Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2408.12575 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916415572803584 |
|---|---|
| author | Musabini, Antonyo Novikov, Ivan Soula, Sana Leonet, Christel Wang, Lihao Benmokhtar, Rachid Burger, Fabian Boulay, Thomas Perrotton, Xavier |
| author_facet | Musabini, Antonyo Novikov, Ivan Soula, Sana Leonet, Christel Wang, Lihao Benmokhtar, Rachid Burger, Fabian Boulay, Thomas Perrotton, Xavier |
| contents | Current parking area perception algorithms primarily focus on detecting vacant slots within a limited range, relying on error-prone homographic projection for both labeling and inference. However, recent advancements in Advanced Driver Assistance System (ADAS) require interaction with end-users through comprehensive and intelligent Human-Machine Interfaces (HMIs). These interfaces should present a complete perception of the parking area going from distinguishing vacant slots' entry lines to the orientation of other parked vehicles. This paper introduces Multi-Task Fisheye Cross View Transformers (MT F-CVT), which leverages features from a four-camera fisheye Surround-view Camera System (SVCS) with multihead attentions to create a detailed Bird-Eye View (BEV) grid feature map. Features are processed by both a segmentation decoder and a Polygon-Yolo based object detection decoder for parking slots and vehicles. Trained on data labeled using LiDAR, MT F-CVT positions objects within a 25m x 25m real open-road scenes with an average error of only 20 cm. Our larger model achieves an F-1 score of 0.89. Moreover the smaller model operates at 16 fps on an Nvidia Jetson Orin embedded board, with similar detection results to the larger one. MT F-CVT demonstrates robust generalization capability across different vehicles and camera rig configurations. A demo video from an unseen vehicle and camera rig is available at: https://streamable.com/jjw54x. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12575 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhanced Parking Perception by Multi-Task Fisheye Cross-view Transformers Musabini, Antonyo Novikov, Ivan Soula, Sana Leonet, Christel Wang, Lihao Benmokhtar, Rachid Burger, Fabian Boulay, Thomas Perrotton, Xavier Computer Vision and Pattern Recognition Artificial Intelligence Current parking area perception algorithms primarily focus on detecting vacant slots within a limited range, relying on error-prone homographic projection for both labeling and inference. However, recent advancements in Advanced Driver Assistance System (ADAS) require interaction with end-users through comprehensive and intelligent Human-Machine Interfaces (HMIs). These interfaces should present a complete perception of the parking area going from distinguishing vacant slots' entry lines to the orientation of other parked vehicles. This paper introduces Multi-Task Fisheye Cross View Transformers (MT F-CVT), which leverages features from a four-camera fisheye Surround-view Camera System (SVCS) with multihead attentions to create a detailed Bird-Eye View (BEV) grid feature map. Features are processed by both a segmentation decoder and a Polygon-Yolo based object detection decoder for parking slots and vehicles. Trained on data labeled using LiDAR, MT F-CVT positions objects within a 25m x 25m real open-road scenes with an average error of only 20 cm. Our larger model achieves an F-1 score of 0.89. Moreover the smaller model operates at 16 fps on an Nvidia Jetson Orin embedded board, with similar detection results to the larger one. MT F-CVT demonstrates robust generalization capability across different vehicles and camera rig configurations. A demo video from an unseen vehicle and camera rig is available at: https://streamable.com/jjw54x. |
| title | Enhanced Parking Perception by Multi-Task Fisheye Cross-view Transformers |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2408.12575 |