Motion Classification and Height Estimation of Pedestrians Using Sparse Radar Data

A complete overview of the surrounding vehicle environment is important for driver assistance systems and highly autonomous driving. Fusing results of multiple sensor types like camera, radar and lidar is crucial for increasing the robustness. The detection and classification of objects like cars, bicycles or pedestrians has been analyzed in the past for many sensor types. Beyond that, it is also helpful to refine these classes and distinguish for example between different pedestrian types or activities. This task is usually performed on camera data, though recent developments are based on radar spectrograms. However, for most automotive radar systems, it is only possible to obtain radar targets instead of the original spectrograms. This work demonstrates that it is possible to estimate the body height of walking pedestrians using 2D radar targets. Furthermore, different pedestrian motion types are classified.

[1]  Changyin Sun,et al.  Supervised class-specific dictionary learning for sparse modeling in action recognition , 2012, Pattern Recognit..

[2]  Daniel Thalmann,et al.  A global human walking model with real-time kinematic personification , 1990, The Visual Computer.

[3]  F. Groen,et al.  Human walking estimation with radar , 2003 .

[4]  Youngwook Kim,et al.  Classification of human activity on water through micro-Dopplers using deep convolutional neural networks , 2016, SPIE Defense + Security.

[5]  V. Chen,et al.  Radar Micro-Doppler signatures : processing and applications , 2014 .

[6]  D. Rajan.  Probability, Random Variables, and Stochastic Processes , 2017 .

[7]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[8]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Andreas Eckner,et al.  Algorithms for Unevenly Spaced Time Series : Moving Averages and Other Rolling Operators , 2015 .

[10]  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).

[11]  Guillermo Sapiro,et al.  Online dictionary learning for sparse coding , 2009, ICML '09.

[12]  Youngwook Kim,et al.  Human Detection and Activity Classification Based on Micro-Doppler Signatures Using Deep Convolutional Neural Networks , 2016, IEEE Geoscience and Remote Sensing Letters.

[13]  Youngwook Kim,et al.  Human Activity Classification Based on Micro-Doppler Signatures Using a Support Vector Machine , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[15]  Jiajin Lei,et al.  Target classification based on micro-Doppler signatures , 2005, IEEE International Radar Conference, 2005..

[16]  F. Harris.  On the use of windows for harmonic analysis with the discrete Fourier transform , 1978, Proceedings of the IEEE.

[17]  Ram M. Narayanan,et al.  Radar micro-Doppler based human activity classification for indoor and outdoor environments , 2016, SPIE Defense + Security.

[18]  Julius Ziegler,et al.  Optimal trajectory generation for dynamic street scenarios in a Frenét Frame , 2010, 2010 IEEE International Conference on Robotics and Automation.

[19]  Hongwei Liu,et al.  Noise-Robust Classification of Ground Moving Targets Based on Time-Frequency Feature From Micro-Doppler Signature , 2014, IEEE Sensors Journal.

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