Probabilistic Lane Estimation using Basis Curves
Lane estimation for autonomous driving can be formulated as a curve estimation problem, where local sensor data provides partial and noisy observations of spatial curves. The number of curves to estimate may be initially unknown and many of the observations may be outliers or false detections (...
| Главные авторы: | , |
|---|---|
| Другие авторы: | |
| Формат: | Статья |
| Язык: | en_US |
| Опубликовано: |
Robotics: Science and Systems (RSS)
2011
|
| Online-ссылка: | http://hdl.handle.net/1721.1/62303 |
| _version_ | 1826202564960452608 |
|---|---|
| author | Huang, Albert S. Teller, Seth |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Huang, Albert S. Teller, Seth |
| author_sort | Huang, Albert S. |
| collection | MIT |
| description | Lane estimation for autonomous driving can be
formulated as a curve estimation problem, where local sensor
data provides partial and noisy observations of spatial curves.
The number of curves to estimate may be initially unknown and
many of the observations may be outliers or false detections
(due e.g. to to tree shadows or lens flare). The challenges lie in
detecting lanes when and where they exist, and updating lane
estimates as new observations are made.
This paper describes an efficient probabilistic lane estimation
algorithm based on a novel curve representation. The key
advance is a principled mechanism to describe many similar
curves as variations of a single basis curve. Locally observed road
paint and curb features are then fused to detect and estimate
all nearby travel lanes. The system handles roads with complex
geometries and makes no assumptions about the position and
orientation of the vehicle with respect to the roadway.
We evaluate our algorithm with a ground truth dataset
containing manually-labeled, fine-grained lane geometries for
vehicle travel in two large and diverse datasets that include more
than 300,000 images and 44km of roadway. The results illustrate
the capabilities of our algorithm for robust lane estimation in the
face of challenging conditions and unknown roadways. |
| first_indexed | 2024-09-23T12:09:32Z |
| format | Article |
| id | mit-1721.1/62303 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:09:32Z |
| publishDate | 2011 |
| publisher | Robotics: Science and Systems (RSS) |
| record_format | dspace |
| spelling | mit-1721.1/623032022-10-01T08:33:23Z Probabilistic Lane Estimation using Basis Curves Huang, Albert S. Teller, Seth Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Teller, Seth Huang, Albert S. Teller, Seth Lane estimation for autonomous driving can be formulated as a curve estimation problem, where local sensor data provides partial and noisy observations of spatial curves. The number of curves to estimate may be initially unknown and many of the observations may be outliers or false detections (due e.g. to to tree shadows or lens flare). The challenges lie in detecting lanes when and where they exist, and updating lane estimates as new observations are made. This paper describes an efficient probabilistic lane estimation algorithm based on a novel curve representation. The key advance is a principled mechanism to describe many similar curves as variations of a single basis curve. Locally observed road paint and curb features are then fused to detect and estimate all nearby travel lanes. The system handles roads with complex geometries and makes no assumptions about the position and orientation of the vehicle with respect to the roadway. We evaluate our algorithm with a ground truth dataset containing manually-labeled, fine-grained lane geometries for vehicle travel in two large and diverse datasets that include more than 300,000 images and 44km of roadway. The results illustrate the capabilities of our algorithm for robust lane estimation in the face of challenging conditions and unknown roadways. 2011-04-22T19:15:38Z 2011-04-22T19:15:38Z 2010-06 Article http://purl.org/eprint/type/ConferencePaper 9780262516815 0262516810 http://hdl.handle.net/1721.1/62303 Huang, Albert S., Seth Teller. "Probabilistic Lane Estimation using Basis Curves" Robotics: Science and Systems (6th : 2010 : Zaragoza, Spain). en_US http://www.roboticsproceedings.org/rss06/p04.pdf Robotics: Science and Systems (RSS). Proceedings Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Robotics: Science and Systems (RSS) MIT web domain |
| spellingShingle | Huang, Albert S. Teller, Seth Probabilistic Lane Estimation using Basis Curves |
| title | Probabilistic Lane Estimation using Basis Curves |
| title_full | Probabilistic Lane Estimation using Basis Curves |
| title_fullStr | Probabilistic Lane Estimation using Basis Curves |
| title_full_unstemmed | Probabilistic Lane Estimation using Basis Curves |
| title_short | Probabilistic Lane Estimation using Basis Curves |
| title_sort | probabilistic lane estimation using basis curves |
| url | http://hdl.handle.net/1721.1/62303 |
| work_keys_str_mv | AT huangalberts probabilisticlaneestimationusingbasiscurves AT tellerseth probabilisticlaneestimationusingbasiscurves |