a satisfying generalizability in the PSV dataset. By introducing a multi-object detection network and a classification network, VPS-Net can detect various vacant parking slots robustly. |
| first_indexed | 2024-03-10T20:33:02Z |
| format | Article |
| id | doaj.art-80c2e6e098e94127bb0a75c5740c5c95 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:33:02Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-80c2e6e098e94127bb0a75c5740c5c952023-11-19T21:15:26ZengMDPI AGSensors1424-82202020-04-01207213810.3390/s20072138Vacant Parking Slot Detection in the Around View Image Based on Deep LearningWei Li0Libo Cao1Lingbo Yan2Chaohui Li3Xiexing Feng4Peijie Zhao5State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha 410006, ChinaState Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha 410006, ChinaState Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha 410006, ChinaState Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha 410006, ChinaState Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha 410006, ChinaGAC Parts Corporation Limited, Guangzhou 510630, ChinaDue to the complex visual environment, such as lighting variations, shadows, and limitations of vision, the accuracy of vacant parking slot detection for the park assist system (PAS) with a standalone around view monitor (AVM) needs to be improved. To address this problem, we propose a vacant parking slot detection method based on deep learning, namely VPS-Net. VPS-Net converts the vacant parking slot detection into a two-step problem, including parking slot detection and occupancy classification. In the parking slot detection stage, we propose a parking slot detection method based on YOLOv3, which combines the classification of the parking slot with the localization of marking points so that various parking slots can be directly inferred using geometric cues. In the occupancy classification stage, we design a customized network whose size of convolution kernel and number of layers are adjusted according to the characteristics of the parking slot. Experiments show that VPS-Net can detect various vacant parking slots with a precision rate of 99.63% and a recall rate of 99.31% in the ps2.0 dataset, and has a satisfying generalizability in the PSV dataset. By introducing a multi-object detection network and a classification network, VPS-Net can detect various vacant parking slots robustly.https://www.mdpi.com/1424-8220/20/7/2138park assist systemvacant parking slot detectiondeep learningaround view image |
| spellingShingle | Wei Li Libo Cao Lingbo Yan Chaohui Li Xiexing Feng Peijie Zhao Vacant Parking Slot Detection in the Around View Image Based on Deep Learning Sensors park assist system vacant parking slot detection deep learning around view image |
| title | Vacant Parking Slot Detection in the Around View Image Based on Deep Learning |
| title_full | Vacant Parking Slot Detection in the Around View Image Based on Deep Learning |
| title_fullStr | Vacant Parking Slot Detection in the Around View Image Based on Deep Learning |
| title_full_unstemmed | Vacant Parking Slot Detection in the Around View Image Based on Deep Learning |
| title_short | Vacant Parking Slot Detection in the Around View Image Based on Deep Learning |
| title_sort | vacant parking slot detection in the around view image based on deep learning |
| topic | park assist system vacant parking slot detection deep learning around view image |
| url | https://www.mdpi.com/1424-8220/20/7/2138 |
| work_keys_str_mv | AT weili vacantparkingslotdetectioninthearoundviewimagebasedondeeplearning AT libocao vacantparkingslotdetectioninthearoundviewimagebasedondeeplearning AT lingboyan vacantparkingslotdetectioninthearoundviewimagebasedondeeplearning AT chaohuili vacantparkingslotdetectioninthearoundviewimagebasedondeeplearning AT xiexingfeng vacantparkingslotdetectioninthearoundviewimagebasedondeeplearning AT peijiezhao vacantparkingslotdetectioninthearoundviewimagebasedondeeplearning |