Radar-based Feature Design and Multiclass Classification for Road User Recognition

The classification of individual traffic participants is a complex task, especially for challenging scenarios with multiple road users or under bad weather conditions. Radar sensors provide an – with respect to well established camera systems – orthogonal way of measuring such scenes. In order to gain accurate classification results, 50 different features are extracted from the measurement data and tested on their performance. From these features a suitable subset is chosen and passed to random forest and long short-term memory (LSTM) classifiers to obtain class predictions for the radar input. Moreover, it is shown why data imbalance is an inherent problem in automotive radar classification when the dataset is not sufficiently large. To overcome this issue, classifier binarization is used among other techniques in order to better account for underrepresented classes. A new method to couple the resulting probabilities is proposed and compared to others with great success. Final results show substantial improvements when compared to ordinary multiclass classification.

[1]  Mikel Galar,et al.  Analysing the classification of imbalanced data-sets with multiple classes: Binarization techniques and ad-hoc approaches , 2013, Knowl. Based Syst..

[2]  Jürgen Dickmann,et al.  Comparison of random forest and long short-term memory network performances in classification tasks using radar , 2017, 2017 Sensor Data Fusion: Trends, Solutions, Applications (SDF).

[3]  T. Zwick,et al.  Millimeter-Wave Technology for Automotive Radar Sensors in the 77 GHz Frequency Band , 2012, IEEE Transactions on Microwave Theory and Techniques.

[4]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[5]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[6]  Pavlo Molchanov,et al.  Radar Target Classification by Micro-Doppler Contributions , 2014 .

[7]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[8]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Markus Hahn,et al.  Detection of arbitrarily rotated parked cars based on radar sensors , 2015, 2015 16th International Radar Symposium (IRS).

[11]  Ralph Helmar Rasshofer,et al.  Pedestrian recognition using automotive radar sensors , 2012 .

[12]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[13]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[14]  Bernhard Schlegel,et al.  Dealing with Class Imbalance the Scalable Way: Evaluation of Various Techniques Based on Classification Grade and Computational Complexity , 2017, 2017 IEEE International Conference on Data Mining Workshops (ICDMW).

[15]  Eddy Mayoraz,et al.  Improved Pairwise Coupling Classification with Correcting Classifiers , 1998, ECML.

[16]  Hermann Rohling,et al.  Two-stage pedestrian classification in automotive radar systems , 2011, 2011 12th International Radar Symposium (IRS).

[17]  Wolfgang Menzel,et al.  High resolution automotive radar measurements of vulnerable road users – pedestrians & cyclists , 2015, 2015 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM).

[18]  Hermann Rohling,et al.  Pedestrian recognition based on 24 GHz radar sensors , 2010, 11-th INTERNATIONAL RADAR SYMPOSIUM.

[19]  Jürgen Dickmann,et al.  Object classification in radar using ensemble methods , 2017, 2017 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM).

[20]  Katarzyna Stapor,et al.  Combining One-Versus-One and One-Versus-All Strategies to Improve Multiclass SVM Classifier , 2015, CORES.