Human Detection Based on Time-Varying Signature on Range-Doppler Diagram Using Deep Neural Networks

Kim, Youngwook; Alnujaim, Ibrahim; You, Sungjin; Jeong, Byung Jang

doi:10.1109/lgrs.2020.2980320

Cited by 29 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This sequence is time-dependent and can be formalized as a 4D tensor X ∈ N N R ×N D ×C×T , where T represents the number of RD maps in the sequence. The aim of collecting T RD maps is to increase the classification accuracy concerning a single RD maps classifier as shown in [31]. The proposed DNN consists of a CNN that extracts automatically the features from each RD map employing a time-distributed layer (TDL).…”

Section: B Classification Stagementioning

confidence: 99%

“…Many papers in the literature address the moving target recognition through FMCW radars [9], [10], [25]- [28] supporting machine learning (ML) algorithms, such as support vector machines (SVMs) or Deep Neural Networks (DNNs) [26], [29], [30]. The use of DNNs in FMCW radar target classification has also been reported in [31]- [34].…”

Section: Introductionmentioning

confidence: 99%

“…Some examples of the use of RNNs in radar applications have been presented in the literature. RNNs were adopted by authors in [31], [47]- [49], for human recognition and target classification in radar security applications. In addition, synthetic aperture radar (SAR) applications are an interesting field of study to use RNNs, as presented by the authors in [50]- [52].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On the Edge Recurrent Neural Network Approach for Ground Moving FMCW Radar Target Classification

Gianoglio,

Rizik,

Tavanti

et al. 2024

IEEE Trans. Consumer Electron.

View full text Add to dashboard Cite

In this paper, an approach for ground-moving target classification with an FMCW radar is proposed. In particular, data are collected using a low-cost 24 GHz off-the-shelf FMCW radar, combined with an embedded Raspberry Pi device for data acquisition and processing. An FFT-based processing scheme is then applied to obtain a sequence of range-Doppler maps, which are provided in input to different convolutional neural network (CNN) architectures for classifying the targets (cars, motorcycles, or pedestrians) eventually passing in front of the radar. Specifically, two approaches have been followed and compared. In the first one, single range-Doppler maps are processed alone using a convolutional neural network, and then a voting mechanism is applied to select the target classes. In the second approach, a sequence of range-Doppler maps is processed using a time-distributed layer feeding a recurrent neural network. The CNNs are deployed on the Raspberry Pi providing the target classification on a low-cost embedded device. The obtained results show that the proposed approaches allow for effectively detecting the different types of targets running on an embedded device in less than one second.

show abstract

Section: B Classification Stagementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On the Edge Recurrent Neural Network Approach for Ground Moving FMCW Radar Target Classification

Gianoglio,

Rizik,

Tavanti

et al. 2024

IEEE Trans. Consumer Electron.

View full text Add to dashboard Cite

show abstract

“…The raw Range-Doppler images were directly fed into a CNN, resulting in performance with 99% accuracy for distinguishing humans from robots. Many other applications that use neural networks for radar problems have been tackled in the literature [ 38 , 39 , 40 , 41 , 42 ].…”

Section: State Of the Artmentioning

confidence: 99%

A Convolutional Neural Network-Based Method for Discriminating Shadowed Targets in Frequency-Modulated Continuous-Wave Radar Systems

Mohanna

Gianoglio

Rizik

et al. 2022

Sensors

View full text Add to dashboard Cite

The radar shadow effect prevents reliable target discrimination when a target lies in the shadow region of another target. In this paper, we address this issue in the case of Frequency-Modulated Continuous-Wave (FMCW) radars, which are low-cost and small-sized devices with an increasing number of applications. We propose a novel method based on Convolutional Neural Networks that take as input the spectrograms obtained after a Short-Time Fourier Transform (STFT) analysis of the radar-received signal. The method discerns whether a target is or is not in the shadow region of another target. The proposed method achieves test accuracy of 92% with a standard deviation of 2.86%.

show abstract

“…These three objects are typical on-road scene [44,45]. Thus, its detection provide critical information for security and surveillance, law enforcement monitoring, search and rescue team [46,47].…”

Section: Plos Onementioning

confidence: 99%

Novel CE-CBCE feature extraction method for object classification using a low-density LiDAR point cloud

et al. 2021

View full text Add to dashboard Cite

Low-end LiDAR sensor provides an alternative for depth measurement and object recognition for lightweight devices. However due to low computing capacity, complicated algorithms are incompatible to be performed on the device, with sparse information further limits the feature available for extraction. Therefore, a classification method which could receive sparse input, while providing ample leverage for the classification process to accurately differentiate objects within limited computing capability is required. To achieve reliable feature extraction from a sparse LiDAR point cloud, this paper proposes a novel Clustered Extraction and Centroid Based Clustered Extraction Method (CE-CBCE) method for feature extraction followed by a convolutional neural network (CNN) object classifier. The integration of the CE-CBCE and CNN methods enable us to utilize lightweight actuated LiDAR input and provides low computing means of classification while maintaining accurate detection. Based on genuine LiDAR data, the final result shows reliable accuracy of 97% through the method proposed.

show abstract

Human Detection Based on Time-Varying Signature on Range-Doppler Diagram Using Deep Neural Networks

Cited by 29 publications

References 19 publications

On the Edge Recurrent Neural Network Approach for Ground Moving FMCW Radar Target Classification

On the Edge Recurrent Neural Network Approach for Ground Moving FMCW Radar Target Classification

A Convolutional Neural Network-Based Method for Discriminating Shadowed Targets in Frequency-Modulated Continuous-Wave Radar Systems

Novel CE-CBCE feature extraction method for object classification using a low-density LiDAR point cloud

Contact Info

Product

Resources

About