CARL-ODD: A Vision Benchmark Dataset of Asia for On-Road Vehicle Detection and Recognition - Figure 1
Fuente:
Zenodo
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Recurso digital |
| Publicado: |
Zenodo
2026
|
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866901584266395648 |
|---|---|
| author | Sarmad Shafique Samia Abid Faisal Riaz Bilal Ahmed Mubeen Javaid Khan Usama Younis Ameer Hamza |
| author_facet | Sarmad Shafique Samia Abid Faisal Riaz Bilal Ahmed Mubeen Javaid Khan Usama Younis Ameer Hamza |
| contents | <p dir="ltr">Currently, there is no public dataset available for object detection that encompasses Asia's local vehicles and pedestrians. Therefore, in this article,we present Asia's only stereo-vision dataset of different types of vehicles and pedestrians for use in autonomous driving research. Stereo vision helps to perceive objects based on the principle of the human eye, and it computes the depth based on the binocular disparity between the images of an object acquired from the left and suitable cameras attached to the front dashboard of our vehicle. The features of the images acquired at a time 't' are matched by examining the relative positions of objects in the visual scene. Our proposed methodology is illustrated in Figure 1. </p> <p> </p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_18709278 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | CARL-ODD: A Vision Benchmark Dataset of Asia for On-Road Vehicle Detection and Recognition - Figure 1 Sarmad Shafique Samia Abid Faisal Riaz Bilal Ahmed Mubeen Javaid Khan Usama Younis Ameer Hamza <p dir="ltr">Currently, there is no public dataset available for object detection that encompasses Asia's local vehicles and pedestrians. Therefore, in this article,we present Asia's only stereo-vision dataset of different types of vehicles and pedestrians for use in autonomous driving research. Stereo vision helps to perceive objects based on the principle of the human eye, and it computes the depth based on the binocular disparity between the images of an object acquired from the left and suitable cameras attached to the front dashboard of our vehicle. The features of the images acquired at a time 't' are matched by examining the relative positions of objects in the visual scene. Our proposed methodology is illustrated in Figure 1. </p> <p> </p> |
| title | CARL-ODD: A Vision Benchmark Dataset of Asia for On-Road Vehicle Detection and Recognition - Figure 1 |
| url | https://doi.org/10.5281/zenodo.18709278 |