Improved object classification of laserscanner measurements at intersections using precise high level maps
- 24 October 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21530009,p. 756-761
- https://doi.org/10.1109/itsc.2005.1520143
Abstract
This paper deals with real-time object classification at intersection scenarios. Objects are observed using a multilayer laserscanner. The classification is performed using well-known methods of statistical learning. The statistical classification is corrected by rule based a priori knowledge. Precise high level maps provide the possibility to additionally improve the classification by using infrastructure information and the position of the objects in the scene. Classification results of several neural networks and support vector machines are described. Finally, the improvement by high level maps and the final system performance are presented.Keywords
This publication has 7 references indexed in Scilit:
- New European approach for intersection safety - the EC-Project INTERSAFEPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Classification of laserscanner measurements at intersection scenarios with automatic parameter optimizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Feature-level map building and object recognition for intersection safety applicationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Feature-level fusion for free-form object tracking using laserscanner and videoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Precise ego-localization in urban areas using Laserscanner and high accuracy feature mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Neural Networks for Pattern RecognitionPublished by Oxford University Press (OUP) ,1995
- The Nature of Statistical Learning TheoryPublished by Springer Nature ,1995