Pedestrian classification in automotive radar systems
- 1 May 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Urban traffic is dangerous for all car drivers and especially for pedestrians. There are about 5000 fatalities on German streets every year, which is absolutely too much. Human beings have strong limitations in the ability to measure precisely the distance and the speed difference between cars, which is the reason for several accidents. Therefore, the European Union has called all car manufactureres to intensify their research activities in protecting vulnerable road users. An automotive radar sensor measures the target range and radial velocity very accurately and with high resolution even in multiple target situations and there is tremendous progress in 24 GHz radar sensor development. The objective of this paper is to protect vulnerable road users by a target recognition scheme in any urban scenario. One main objective is the difference between lateral moving vehicles and pedestrians in terms of feature extraction and classification. Therefore, a pedestrian detection procedure is additionally integrated into the 24 GHz automotive radar sensor.Keywords
This publication has 5 references indexed in Scilit:
- Statistical Pattern RecognitionPublished by Wiley ,2011
- Pedestrian detection procedure integrated into an 24 GHz automotive radarPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Top 10 algorithms in data miningKnowledge and Information Systems, 2007
- Comparison of machine learning and traditional classifiers in glaucoma diagnosisIEEE Transactions on Biomedical Engineering, 2002
- A training algorithm for optimal margin classifiersPublished by Association for Computing Machinery (ACM) ,1992