Distant vehicle detection using radar and vision
For autonomous vehicles to be able to operate successfully they need to be aware of other vehicles with sufficient time to make safe, stable plans. Given the possible closing speeds between two vehicles, this necessitates the ability to accurately detect distant vehicles. Many current image-based ob...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Published: |
Institute of Electrical and Electronics Engineers
2019
|
| _version_ | 1797052920993153024 |
|---|---|
| author | Chadwick, S Maddern, W Newman, P |
| author_facet | Chadwick, S Maddern, W Newman, P |
| author_sort | Chadwick, S |
| collection | OXFORD |
| description | For autonomous vehicles to be able to operate successfully they need to be aware of other vehicles with sufficient time to make safe, stable plans. Given the possible closing speeds between two vehicles, this necessitates the ability to accurately detect distant vehicles. Many current image-based object detectors using convolutional neural networks exhibit excellent performance on existing datasets such as KITTI. However, the performance of these networks falls when detecting small (distant) objects. We demonstrate that incorporating radar data can boost performance in these difficult situations. We also introduce an efficient automated method for training data generation using cameras of different focal lengths. |
| first_indexed | 2024-03-06T18:37:21Z |
| format | Conference item |
| id | oxford-uuid:0bb1a1d5-21ab-4bd3-9402-8a3c394bd236 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T18:37:21Z |
| publishDate | 2019 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:0bb1a1d5-21ab-4bd3-9402-8a3c394bd2362022-03-26T09:30:51ZDistant vehicle detection using radar and visionConference itemhttp://purl.org/coar/resource_type/c_5794uuid:0bb1a1d5-21ab-4bd3-9402-8a3c394bd236Symplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2019Chadwick, SMaddern, WNewman, PFor autonomous vehicles to be able to operate successfully they need to be aware of other vehicles with sufficient time to make safe, stable plans. Given the possible closing speeds between two vehicles, this necessitates the ability to accurately detect distant vehicles. Many current image-based object detectors using convolutional neural networks exhibit excellent performance on existing datasets such as KITTI. However, the performance of these networks falls when detecting small (distant) objects. We demonstrate that incorporating radar data can boost performance in these difficult situations. We also introduce an efficient automated method for training data generation using cameras of different focal lengths. |
| spellingShingle | Chadwick, S Maddern, W Newman, P Distant vehicle detection using radar and vision |
| title | Distant vehicle detection using radar and vision |
| title_full | Distant vehicle detection using radar and vision |
| title_fullStr | Distant vehicle detection using radar and vision |
| title_full_unstemmed | Distant vehicle detection using radar and vision |
| title_short | Distant vehicle detection using radar and vision |
| title_sort | distant vehicle detection using radar and vision |
| work_keys_str_mv | AT chadwicks distantvehicledetectionusingradarandvision AT maddernw distantvehicledetectionusingradarandvision AT newmanp distantvehicledetectionusingradarandvision |