Transformer-Based Parking Slot Detection Using Fixed Anchor Points
Transformer-based architectures have recently gained significant attention in various computer vision tasks. Their ability to capture non-local dependencies and intricate characteristics makes them a promising complement to CNNs. However, their application in parking slot detection tasks is still li...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10252025/ |
| _version_ | 1797668067539419136 |
|---|---|
| author | Quang Huy Bui Jae Kyu Suhr |
| author_facet | Quang Huy Bui Jae Kyu Suhr |
| author_sort | Quang Huy Bui |
| collection | DOAJ |
| description | Transformer-based architectures have recently gained significant attention in various computer vision tasks. Their ability to capture non-local dependencies and intricate characteristics makes them a promising complement to CNNs. However, their application in parking slot detection tasks is still limited. Thus, this paper proposes an appropriate way to apply transformer-based architectures to parking slot detection tasks. The proposed method adopts the Detection Transformer (DETR) architecture, which employs a standard transformer encoder-decoder framework. Since this approach requires a long training time, this paper suggests utilizing fixed anchor points to replace object queries in the original DETR architecture. Each anchor point is assigned a known location and focuses only on a predefined area of the feature map, resulting in a considerable reduction in training time. In addition, this paper suggests using a more suitable and efficient two-point parking slot representation to improve detection performance. In experiments, the proposed method was evaluated with the public large-scale SNU dataset and showed comparable detection performance to the state-of-the-art CNN-based methods with 96.11% recall and 96.61% precision. |
| first_indexed | 2024-03-11T20:22:42Z |
| format | Article |
| id | doaj.art-cee01d6ab73d4ddeb37c5d68a9ccda2a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T20:22:42Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-cee01d6ab73d4ddeb37c5d68a9ccda2a2023-10-02T23:01:41ZengIEEEIEEE Access2169-35362023-01-011110441710442710.1109/ACCESS.2023.331573810252025Transformer-Based Parking Slot Detection Using Fixed Anchor PointsQuang Huy Bui0https://orcid.org/0000-0002-2639-682XJae Kyu Suhr1https://orcid.org/0000-0003-4844-851XSchool of Intelligent Mechatronics Engineering, Sejong University, Seoul, South KoreaSchool of Intelligent Mechatronics Engineering, Sejong University, Seoul, South KoreaTransformer-based architectures have recently gained significant attention in various computer vision tasks. Their ability to capture non-local dependencies and intricate characteristics makes them a promising complement to CNNs. However, their application in parking slot detection tasks is still limited. Thus, this paper proposes an appropriate way to apply transformer-based architectures to parking slot detection tasks. The proposed method adopts the Detection Transformer (DETR) architecture, which employs a standard transformer encoder-decoder framework. Since this approach requires a long training time, this paper suggests utilizing fixed anchor points to replace object queries in the original DETR architecture. Each anchor point is assigned a known location and focuses only on a predefined area of the feature map, resulting in a considerable reduction in training time. In addition, this paper suggests using a more suitable and efficient two-point parking slot representation to improve detection performance. In experiments, the proposed method was evaluated with the public large-scale SNU dataset and showed comparable detection performance to the state-of-the-art CNN-based methods with 96.11% recall and 96.61% precision.https://ieeexplore.ieee.org/document/10252025/Automatic parking systemparking slot detectiondeep learningtransformersconvolutional neural network (CNN)around view monitor (AVM) |
| spellingShingle | Quang Huy Bui Jae Kyu Suhr Transformer-Based Parking Slot Detection Using Fixed Anchor Points IEEE Access Automatic parking system parking slot detection deep learning transformers convolutional neural network (CNN) around view monitor (AVM) |
| title | Transformer-Based Parking Slot Detection Using Fixed Anchor Points |
| title_full | Transformer-Based Parking Slot Detection Using Fixed Anchor Points |
| title_fullStr | Transformer-Based Parking Slot Detection Using Fixed Anchor Points |
| title_full_unstemmed | Transformer-Based Parking Slot Detection Using Fixed Anchor Points |
| title_short | Transformer-Based Parking Slot Detection Using Fixed Anchor Points |
| title_sort | transformer based parking slot detection using fixed anchor points |
| topic | Automatic parking system parking slot detection deep learning transformers convolutional neural network (CNN) around view monitor (AVM) |
| url | https://ieeexplore.ieee.org/document/10252025/ |
| work_keys_str_mv | AT quanghuybui transformerbasedparkingslotdetectionusingfixedanchorpoints AT jaekyusuhr transformerbasedparkingslotdetectionusingfixedanchorpoints |