oTTC: Object Time-to-Contact for Motion Estimation in Autonomous Driving
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917664309379072 |
|---|---|
| author | Khan, Abdul Hannan Rizvi, Syed Tahseen Raza Macharavtu, Dheeraj Varma Chittari Dengel, Andreas |
| author_facet | Khan, Abdul Hannan Rizvi, Syed Tahseen Raza Macharavtu, Dheeraj Varma Chittari Dengel, Andreas |
| contents | Autonomous driving systems require a quick and robust perception of the nearby environment to carry out their routines effectively. With the aim to avoid collisions and drive safely, autonomous driving systems rely heavily on object detection. However, 2D object detections alone are insufficient; more information, such as relative velocity and distance, is required for safer planning. Monocular 3D object detectors try to solve this problem by directly predicting 3D bounding boxes and object velocities given a camera image. Recent research estimates time-to-contact in a per-pixel manner and suggests that it is more effective measure than velocity and depth combined. However, per-pixel time-to-contact requires object detection to serve its purpose effectively and hence increases overall computational requirements as two different models need to run. To address this issue, we propose per-object time-to-contact estimation by extending object detection models to additionally predict the time-to-contact attribute for each object. We compare our proposed approach with existing time-to-contact methods and provide benchmarking results on well-known datasets. Our proposed approach achieves higher precision compared to prior art while using a single image. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_07698 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | oTTC: Object Time-to-Contact for Motion Estimation in Autonomous Driving Khan, Abdul Hannan Rizvi, Syed Tahseen Raza Macharavtu, Dheeraj Varma Chittari Dengel, Andreas Computer Vision and Pattern Recognition Autonomous driving systems require a quick and robust perception of the nearby environment to carry out their routines effectively. With the aim to avoid collisions and drive safely, autonomous driving systems rely heavily on object detection. However, 2D object detections alone are insufficient; more information, such as relative velocity and distance, is required for safer planning. Monocular 3D object detectors try to solve this problem by directly predicting 3D bounding boxes and object velocities given a camera image. Recent research estimates time-to-contact in a per-pixel manner and suggests that it is more effective measure than velocity and depth combined. However, per-pixel time-to-contact requires object detection to serve its purpose effectively and hence increases overall computational requirements as two different models need to run. To address this issue, we propose per-object time-to-contact estimation by extending object detection models to additionally predict the time-to-contact attribute for each object. We compare our proposed approach with existing time-to-contact methods and provide benchmarking results on well-known datasets. Our proposed approach achieves higher precision compared to prior art while using a single image. |
| title | oTTC: Object Time-to-Contact for Motion Estimation in Autonomous Driving |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.07698 |