Pub Date : 2021-10-31DOI: 10.1109/SENSORS47087.2021.9639486
Wenxin Wu, Kevin Schnittker, J. Andrews
Printable electronics have demonstrated significant promise in enabling soft tactile sensing systems. This paper presents a fully printed and soft capacitive pressure sensor realized through a two-dimensional interdigitated capacitor. The sensor transduces applied pressures through a fringing electric field interacting with a deformable elastomer. The deformable elastomer consists of either pure polydimethylsiloxane (PDMS) or a layered PDMS/BaTiO3 structure. A 10 mm overlaid layered structure is created by depositing six alternating layers of a Barium Titanate-PDMS mixture and pure PDMS, followed by a 4 mm PDMS layer on the printed electrode. Multiple tests using standardized pressure and capacitance measurements have been performed to measure and compare the sensitivity between pure PDMS and PDMS/BaTiO3 layered configuration. The capacitive response shows that the layered PDMS/BaTiO3 device enhances the sensitivity for pressures less than 1 kPa by approximately 10x. This work demonstrates the potential of a printed electronic sensor in measuring small-scale pressure variation using inexpensive and simple fabrication methods.
{"title":"Printed Capacitive Pressure Sensor with Enhanced Sensitivity through a Layered PDMS/BaTiO3 Structure","authors":"Wenxin Wu, Kevin Schnittker, J. Andrews","doi":"10.1109/SENSORS47087.2021.9639486","DOIUrl":"https://doi.org/10.1109/SENSORS47087.2021.9639486","url":null,"abstract":"Printable electronics have demonstrated significant promise in enabling soft tactile sensing systems. This paper presents a fully printed and soft capacitive pressure sensor realized through a two-dimensional interdigitated capacitor. The sensor transduces applied pressures through a fringing electric field interacting with a deformable elastomer. The deformable elastomer consists of either pure polydimethylsiloxane (PDMS) or a layered PDMS/BaTiO3 structure. A 10 mm overlaid layered structure is created by depositing six alternating layers of a Barium Titanate-PDMS mixture and pure PDMS, followed by a 4 mm PDMS layer on the printed electrode. Multiple tests using standardized pressure and capacitance measurements have been performed to measure and compare the sensitivity between pure PDMS and PDMS/BaTiO3 layered configuration. The capacitive response shows that the layered PDMS/BaTiO3 device enhances the sensitivity for pressures less than 1 kPa by approximately 10x. This work demonstrates the potential of a printed electronic sensor in measuring small-scale pressure variation using inexpensive and simple fabrication methods.","PeriodicalId":6775,"journal":{"name":"2021 IEEE Sensors","volume":"14 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90143353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-31DOI: 10.1109/SENSORS47087.2021.9639796
Riadh A. Kadhim, Al-Hemeary Nawar, Jiang Wu
The surface plasmon resonance (SPR) of the refractive index (RI) sensor based on a Multiple D-shaped Au/Fe3O4 Nanowire is presented in this paper. This designed sensor uses magnetite (Fe3O4) as the sensing layer, coated on the multiple D-shaped gold nanowires (AuNWs) to stimulate the plasmon mode. The key sensing mechanism is the interaction between the fundamental fiber guided mode and plasmonic modes of optical fibers, which results in the formation of various resonance peaks depending on the analyte RI. Finite-Element Method (FEM) based COMSOL Multiphysicsis employed to analyze the surface plasmon properties. By optimizing the performance key parameters of the proposed sensor, the radius of the AuNW and the thickness of the magnetite sensing layer on sensor sensitivity (S) are optimized. Simulation results indicate enhanced sensitivity at 8.5µm/RIU. The resolution is 1.17 ×10−6 RIU in the sensing RI range of 1.33 -1.39. The results indicated that the proposed plasmonic sensor-based multiple D-shaped AuNWs with Fe3O4 nanomaterials structure has potential biosensor applications.
{"title":"Plasmonic Refractive Index Sensor Based on a Multiple D-shaped Au/Fe3O4 Nanowire","authors":"Riadh A. Kadhim, Al-Hemeary Nawar, Jiang Wu","doi":"10.1109/SENSORS47087.2021.9639796","DOIUrl":"https://doi.org/10.1109/SENSORS47087.2021.9639796","url":null,"abstract":"The surface plasmon resonance (SPR) of the refractive index (RI) sensor based on a Multiple D-shaped Au/Fe3O4 Nanowire is presented in this paper. This designed sensor uses magnetite (Fe3O4) as the sensing layer, coated on the multiple D-shaped gold nanowires (AuNWs) to stimulate the plasmon mode. The key sensing mechanism is the interaction between the fundamental fiber guided mode and plasmonic modes of optical fibers, which results in the formation of various resonance peaks depending on the analyte RI. Finite-Element Method (FEM) based COMSOL Multiphysicsis employed to analyze the surface plasmon properties. By optimizing the performance key parameters of the proposed sensor, the radius of the AuNW and the thickness of the magnetite sensing layer on sensor sensitivity (S) are optimized. Simulation results indicate enhanced sensitivity at 8.5µm/RIU. The resolution is 1.17 ×10−6 RIU in the sensing RI range of 1.33 -1.39. The results indicated that the proposed plasmonic sensor-based multiple D-shaped AuNWs with Fe3O4 nanomaterials structure has potential biosensor applications.","PeriodicalId":6775,"journal":{"name":"2021 IEEE Sensors","volume":"510 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85640352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-31DOI: 10.1109/SENSORS47087.2021.9639600
Saikat Banerjee, Mathew L. Nguyen, G. Slaughter
A glucose biofuel cell on a flexible bacterial nanocellulose film was prepared. The bioelectrodes were printed using gold ink as the conductive material. The anode was modified with colloidal platinum for the oxidation of glucose. The cathode was modified with a nanocomposite comprising gold nanoparticles (AuNPs) and silver oxide (Ag2O) nanoparticles. The cathode was characterized via cyclic voltammetry (CV), electrochemical impedance spectroscopy (EIS), and UV spectroscopy techniques. The assembled biofuel cell generated a maximum open circuit voltage (Voc) of 0.485 V, short circuit current (Isc) of 0.352 mA/cm2, and a maximum peak power density (Pmax) of 0.032 mW/cm2 when operating in 30 mM concentration. This system showed a stable and linear performance with a linear range of 1 mM to 30 mM glucose. The gold printed electrode process is applicable to the development of wearable and implantable abiotic biofuel cell.
{"title":"Gold and silver oxide conducting nanocomposite cathode for glucose biofuel cell","authors":"Saikat Banerjee, Mathew L. Nguyen, G. Slaughter","doi":"10.1109/SENSORS47087.2021.9639600","DOIUrl":"https://doi.org/10.1109/SENSORS47087.2021.9639600","url":null,"abstract":"A glucose biofuel cell on a flexible bacterial nanocellulose film was prepared. The bioelectrodes were printed using gold ink as the conductive material. The anode was modified with colloidal platinum for the oxidation of glucose. The cathode was modified with a nanocomposite comprising gold nanoparticles (AuNPs) and silver oxide (Ag2O) nanoparticles. The cathode was characterized via cyclic voltammetry (CV), electrochemical impedance spectroscopy (EIS), and UV spectroscopy techniques. The assembled biofuel cell generated a maximum open circuit voltage (Voc) of 0.485 V, short circuit current (Isc) of 0.352 mA/cm2, and a maximum peak power density (Pmax) of 0.032 mW/cm2 when operating in 30 mM concentration. This system showed a stable and linear performance with a linear range of 1 mM to 30 mM glucose. The gold printed electrode process is applicable to the development of wearable and implantable abiotic biofuel cell.","PeriodicalId":6775,"journal":{"name":"2021 IEEE Sensors","volume":"92 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91051381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study demonstrates the piezoelectric MEMS microphone (Fig. 1a) with cantilever diaphragms and partially removed PZT (piezoelectric layer) to increase the bandwidth (BW) without sacrificing signal-to-noise ratio (SNR). The proposed design in Fig. 1a has two major merits: (1) the figure of merit of SNR×BW is presented to evaluate the performance of microphone design, (2) based on the figure of merit, the PZT and top electrode layers are partially removed to achieve a better BW without sacrificing the SNR; and two minor merits: (1) to pattern the bottom electrode to reduce stress-induced diaphragm bending to lower the acoustic short circuit; (2) apply DC bias on PZT layer to further reduce diaphragm bending. Measurements demonstrate the SNR at 1kHz up to 77.2 dB with bandwidth up to 10kHz for proposed design, and the comparison with reference designs are summarized in Table 2. Moreover, the proposed design has a 3 dB sensitivity enhancement after applying 10 V bias on PZT.
{"title":"On The Performance Enhancement of Cantilever Diaphragm Piezoelectric Microphone","authors":"Shao-Da Wang, Yu-Chen Chen, Sung-Cheng Lo, Yi-Jia Wang, Mingching Wu, W. Fang","doi":"10.1109/SENSORS47087.2021.9639769","DOIUrl":"https://doi.org/10.1109/SENSORS47087.2021.9639769","url":null,"abstract":"This study demonstrates the piezoelectric MEMS microphone (Fig. 1a) with cantilever diaphragms and partially removed PZT (piezoelectric layer) to increase the bandwidth (BW) without sacrificing signal-to-noise ratio (SNR). The proposed design in Fig. 1a has two major merits: (1) the figure of merit of SNR×BW is presented to evaluate the performance of microphone design, (2) based on the figure of merit, the PZT and top electrode layers are partially removed to achieve a better BW without sacrificing the SNR; and two minor merits: (1) to pattern the bottom electrode to reduce stress-induced diaphragm bending to lower the acoustic short circuit; (2) apply DC bias on PZT layer to further reduce diaphragm bending. Measurements demonstrate the SNR at 1kHz up to 77.2 dB with bandwidth up to 10kHz for proposed design, and the comparison with reference designs are summarized in Table 2. Moreover, the proposed design has a 3 dB sensitivity enhancement after applying 10 V bias on PZT.","PeriodicalId":6775,"journal":{"name":"2021 IEEE Sensors","volume":"113 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91106955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-31DOI: 10.1109/SENSORS47087.2021.9639725
R. Ecker, A. Fuchsluger, B. Jakoby
The design, fabrication, and evaluation of an electroosmotic pump (EOP) for high flow rate water transport is reported in this paper. Using polymethylmethacrylate (PMMA) as a substrate and using mainly thermal processing enables simple low-cost fabrication. The placement of a glass fiber filter in the main channel immensely increases the contact surface between water and glass, which, together with the associated high zeta potentials, significantly boosts the EOP efficiency. Therefore, our microfluidic pump can achieve both high flow rates and high pressures. With the application of two gas permeable polytetrafluoroethylene (PTFE) membranes, oxygen and hydrogen caused by spurious electrolysis are easily removed from the system. Moreover, highly chemically inert platinum wires are used as electrodes, furthering the durability of the pump.
{"title":"Electroosmotic Pump Using a Glass Fiber Filter for High Flow Rate Water Transport","authors":"R. Ecker, A. Fuchsluger, B. Jakoby","doi":"10.1109/SENSORS47087.2021.9639725","DOIUrl":"https://doi.org/10.1109/SENSORS47087.2021.9639725","url":null,"abstract":"The design, fabrication, and evaluation of an electroosmotic pump (EOP) for high flow rate water transport is reported in this paper. Using polymethylmethacrylate (PMMA) as a substrate and using mainly thermal processing enables simple low-cost fabrication. The placement of a glass fiber filter in the main channel immensely increases the contact surface between water and glass, which, together with the associated high zeta potentials, significantly boosts the EOP efficiency. Therefore, our microfluidic pump can achieve both high flow rates and high pressures. With the application of two gas permeable polytetrafluoroethylene (PTFE) membranes, oxygen and hydrogen caused by spurious electrolysis are easily removed from the system. Moreover, highly chemically inert platinum wires are used as electrodes, furthering the durability of the pump.","PeriodicalId":6775,"journal":{"name":"2021 IEEE Sensors","volume":"14 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88848947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-31DOI: 10.1109/SENSORS47087.2021.9639633
Onat Güngör, T. Rosing, Baris Aksanli
Fault diagnosis is a key component of predictive system maintenance. Big data collected from sensors helps create data-driven fault diagnosis methods. However, it may be extremely costly to label specific fault types in a collected dataset. Hence, prediction algorithms should perform well under limited supervision. Few-shot learning (FSL) can provide a great prediction performance using very limited labeled data by discovering similarity among input pairs. But selection of a single FSL method may be arduous due to changing working conditions. Ensemble FSL solves this problem by combining a variety of FSL methods systematically. We propose an ensemble FSL framework, ENFES, where we combine 5 different Siamese neural network architectures using an iterative majority voting classifier. Our transfer learning-oriented experiments show that ENFES can improve the best algorithm significantly while using very limited labeled data. We obtain up to 16.4% improvement over the best algorithm by only using 0.3% of the training data.
{"title":"ENFES: ENsemble FEw-Shot Learning For Intelligent Fault Diagnosis with Limited Data","authors":"Onat Güngör, T. Rosing, Baris Aksanli","doi":"10.1109/SENSORS47087.2021.9639633","DOIUrl":"https://doi.org/10.1109/SENSORS47087.2021.9639633","url":null,"abstract":"Fault diagnosis is a key component of predictive system maintenance. Big data collected from sensors helps create data-driven fault diagnosis methods. However, it may be extremely costly to label specific fault types in a collected dataset. Hence, prediction algorithms should perform well under limited supervision. Few-shot learning (FSL) can provide a great prediction performance using very limited labeled data by discovering similarity among input pairs. But selection of a single FSL method may be arduous due to changing working conditions. Ensemble FSL solves this problem by combining a variety of FSL methods systematically. We propose an ensemble FSL framework, ENFES, where we combine 5 different Siamese neural network architectures using an iterative majority voting classifier. Our transfer learning-oriented experiments show that ENFES can improve the best algorithm significantly while using very limited labeled data. We obtain up to 16.4% improvement over the best algorithm by only using 0.3% of the training data.","PeriodicalId":6775,"journal":{"name":"2021 IEEE Sensors","volume":"26 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87492202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-31DOI: 10.1109/SENSORS47087.2021.9639597
Shirin Mahinnezhad, H. Emami, Mohsen Ketabi, A. A. Shboul, Najet Belkhamssa, Andy Shih, R. Izquierdo
In this work, a fully screen-printed and flexible potentiometric pH sensor was designed and fabricated by incorporating a carbon black (CB) paste/polyaniline emeraldine salt (PANI-ES) nanocomposite as the working electrode and Ag/AgCl as the quasi-reference electrode. Rather than the PANI electrochemical polymerization deposition method, the PANI-ES was blended with a commercial CB paste for screen-printing, enabling a fully printed and scalable process. As a result, a nanocomposite mixture of 99.1% CB and 0.9% PANI-ES emerged as a promising nanocomposite candidate to develop high-performance pH sensors. The sensor exhibited a near Nernstian sensitivity of 50 mV/pH, response time of 15 s at room temperature, high linearity in the pH range between 3 and 11 and reversible pH sensing performance. The sensing mechanism depends mainly on the degree of the oxidation states transition of PANI-ES at different pH levels. The proposed flexible pH sensor can be used to monitor a patient’s health and water quality.
{"title":"Fully Printed pH Sensor Based in Carbon Black/Polyaniline Nanocomposite","authors":"Shirin Mahinnezhad, H. Emami, Mohsen Ketabi, A. A. Shboul, Najet Belkhamssa, Andy Shih, R. Izquierdo","doi":"10.1109/SENSORS47087.2021.9639597","DOIUrl":"https://doi.org/10.1109/SENSORS47087.2021.9639597","url":null,"abstract":"In this work, a fully screen-printed and flexible potentiometric pH sensor was designed and fabricated by incorporating a carbon black (CB) paste/polyaniline emeraldine salt (PANI-ES) nanocomposite as the working electrode and Ag/AgCl as the quasi-reference electrode. Rather than the PANI electrochemical polymerization deposition method, the PANI-ES was blended with a commercial CB paste for screen-printing, enabling a fully printed and scalable process. As a result, a nanocomposite mixture of 99.1% CB and 0.9% PANI-ES emerged as a promising nanocomposite candidate to develop high-performance pH sensors. The sensor exhibited a near Nernstian sensitivity of 50 mV/pH, response time of 15 s at room temperature, high linearity in the pH range between 3 and 11 and reversible pH sensing performance. The sensing mechanism depends mainly on the degree of the oxidation states transition of PANI-ES at different pH levels. The proposed flexible pH sensor can be used to monitor a patient’s health and water quality.","PeriodicalId":6775,"journal":{"name":"2021 IEEE Sensors","volume":"22 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84202597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-31DOI: 10.1109/SENSORS47087.2021.9639706
S. Kianoush, S. Savazzi, V. Rampa, L. Costa, Denis Tolochenko
Infrared (IR) thermal vision systems provide a passive and contact-less framework to evaluate temporal signatures of people presence in indoor scenarios. However, static 2D IR thermal projection of complex 3D objects cannot provide sufficient information for large-scale and continuous people estimation tasks. This paper proposes a change-point detection algorithm that jointly fuses thermal and distance information obtained from an IR array and an ultrasonic distance sensor to detect targets, namely human subjects, inside an indoor environment. An extensive validation phase has been carried out through experimental trials that have been conducted in a smart office using ceiling-mounted devices. Unlike previous works in this area, the proposed approach eliminates time consuming calibration steps by highlighting the benefits of the IR thermal and ultrasonic sensor fusion framework.
{"title":"Calibration-free target detection based on thermal and distance sensor fusion","authors":"S. Kianoush, S. Savazzi, V. Rampa, L. Costa, Denis Tolochenko","doi":"10.1109/SENSORS47087.2021.9639706","DOIUrl":"https://doi.org/10.1109/SENSORS47087.2021.9639706","url":null,"abstract":"Infrared (IR) thermal vision systems provide a passive and contact-less framework to evaluate temporal signatures of people presence in indoor scenarios. However, static 2D IR thermal projection of complex 3D objects cannot provide sufficient information for large-scale and continuous people estimation tasks. This paper proposes a change-point detection algorithm that jointly fuses thermal and distance information obtained from an IR array and an ultrasonic distance sensor to detect targets, namely human subjects, inside an indoor environment. An extensive validation phase has been carried out through experimental trials that have been conducted in a smart office using ceiling-mounted devices. Unlike previous works in this area, the proposed approach eliminates time consuming calibration steps by highlighting the benefits of the IR thermal and ultrasonic sensor fusion framework.","PeriodicalId":6775,"journal":{"name":"2021 IEEE Sensors","volume":"73 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84268212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-31DOI: 10.1109/SENSORS47087.2021.9639798
Michael Stephan, Souvik Hazra, Avik Santra, R. Weigel, Georg Fischer
Radar systems enable remote sensing of multiple persons within their field of view. In this paper, we propose a novel architecture to perform people counting using a 60 GHz Frequency Modulated Continuous Wave radar trained on supervised radar data and knowledge distillation performed using synchronized camera data. In the evaluation phase, only the radar encoder with Range - Doppler Images (RDI) as input is used and tested on a dataset consisting of scenarios recorded in a different setup than the training recordings with up to 6 persons present. In this paper we focus on showing the benefit of using the cross-modal camera information compared to the same unimodal model. In spite of the low-cost radar sensor, the proposed architecture achieves an accuracy of 71% compared to 58% for the test data from a different sensor with a different orientation and aspect angle, and an accuracy of 89% compared to 74% for test data from the same radar sensor when training without knowledge distillation.
{"title":"People Counting Solution Using an FMCW Radar with Knowledge Distillation From Camera Data","authors":"Michael Stephan, Souvik Hazra, Avik Santra, R. Weigel, Georg Fischer","doi":"10.1109/SENSORS47087.2021.9639798","DOIUrl":"https://doi.org/10.1109/SENSORS47087.2021.9639798","url":null,"abstract":"Radar systems enable remote sensing of multiple persons within their field of view. In this paper, we propose a novel architecture to perform people counting using a 60 GHz Frequency Modulated Continuous Wave radar trained on supervised radar data and knowledge distillation performed using synchronized camera data. In the evaluation phase, only the radar encoder with Range - Doppler Images (RDI) as input is used and tested on a dataset consisting of scenarios recorded in a different setup than the training recordings with up to 6 persons present. In this paper we focus on showing the benefit of using the cross-modal camera information compared to the same unimodal model. In spite of the low-cost radar sensor, the proposed architecture achieves an accuracy of 71% compared to 58% for the test data from a different sensor with a different orientation and aspect angle, and an accuracy of 89% compared to 74% for test data from the same radar sensor when training without knowledge distillation.","PeriodicalId":6775,"journal":{"name":"2021 IEEE Sensors","volume":"183 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86814645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-31DOI: 10.1109/SENSORS47087.2021.9639696
Faisal Ahmed, Miguel Heredia Conde, O. Loffeld
The need for active illumination is one of the fundamental downsides of state-of-the-art Time-of-Flight (ToF) cameras and translates into large power consumption as compared to passive imaging modalities. Recently, developments in visible light communications (VLC) have allowed the lighting infrastructure to provide both illumination and communication services in indoor environments. In this paper, we propose exploiting visible light sources as opportunity illuminators for indoor ToF sensing. This allows for drastically reducing the power consumption of the ToF camera, as the need for illumination modules is eliminated. We study the feasibility of this idea using an off-the-shelf VLC module, model the emitted light signal, and study its autocorrelation properties. We show that the prominence of two dominant frequencies, arising from the underlying clock signal and coding scheme, enables CW-ToF operation. Simulations carried out using real signals from the VLC module showed successful depth estimation, up to an offset, using standard methods for CW-ToF depth estimation such as the four-phases algorithm.
{"title":"Pseudo-Passive Indoor ToF Sensing exploiting Visible Light Communication Sources","authors":"Faisal Ahmed, Miguel Heredia Conde, O. Loffeld","doi":"10.1109/SENSORS47087.2021.9639696","DOIUrl":"https://doi.org/10.1109/SENSORS47087.2021.9639696","url":null,"abstract":"The need for active illumination is one of the fundamental downsides of state-of-the-art Time-of-Flight (ToF) cameras and translates into large power consumption as compared to passive imaging modalities. Recently, developments in visible light communications (VLC) have allowed the lighting infrastructure to provide both illumination and communication services in indoor environments. In this paper, we propose exploiting visible light sources as opportunity illuminators for indoor ToF sensing. This allows for drastically reducing the power consumption of the ToF camera, as the need for illumination modules is eliminated. We study the feasibility of this idea using an off-the-shelf VLC module, model the emitted light signal, and study its autocorrelation properties. We show that the prominence of two dominant frequencies, arising from the underlying clock signal and coding scheme, enables CW-ToF operation. Simulations carried out using real signals from the VLC module showed successful depth estimation, up to an offset, using standard methods for CW-ToF depth estimation such as the four-phases algorithm.","PeriodicalId":6775,"journal":{"name":"2021 IEEE Sensors","volume":"28 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86971308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：