Automatic Radar-based Gesture Detection and Classification via a Region-based Deep Convolutional Neural Network

Sun, Yuliang; Fei, Tai; Gao, Shangyin; Pohl, Nils

doi:10.1109/icassp.2019.8682277

Cited by 31 publications

(23 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Angle of Arrival (AoA) of the reflected or scattered signal in both the elevation dimension and azimuth dimension (bearing angle) is calculated based on Multiple Input Multiple Output (MIMO) radar principles [130], [172], [173]. Rather than having one transmitter and one receiver, multiple transmitters and receivers are used.…”

Section: A Collection Systemsmentioning

confidence: 99%

“…Pulse integration uses the integration operation with the purpose of improving signal-to-noise ratio [128], [179], help discover movement in a spectrogram [106], and to deduce a spectrogram representing micro-doppler signatures [129], [130]. Pulse integration types include incoherent integration [106], coherent integration [128], spectrogram integration across range [129], [130], and a wideband signal filter operation [179]. POSP is used in [141] to calculate an integral.…”

Section: Time Domain Frequency Domainmentioning

confidence: 99%

“…The border between feature extraction and analytical modeling has become blurry in recent papers on millimeter wave sensing applications. Several deep learning models contain layers designated for feature extraction [16], [46], [47], [92], [125], [126], [130], [138], [158]. Certain positioning and environment mapping algorithms resemble feature extraction methodologies [160], [184].…”

Section: Feature Extractionmentioning

confidence: 99%

“…A Convolutional Neural Network (CNN) is a deep learning model of which at least one layer involves convolution operations. CNNs found in millimeter wave sensing application pipelines are mainly combined with 2D spectrograms [48], [53], [92], [93], [123], [127], [130] and 2D radar images [103], [120], [174], [181], [192], [193]. CNNs have been used extensively for images originating from vision and object detection domains in the past.…”

Section: White Box Grey Box Shallow Black Box Deep Black Boxmentioning

confidence: 99%

“…The data types are 2-dimensional and features relevant to the mapping function are made up of values local to one another in the value matrix. Another observation is that many approaches base their model on existing vision and object detection models such as VGG [92], [93], ResNet [92], [123], ZFnet [193], Faster R-CNN [130], [181], YOLO [192] and FCOS [120]. The pipelines therefore rely on experience gathered with images in the vision and object detection domains.…”

Section: White Box Grey Box Shallow Black Box Deep Black Boxmentioning

confidence: 99%

See 4 more Smart Citations

Millimeter Wave Sensing: A Review of Application Pipelines and Building Blocks

et al. 2021

View full text Add to dashboard Cite

The increasing bandwidth requirement of new wireless applications has lead to standardization of the millimeter wave spectrum for high-speed wireless communication. The millimeter wave spectrum is part of 5G and covers frequencies between 30 and 300 GHz that correspond to wavelengths ranging from 10 to 1 mm. Although millimeter wave is often considered as a communication medium, it has also proved to be an excellent 'sensor', thanks to its narrow beams, operation across a wide bandwidth, and interaction with atmospheric constituents. In this paper, which is to the best of our knowledge the first review that completely covers millimeter wave sensing application pipelines, we provide a comprehensive overview and analysis of different basic application pipeline building blocks, including hardware, algorithms, analytical models, and model evaluation techniques. The review also provides a taxonomy that highlights different millimeter wave sensing application domains. By performing a thorough analysis, complying with the systematic literature review methodology and reviewing 165 papers, we not only extend previous investigations focused only on communication aspects of the millimeter wave technology and using millimeter wave technology for active imaging, but also highlight scientific and technological challenges and trends, and provide a future perspective for applications of millimeter wave as a sensing technology.

show abstract

Section: A Collection Systemsmentioning

confidence: 99%