Target Classification Using Frontal Images Measured by 77 GHz FMCW Radar through DCNN
Source abstract
Abstract
This paper proposes a target classification method using radar frontal imaging measured by millimeter-wave multiple-input multiple-output (MW-MIMO) radar through deep convolutional neural networks. Autonomous vehicles must classify targets in front of the vehicle to attain better situational awareness. We use 2D sparse array radar to capture the frontal images of objects on the road, such as sedans, vans, trucks, humans, poles, and trees. The frontal image includes information regarding not only the shape of a target but also the reflection characteristics of each part of the target. The measured frontal images are classified by deep convolutional neural networks, and the classification rate yielded 87.1% for six classes and 92.6% for three classes.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced SAR Imaging Techniques · Radar Systems and Signal Processing · Microwave Imaging and Scattering Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical and Computer Engineering, California State University, Fresno, CA 93740, USA
Electronics and Telecommunications Research Institute (ETRI), Daejeon 34129, Korea
Department of Electronic Engineering, Sogang University, Seoul 04107, Korea
Funding
Electronics and Telecommunications Research Institute (ETRI) · National Research Foundation (NRF), Korea
References (20)
Show source-provided references
1. Millimeter-wave technology for automotive radar sensors in the 77 GHz frequency band10.1109/TMTT.2011.2178427 ↗
2. Fan, Y., Xiang, K., An, J., and Bu, X. (2013, January 14–16). A new method of multi-target detection for FMCW automotive radar. Proceedings of the IET International Radar Conference 2013, Xi’an, China.
3. Liu, J., and Xu, Q. (2021). Radar target classification based on high resolution range profile segmentation and ensemble classification. IEEE Sens. Lett., 5.10.1109/LSENS.2021.3066596 ↗
4. Wit, J., Dorp, P., and Huizing, A. (2016, January 5–7). Classification of air targets based on range-Doppler diagrams. Proceedings of the European Radar Conference (EuRAD), London, UK.
5. Ng, W., Wang, G., Lin, Z., and Dutta, B. (2020, January 19–24). Range-Doppler detection in automotive radar with deep learning. In Proceedings of the International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.10.1109/IJCNN48605.2020.9207080 ↗
6. Learning approach to FMCW radar target classification with feature extraction from wave physics10.1109/TAP.2022.3175716 ↗
7. Human detection based on time-varying signature on range-Doppler diagram using deep neural networks10.1109/LGRS.2020.2980320 ↗
8. Padar, M., Ertan, A., and Candan, C. (2016, January 2–6). Classification of human motion using radar micro-Doppler signatures with hidden Markov models. Proceedings of the 2016 IEEE Radar Conference (RadarConf), Philadelphia, PA, USA.10.1109/RADAR.2016.7485201 ↗
9. Jokanovic, B., Amin, M., and Ahmad, F. (2016, January 2–6). Radar fall motion detection using deep learning. Proceedings of the 2016 IEEE Radar Conference (RadarConf), Philadelphia, PA, USA.10.1109/RADAR.2016.7485147 ↗
10. Human gait recognition with cane assistive device using quadratic time–frequency distributions10.1049/iet-rsn.2015.0119 ↗
11. Feng, Z., Zhang, S., Kunert, M., and Wiesbeck, W. (2019, January 12–13). Point cloud segmentation with a high-resolution automotive radar. Proceedings of the AmE 2019—Automotive meets Electronics; 10th GMM-Symposium, Dortmund, Germany.
12. Sengupta, A., Cao, S., and Wu, Y. (2020, January 28–30). MmWave radar point cloud segmentation using GMM in multimodal traffic monitoring. Proceedings of the International Radar Conference (RADAR), Florence, Italy.
13. Frontal imaging of human using three-element Doppler and direction-of-arrival radar10.1049/el:20060355 ↗
14. Sparse direction of arrival estimation using co-prime arrays with off-grid targets10.1109/LSP.2013.2289740 ↗
15. Three-dimensional imaging via wideband MIMO radar system10.1109/LGRS.2009.2038728 ↗
16. Chen, Z., and Gokeda, G. (2010). Introduction to Direction-of-Arrival Estimation, Artech House.
17. Human detection and activity classification based on micro-Dopplers using deep convolutional neural networks10.1109/LGRS.2015.2491329 ↗
18. Deep convolutional autoencoder for radar-based classification of similar aided and unaided human activities10.1109/TAES.2018.2799758 ↗
19. Patel, K., Rambach, K., Visentin, T., Rusev, D., Pfeiffer, M., and Yang, B. (2019, January 22–26). Deep Learning-based Object Classification on Automotive Radar Spectra. Proceedings of the 2019 IEEE Radar Conference (RadarConf), Boston, MA, USA.10.1109/RADAR.2019.8835775 ↗
20. Neumann, C., and Brosch, T. (2020, January 5–8). Deep learning approach for radar applications. Proceedings of the 2020 21st International Radar Symposium (IRS), Warsaw, Poland.10.23919/IRS48640.2020.9253868 ↗