ABSTRACT
The paper proposes a novel Euclidean distance softmax layer for radar-based human activity classification. The method aims to overcome the angular dependency of classical softmax approaches. Through the freedoms thus gained, the activity classes can be distributed freely within the entire embedded feature space, due to which the dimension of the embeddings and the whole neural network size can be reduced. The performance of our novel deep learning architecture is evaluated for 60 GHz mm-wave radar sensor-based human activity classification. The results show that the proposed approach increases the robustness against random and unknown movements compared to state-of-art representation learning techniques.
- Jiankang Deng, Jia Guo, Niannan Xue, and Stefanos Zafeiriou. 2019. Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4690--4699.Google ScholarCross Ref
- Vishal Garg and Narendra K Bansal. 2000. Smart occupancy sensors to reduce energy consumption. Energy and Buildings 32, 1 (2000), 81--87.Google ScholarCross Ref
- Souvik Hazra and Avik Santra. 2019. Short-Range Radar-Based Gesture Recognition System Using 3D CNN With Triplet Loss. IEEE Access 7 (2019), 125623--125633.Google ScholarCross Ref
- Lanqing He, Zhongdao Wang, Yongzeng Li, and Shengjin Wang. 2020. Softmax Dissection: Towards Understanding Intra- and Inter-clas Objective for Embedding Learning. ArXiv abs/1908.01281 (2020).Google Scholar
- Rodrigo Hernangómez, Avik Santra, and Slawomir Stańczak. 2019. Human Activity Classification with Frequency Modulated Continuous Wave Radar Using Deep Convolutional Neural Networks. In 2019 International Radar Conference (RADAR). IEEE, 1--6.Google Scholar
- Rios Jesus Javier and Youngwook Kim. 2014. Application of linear predictive coding for human activity classification based on micro-Doppler signatures. IEEE Geoscience and Remote Sensing Letters 11, 10 (2014), 1831--1834.Google ScholarCross Ref
- Youngwook Kim and Taesup Moon. 2015. Human detection and activity classification based on micro-Doppler signatures using deep convolutional neural networks. IEEE geoscience and remote sensing letters 13, 1 (2015), 8--12.Google Scholar
- Yier Lin, Julien Le Kernec, Shufan Yang, Francesco Fioranelli, Olivier Romain, and Zhiqin Zhao. 2018. Human activity classification with radar: Optimization and noise robustness with iterative convolutional neural networks followed with random forests. IEEE Sensors Journal 18, 23 (2018), 9669--9681.Google ScholarCross Ref
- Weiyang Liu, Yandong Wen, Zhiding Yu, Ming Li, Bhiksha Raj, and Le Song. 2017. SphereFace: Deep Hypersphere Embedding for Face Recognition. CoRR abs/1704.08063 (2017). arXiv:1704.08063 http://arxiv.org/abs/1704.08063Google Scholar
- Jacopo Pegoraro, Francesca Meneghello, and Michele Rossi. 2020. Multi-Person Continuous Tracking and Identification from mm-Wave micro-Doppler Signatures. arXiv: Signal Processing (2020).Google Scholar
- Avik Santra, Raghavendran Vagarappan Ulaganathan, and Thomas Finke. 2018. Short-range millimetric-wave radar system for occupancy sensing application. IEEE sensors letters 2, 3 (2018), 1--4.Google Scholar
- Florian Schroff, Dmitry Kalenichenko, and James Philbin. 2015. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition. 815--823.Google ScholarCross Ref
- Yaniv Taigman, Ming Yang, Marc'Aurelio Ranzato, and Lior Wolf. 2014. Deepface: Closing the gap to human-level performance in face verification. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1701--1708.Google ScholarDigital Library
- Prachi Vaishnav and Avik Santra. 2020. Continuous Human Activity Classification with Unscented Kalman Filter Tracking using FMCW radar. IEEE Sensors Letters (2020).Google ScholarCross Ref
- Feng Wang, Jian Cheng, Weiyang Liu, and Haijun Liu. 2018. Additive margin softmax for face verification. IEEE Signal Processing Letters 25, 7 (2018), 926--930.Google ScholarCross Ref
- Hao Wang, Yitong Wang, Zheng Zhou, Xing Ji, Zhifeng Li, Dihong Gong, Jingchao Zhou, and Wei Liu. 2018. CosFace: Large Margin Cosine Loss for Deep Face Recognition. CoRR abs/1801.09414 (2018). arXiv:1801.09414 http://arxiv.org/abs/1801.09414Google Scholar
- Jonas Weiß and Avik Santra. 2018. One-shot learning for robust material classification using millimeter-wave radar system. IEEE sensors letters 2, 4 (2018), 1--4.Google ScholarCross Ref
- Yandong Wen, Kaipeng Zhang, Zhifeng Li, and Yu Qiao. 2016. A discriminative feature learning approach for deep face recognition. In European conference on computer vision. Springer, 499--515.Google ScholarCross Ref
- Matthew Zenaldin and Ram M Narayanan. 2016. Radar micro-Doppler based human activity classification for indoor and outdoor environments. In Radar Sensor Technology XX, Vol. 9829. International Society for Optics and Photonics, 98291B.Google Scholar
Index Terms
- Human Activity Classification Using mm-Wave FMCW Radar by Improved Representation Learning
Recommendations
Human activity learning for assistive robotics using a classifier ensemble
Assistive robots in ambient assisted living environments can be equipped with learning capabilities to effectively learn and execute human activities. This paper proposes a human activity learning (HAL) system for application in assistive robotics. An ...
RMVS: Remote Monitoring of Vital Signs with mm-Wave Radar
MORSE '22: Proceedings of the 1st ACM Workshop on AI Empowered Mobile and Wireless SensingIndoor vital signs monitoring is beneficial for people's healthy life. However, the monitoring distance limits most existing mm-wave radar-based vital signs monitoring methods. Enhancing and analyzing the echo signal helps to improve the monitoring ...
Human Activity Classification Using On-Body Miniaturized Antennas
AbstractEM waves are extremely powerful when it comes to propagation of information during communication. There is no alternative to EM waves in such applications. However, the use of EM waves or antennas in general has not been explored fully as sensors ...
Comments