Title :
Interacting multiple model road curvature estimation
Author :
Shen, Truman ; Ibrahim, Faroog
Author_Institution :
Takata Holdings Inc., Japan
Abstract :
Accurate road curvature estimation is essential to many drive assistance systems and active safety systems, such as curve speed warning, lane departure warning, and lane keeping assistance. To improve the overall performance of road curvature estimation and path prediction, we proposed an interacting multiple model (structure) approach in curvature filtering, so that the curvature estimates for straight road and pure arc can be more accurate while the transitional curvature change between straight and constant radius curve can still be accounted for.
Keywords :
computer vision; driver information systems; road safety; active safety systems; curvature filtering; curve speed warning; drive assistance systems; interacting multiple model road curvature estimation; lane departure warning; lane keeping assistance; path prediction; radius curve; transitional curvature; Accuracy; Data models; Estimation; Filtering; Mathematical model; Noise; Roads;
Conference_Titel :
Intelligent Transportation Systems (ITSC), 2012 15th International IEEE Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
978-1-4673-3064-0
Electronic_ISBN :
2153-0009
DOI :
10.1109/ITSC.2012.6338884