Classification of human activity on water through micro-Dopplers using deep convolutional neural networks

Content Provider	Semantic Scholar
Author	Kim, Youngwook Moonb, Taesup
Copyright Year	2016
Abstract	Detecting humans and classifying their activities on the water has significant applications for surveillance, border patrols, and rescue operations. When humans are illuminated by radar signal, they produce micro-Doppler signatures due to moving limbs. There has been a number of research into recognizing humans on land by their unique micro-Doppler signatures, but there is scant research into detecting humans on water. In this study, we investigate the micro-Doppler signatures of humans on water, including a swimming person, a swimming person pulling a floating object, and a rowing person in a small boat. The measured swimming styles were free stroke, backstroke, and breaststroke. Each activity was observed to have a unique micro-Doppler signature. Human activities were classified based on their micro-Doppler signatures. For the classification, we propose to apply deep convolutional neural networks (DCNN), a powerful deep learning technique. Rather than using conventional supervised learning that relies on handcrafted features, we present an alternative deep learning approach. We apply the DCNN, one of the most successful deep learning algorithms for image recognition, directly to a raw micro-Doppler spectrogram of humans on the water. Without extracting any explicit features from the micro-Dopplers, the DCNN can learn the necessary features and build classification boundaries using the training data. We show that the DCNN can achieve accuracy of more than 87.8% for activity classification using 5fold cross validation.
File Format	PDF HTM / HTML
Alternate Webpage(s)	http://mind.dgist.ac.kr/files/Conference/SPIE2016.pdf
Language	English
Access Restriction	Open
Subject Keyword	Algorithm Antivirus software Artificial neural network Cerebrovascular accident Classification Computer vision Convolution Convolutional neural network Cross Reactions Cross-validation (statistics) Deep learning Electronic signature Greater Than HL7PublishingSubSection Human Activities Imagery Limb structure Machine learning Pulse-Doppler radar Radar Sensor Spectrogram Supervised learning Type signature
Content Type	Text
Resource Type	Article