Human Detection and Activity Classification Based on Micro-Doppler Signatures Using Deep Convolutional Neural Networks

By Youngwook Kim, Taesup Moon. IEEE Geoscience and Remote Sensing Letters, 2016

552 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Biomedical Engineering

View Paper: https://www.semanticscholar.org/paper/fd72b200146da5b0cf5de329b155ff48fa4e6f14

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. S. Gürbüz
2. Brian Toomajian
3. Moeness G. Amin
4. A. Ozbayoglu
5. Mehmet Saygin Seyfioglu
6. Jun Liu
7. Qiuhong Ke
8. Hossein Rahmani

In Biomedical Engineering

1. Jun Liu
2. Qiuhong Ke
3. Hossein Rahmani
4. Zehua Sun
5. Brian Toomajian
6. S. Gürbüz
7. Moeness G. Amin
8. A. Ozbayoglu

Citations in the corpus

• Deep convolutional neural networks for detection of rail surface defects (2016, background): “Some examples of activation functions are the hyperbolic tangent function (Tanh), the sigmoid function, and rectified linear units (ReLU) [24].”
• Hand Gesture Recognition Using Micro-Doppler Signatures With Convolutional Neural Network (2016, methodology): “Consequently, we employed DCNNs to classify our hand gestures.”
• Deep convolutional autoencoder for radar-based classification of similar aided and unaided human activities (2018, background): “In one of the first works on radar micro-Doppler classification with deep learning in 2016, Kim and Moon [18] utilized a convolutional neural network (CNN) with 3 convolutional layers and 20 filters to classify 7 different activities: running, walking, walking while holding a stick, crawling, boxing”
• Human Action Recognition From Various Data Modalities: A Review (2020, background): “Hence numerous works [7], [8], [9], [10], [11], [12], [13], [14], [15], [16] exploited various modalities for HAR.”
• A survey of deep neural network architectures and their applications (2017, background): “It sh ould be noted that promising results have been achieved by CNNs in areas like human detection and Doppler radar based ctivity classification [85].”
• Radar-Based Human-Motion Recognition With Deep Learning: Promising applications for indoor monitoring (2019, methodology): “For example, in a seven-class problem of visually identifiable signatures, a support vector machine (SVM) classifier yielded roughly the same performance as that of a convolutional neural network (CNN) [3].”