Real-time probabilistic fusion of sparse 3D LIDAR and dense stereo
Real-time 3D perception is critical for localisation, mapping, path planning and obstacle avoidance for mobile robots and autonomous vehicles. For outdoor operation in real-world environments, 3D perception is often provided by sparse 3D LIDAR scanners, which provide accurate but lowdensity depth ma...
Main Authors: | , |
---|---|
Format: | Conference item |
Published: |
Institute of Electrical and Electronics Engineers
2016
|
_version_ | 1797062174010507264 |
---|---|
author | Maddern, W Newman, P |
author_facet | Maddern, W Newman, P |
author_sort | Maddern, W |
collection | OXFORD |
description | Real-time 3D perception is critical for localisation, mapping, path planning and obstacle avoidance for mobile robots and autonomous vehicles. For outdoor operation in real-world environments, 3D perception is often provided by sparse 3D LIDAR scanners, which provide accurate but lowdensity depth maps, and dense stereo approaches, which require significant computational resources for accurate results. Here, taking advantage of the complementary error characteristics of LIDAR range sensing and dense stereo, we present a probabilistic method for fusing sparse 3D LIDAR data with stereo images to provide accurate dense depth maps and uncertainty estimates in real-time. We evaluate the method on data collected from a small urban autonomous vehicle and the KITTI dataset, providing accuracy results competitive with state-of-the-art stereo approaches and credible uncertainty estimates that do not misrepresent the true errors, and demonstrate real-time operation on a range of low-power GPU systems. |
first_indexed | 2024-03-06T20:41:48Z |
format | Conference item |
id | oxford-uuid:348adb53-1448-43c5-a5d9-7d7b7ef6c83c |
institution | University of Oxford |
last_indexed | 2024-03-06T20:41:48Z |
publishDate | 2016 |
publisher | Institute of Electrical and Electronics Engineers |
record_format | dspace |
spelling | oxford-uuid:348adb53-1448-43c5-a5d9-7d7b7ef6c83c2022-03-26T13:26:31ZReal-time probabilistic fusion of sparse 3D LIDAR and dense stereoConference itemhttp://purl.org/coar/resource_type/c_5794uuid:348adb53-1448-43c5-a5d9-7d7b7ef6c83cSymplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2016Maddern, WNewman, PReal-time 3D perception is critical for localisation, mapping, path planning and obstacle avoidance for mobile robots and autonomous vehicles. For outdoor operation in real-world environments, 3D perception is often provided by sparse 3D LIDAR scanners, which provide accurate but lowdensity depth maps, and dense stereo approaches, which require significant computational resources for accurate results. Here, taking advantage of the complementary error characteristics of LIDAR range sensing and dense stereo, we present a probabilistic method for fusing sparse 3D LIDAR data with stereo images to provide accurate dense depth maps and uncertainty estimates in real-time. We evaluate the method on data collected from a small urban autonomous vehicle and the KITTI dataset, providing accuracy results competitive with state-of-the-art stereo approaches and credible uncertainty estimates that do not misrepresent the true errors, and demonstrate real-time operation on a range of low-power GPU systems. |
spellingShingle | Maddern, W Newman, P Real-time probabilistic fusion of sparse 3D LIDAR and dense stereo |
title | Real-time probabilistic fusion of sparse 3D LIDAR and dense stereo |
title_full | Real-time probabilistic fusion of sparse 3D LIDAR and dense stereo |
title_fullStr | Real-time probabilistic fusion of sparse 3D LIDAR and dense stereo |
title_full_unstemmed | Real-time probabilistic fusion of sparse 3D LIDAR and dense stereo |
title_short | Real-time probabilistic fusion of sparse 3D LIDAR and dense stereo |
title_sort | real time probabilistic fusion of sparse 3d lidar and dense stereo |
work_keys_str_mv | AT maddernw realtimeprobabilisticfusionofsparse3dlidaranddensestereo AT newmanp realtimeprobabilisticfusionofsparse3dlidaranddensestereo |