Pedestrian and Animal Recognition Using Doppler Radar Signature and Deep Learning

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 9; p. 3456
• Main Authors: Buchman, Danny, Drozdov, Michail, Krilavičius, Tomas, Maskeliūnas, Rytis, Damaševičius, Robertas
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01-05-2022; MDPI
• Subjects: Accuracy; animal recognition; Animals; Artificial intelligence; Classification; Decomposition; Deep Learning; Doppler radar; Humans; Internet of Things; Machine learning; micro-Doppler signature; Neural networks; Neural Networks, Computer; pedestrian recognition; Pedestrians; Radar; Radar data; Radar signatures; Sensors; Surveillance; Test sets; Time-frequency analysis; Ultrasonography, Doppler; Unmanned aerial vehicles; deep learning; animal recognition; pedestrian recognition; doppler radar; micro-Doppler signature
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22093456

Pedestrian occurrences in images and videos must be accurately recognized in a number of applications that may improve the quality of human life. Radar can be used to identify pedestrians. When distinct portions of an object move in front of a radar, micro-Doppler signals are produced that may be utilized to identify the object. Using a deep-learning network and time-frequency analysis, we offer a method for classifying pedestrians and animals based on their micro-Doppler radar signature features. Based on these signatures, we employed a convolutional neural network (CNN) to recognize pedestrians and animals. The proposed approach was evaluated on the MAFAT Radar Challenge dataset. Encouraging results were obtained, with an AUC (Area Under Curve) value of 0.95 on the public test set and over 0.85 on the final (private) test set. The proposed DNN architecture, in contrast to more common shallow CNN architectures, is one of the first attempts to use such an approach in the domain of radar data. The use of the synthetic radar data, which greatly improved the final result, is the other novel aspect of our work.