Pedestrian recognition using automotive radar sensors
作者： A. Bartsch , F. Fitzek , R. H. Rasshofer
关键词:
摘要: Abstract. The application of modern series production automotive radar sensors to pedestrian recognition is an important topic in research on future driver assistance systems. aim this paper understand the potential and limits such recognition. This knowledge could be used develop next generation with improved capabilities. A new raw data signal processing algorithm proposed that allows deep insights into object classification process. impact properties can directly observed every layer system by avoiding machine learning tracking. gives information limiting factors terms decision making. To accomplish very challenging distinction between pedestrians static objects, five significant stable features from spatial distribution Doppler are found. Experimental results a 77 GHz sensor show over 95% classified correctly under optimal conditions, which compareable pedestrian's direction movement, occlusion, antenna beam elevation angle, linear vehicle other investigated discussed. real life only based limited due insufficient frequency resolution as well side lobe effects.
adv-radio-sci.net
harvard.edu
core.ac.uk参考文章(12)
Zhaozhang Jin, Diego Benitez, A method for human only activity detection based on radar signals ,(2009)
C. Hornsteiner, J. Detlefsen, Characterisation of human gait using a continuous-wave radar at 24 GHz Advances in Radio Science. ,vol. 6, pp. 67- 70 ,(2008) , 10.5194/ARS-6-67-2008
N. Yamada, Y. Tanaka, K. Nishikawa, Radar cross section for pedestrian in 76GHz band european microwave conference. ,vol. 2, ,(2005) , 10.1109/EUMC.2005.1610101
Feng He, Xiaotao Huang, Chenglan Liu, Zhimin Zhou, Chongyi Fan, Modeling and simulation study on radar Doppler signatures of pedestrian ieee radar conference. pp. 1322- 1326 ,(2010) , 10.1109/RADAR.2010.5494414
Steffen Heuel, Henning Ritter, Pedestrian detection procedure integrated into an 24 GHz automotive radar ieee radar conference. pp. 1229- 1232 ,(2010) , 10.1109/RADAR.2010.5494432
G. Kouemou, F. Opitz, Impact of Wavelet based signal processing methods in radar classification systems using Hidden Markov Models international radar symposium. pp. 1- 4 ,(2008) , 10.1109/IRS.2008.4585763
Youngwook Kim, Hao Ling, Human activity classification based on micro-Doppler signatures using an artificial neural network ieee antennas and propagation society international symposium. pp. 1- 4 ,(2008) , 10.1109/APS.2008.4619933
Josef Wenger, Stefan Hahn, Long Range and Ultra-Wideband Short Range Automotive Radar international conference on ultra-wideband. pp. 518- 522 ,(2007) , 10.1109/ICUWB.2007.4381000
David Gerónimo, Antonio M López, Angel D Sappa, Thorsten Graf, Survey of Pedestrian Detection for Advanced Driver Assistance Systems IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 32, pp. 1239- 1258 ,(2010) , 10.1109/TPAMI.2009.122
J.A. Nanzer, R.L. Rogers, Bayesian Classification of Humans and Vehicles Using Micro-Doppler Signals From a Scanning-Beam Radar IEEE Microwave and Wireless Components Letters. ,vol. 19, pp. 338- 340 ,(2009) , 10.1109/LMWC.2009.2017620