Pub Date : 2018-04-01DOI: 10.1109/ICMIM.2018.8443547
Keerthi Kumar Nagalapur, E. Ström, Fredrik Brännström, J. Carlsson, K. Karlsson
For critical vehicular communication services, such as traffic safety and traffic efficiency, it is advisable to design systems with robustness as the main criteria, possibly at the price of reduced peak performance and efficiency. We describe a simple, low-cost method for combining the output of L nonideal (i.e., nonisotropic) antennas to the input signal to a single-port receiver with the aim to guarantee robustness, i.e., to minimize the probability that K consecutive packets arriving from the worst-case angle-of-arrival are decoded incorrectly. To minimize complexity, the combining network does not estimate or use channel state information (complex channel gains, noise levels, etc.). The combining network consists of L −1 analog phase shifters whose phases are affine functions of time. For a general L and the case when the packet error probability decays exponentially with the received SNR, the optimum slopes of the affine functions can be computed by solving an optimization problem that depends on the antenna far field functions. We provide an analytical solution for the special case of L $=2$ antennas, which turns out to be independent of the antenna patterns. In an experimental setup consisting of two monopole antennas mounted on the roof of a Volvo XC90, the proposed combining method is shown to give significant performance gains compared to using just one of the antennas.
{"title":"A Simple Method for Robust Vehicular Communication with Multiple Nonideal Antennas","authors":"Keerthi Kumar Nagalapur, E. Ström, Fredrik Brännström, J. Carlsson, K. Karlsson","doi":"10.1109/ICMIM.2018.8443547","DOIUrl":"https://doi.org/10.1109/ICMIM.2018.8443547","url":null,"abstract":"For critical vehicular communication services, such as traffic safety and traffic efficiency, it is advisable to design systems with robustness as the main criteria, possibly at the price of reduced peak performance and efficiency. We describe a simple, low-cost method for combining the output of L nonideal (i.e., nonisotropic) antennas to the input signal to a single-port receiver with the aim to guarantee robustness, i.e., to minimize the probability that K consecutive packets arriving from the worst-case angle-of-arrival are decoded incorrectly. To minimize complexity, the combining network does not estimate or use channel state information (complex channel gains, noise levels, etc.). The combining network consists of L −1 analog phase shifters whose phases are affine functions of time. For a general L and the case when the packet error probability decays exponentially with the received SNR, the optimum slopes of the affine functions can be computed by solving an optimization problem that depends on the antenna far field functions. We provide an analytical solution for the special case of L $=2$ antennas, which turns out to be independent of the antenna patterns. In an experimental setup consisting of two monopole antennas mounted on the roof of a Volvo XC90, the proposed combining method is shown to give significant performance gains compared to using just one of the antennas.","PeriodicalId":342532,"journal":{"name":"2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132849690","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 : 2018-04-01DOI: 10.1109/ICMIM.2018.8443504
Marc A. Mutschler, Philipp A. Scharf, Pascal Fonfara, H. Mantz, T. Walter, C. Waldschmidt
In this contribution results from radar based Doppler measurements for rain drop detection will be presented and discussed. It will be pointed out that using such sensors not only the velocity but also the incident angle of the impinging rain drop can be determined which is an additional relevant parameter for an environmental sensor. Furthermore, the importance of simulation will be addressed for an enhanced understanding of such multi-particle problems
{"title":"Radar Based Rain Drop Classification for Industrial Applications","authors":"Marc A. Mutschler, Philipp A. Scharf, Pascal Fonfara, H. Mantz, T. Walter, C. Waldschmidt","doi":"10.1109/ICMIM.2018.8443504","DOIUrl":"https://doi.org/10.1109/ICMIM.2018.8443504","url":null,"abstract":"In this contribution results from radar based Doppler measurements for rain drop detection will be presented and discussed. It will be pointed out that using such sensors not only the velocity but also the incident angle of the impinging rain drop can be determined which is an additional relevant parameter for an environmental sensor. Furthermore, the importance of simulation will be addressed for an enhanced understanding of such multi-particle problems","PeriodicalId":342532,"journal":{"name":"2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114139431","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 : 2018-04-01DOI: 10.1109/ICMIM.2018.8443483
Yassen Dobrev, Y. Dobrev, P. Gulden, Melanie Lipka, T. Pavlenko, D. Moormann, M. Vossiek
Global navigation satellite systems (GNSS) such as GPS are the de-facto standard for absolute and reliable unmanned aerial vehicles (UAV) localization due to their global availability and the maturity and wide spread of the underlying technology. However, as the spread and reliance upon autonomous UAV systems increases, the risk of jamming becomes a substantial safety problem. The area where jamming attacks are most likely to occur is the close vicinity of the UAV landing station. Hence, to ensure reliable operations, an alternative localization technology for the approach and landing phase is needed. This paper presents a localization system for 3D position estimation based on 24 GHz FMCW cooperative radar. It has very low infrastructure requirements thanks to the combination of ranging and direction-of-arrival (DOA) estimation techniques employed in the ground station. Jamming resistance is improved due to the large bandwidth of 250 MHz. A measurement campaign was conducted to prove the feasibility of the proposed concept.
{"title":"Radar-Based High-Accuracy 3D Localization of UAVs for Landing in GNSS-Denied Environments","authors":"Yassen Dobrev, Y. Dobrev, P. Gulden, Melanie Lipka, T. Pavlenko, D. Moormann, M. Vossiek","doi":"10.1109/ICMIM.2018.8443483","DOIUrl":"https://doi.org/10.1109/ICMIM.2018.8443483","url":null,"abstract":"Global navigation satellite systems (GNSS) such as GPS are the de-facto standard for absolute and reliable unmanned aerial vehicles (UAV) localization due to their global availability and the maturity and wide spread of the underlying technology. However, as the spread and reliance upon autonomous UAV systems increases, the risk of jamming becomes a substantial safety problem. The area where jamming attacks are most likely to occur is the close vicinity of the UAV landing station. Hence, to ensure reliable operations, an alternative localization technology for the approach and landing phase is needed. This paper presents a localization system for 3D position estimation based on 24 GHz FMCW cooperative radar. It has very low infrastructure requirements thanks to the combination of ranging and direction-of-arrival (DOA) estimation techniques employed in the ground station. Jamming resistance is improved due to the large bandwidth of 250 MHz. A measurement campaign was conducted to prove the feasibility of the proposed concept.","PeriodicalId":342532,"journal":{"name":"2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115745530","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 : 2018-04-01DOI: 10.1109/ICMIM.2018.8443554
A. Laribi, Markus Hahn, J. Dickmann, C. Waldschmidt
This paper investigates the potential of applying synthetic aperture radar (SAR) to automotive applications using a short range vehicle-mounted Frequency Modulation Continuous Wave (FMCW) radar. The Range Migration Algorithm (RMA) is adopted in this work for SAR image formation as it is ideal for focusing range curvatures of targets at short ranges. The first part of this paper gives a brief overview of RMA based strip map SAR processing of FMCW radar signals. In the latter part, collected data of real world stationary targets such as cars, poles and buildings are processed providing high resolution SAR images of different synthetic aperture lengths. The obtained images are presented, discussed and compared in terms of cross range accuracy and resolution to show that high resolution target imaging can be achieved using automotive SAR.
{"title":"Performance Investigation of Automotive SAR Imaging","authors":"A. Laribi, Markus Hahn, J. Dickmann, C. Waldschmidt","doi":"10.1109/ICMIM.2018.8443554","DOIUrl":"https://doi.org/10.1109/ICMIM.2018.8443554","url":null,"abstract":"This paper investigates the potential of applying synthetic aperture radar (SAR) to automotive applications using a short range vehicle-mounted Frequency Modulation Continuous Wave (FMCW) radar. The Range Migration Algorithm (RMA) is adopted in this work for SAR image formation as it is ideal for focusing range curvatures of targets at short ranges. The first part of this paper gives a brief overview of RMA based strip map SAR processing of FMCW radar signals. In the latter part, collected data of real world stationary targets such as cars, poles and buildings are processed providing high resolution SAR images of different synthetic aperture lengths. The obtained images are presented, discussed and compared in terms of cross range accuracy and resolution to show that high resolution target imaging can be achieved using automotive SAR.","PeriodicalId":342532,"journal":{"name":"2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132747655","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 : 2018-04-01DOI: 10.1109/ICMIM.2018.8443524
Martin Schtz, Yassen Dobrev, C. Carlowitz, M. Vossiek
In this paper, we present a concept for wireless local positioning with multiple backscatter transponders based on the switched-injection locked oscillator (SILO). It allows reliable localization and ego-motion estimation of autonomous robots in indoor and outdoor environments. We derive the range-doppler spectrum of the beat signal that is induced by a single transponder in a FMCW radar system. With multiple transponders, a localization network is created that allows multilateral and multiangulation based positioning. For an initial evaluation, we built a miniaturized transponder for the 24 GHz ISM band and proofed the concept with a straightforward measurement, including two transponders, a moving ground robot equipped with a FMCW radar system and a laser tracker reference.
{"title":"Wireless Local Positioning with SILO-Based Backscatter Transponders for Autonomous Robot Navigation","authors":"Martin Schtz, Yassen Dobrev, C. Carlowitz, M. Vossiek","doi":"10.1109/ICMIM.2018.8443524","DOIUrl":"https://doi.org/10.1109/ICMIM.2018.8443524","url":null,"abstract":"In this paper, we present a concept for wireless local positioning with multiple backscatter transponders based on the switched-injection locked oscillator (SILO). It allows reliable localization and ego-motion estimation of autonomous robots in indoor and outdoor environments. We derive the range-doppler spectrum of the beat signal that is induced by a single transponder in a FMCW radar system. With multiple transponders, a localization network is created that allows multilateral and multiangulation based positioning. For an initial evaluation, we built a miniaturized transponder for the 24 GHz ISM band and proofed the concept with a straightforward measurement, including two transponders, a moving ground robot equipped with a FMCW radar system and a laser tracker reference.","PeriodicalId":342532,"journal":{"name":"2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116821074","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 : 2018-04-01DOI: 10.1109/ICMIM.2018.8443549
Javier Martinez, D. Kopyto, Martin Schütz, M. Vossiek
We present an approach to detect and locate non-cooperative UAVs from their micro-Doppler signature using a narrowband radar in a multi-site configuration. We describe a method for the localization of rotating objects with the geometric information obtained exclusively from their micro-Doppler signatures. This approach only requires very simple transceivers with CW waveforms, in a cost-effective multi-site architecture. A convolutional neural network is used to detect and identify the UAVs by extracting the characteristic features of their micro-Doppler signature. We present simulated and preliminary experimental data that show the technical viability of this concept.
{"title":"Convolutional Neural Network Assisted Detection and Localization of UAVs with a Narrowband Multi-site Radar","authors":"Javier Martinez, D. Kopyto, Martin Schütz, M. Vossiek","doi":"10.1109/ICMIM.2018.8443549","DOIUrl":"https://doi.org/10.1109/ICMIM.2018.8443549","url":null,"abstract":"We present an approach to detect and locate non-cooperative UAVs from their micro-Doppler signature using a narrowband radar in a multi-site configuration. We describe a method for the localization of rotating objects with the geometric information obtained exclusively from their micro-Doppler signatures. This approach only requires very simple transceivers with CW waveforms, in a cost-effective multi-site architecture. A convolutional neural network is used to detect and identify the UAVs by extracting the characteristic features of their micro-Doppler signature. We present simulated and preliminary experimental data that show the technical viability of this concept.","PeriodicalId":342532,"journal":{"name":"2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115413354","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 : 2018-04-01DOI: 10.1109/ICMIM.2018.8443355
Peter Große, Carsten Andrich, W. Kotterman, Alexander Ihlow, G. D. Galdo
We transmit ETSI ITS-G5 standard compliant packets using commercial off-the-shelf Wi-Fi cards based on the Atheros 9k chipset under Linux operating system and measure latencies within the transmission chain by a ping-pong scheme. While preparing, enqueing, and handing over a packet to the kernel via send() takes about 10 microseconds, a reception delay of about 500 microseconds is introduced, before the dequeing and return of recv() takes about another 10 microseconds. The 500 microsecond delay is caused by RX interrupt mitigation in the ath9k device driver and can be adjusted by a kernel patch.
{"title":"Measuring ETSI ITS-G5 Communications Latencies with Commercial off-the-shelf Wi-Fi Hardware","authors":"Peter Große, Carsten Andrich, W. Kotterman, Alexander Ihlow, G. D. Galdo","doi":"10.1109/ICMIM.2018.8443355","DOIUrl":"https://doi.org/10.1109/ICMIM.2018.8443355","url":null,"abstract":"We transmit ETSI ITS-G5 standard compliant packets using commercial off-the-shelf Wi-Fi cards based on the Atheros 9k chipset under Linux operating system and measure latencies within the transmission chain by a ping-pong scheme. While preparing, enqueing, and handing over a packet to the kernel via send() takes about 10 microseconds, a reception delay of about 500 microseconds is introduced, before the dequeing and return of recv() takes about another 10 microseconds. The 500 microsecond delay is caused by RX interrupt mitigation in the ath9k device driver and can be adjusted by a kernel patch.","PeriodicalId":342532,"journal":{"name":"2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116742459","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 : 2018-04-01DOI: 10.1109/ICMIM.2018.8443505
M. Vogt
The measurement of the filling level of liquid and solid goods in storage, process, and other tanks and silos is an important task in many industries. Examples of liquids are oil, gasoline, various chemicals and pharmaceuticals, water, and beverages. Also, a large variety of bulk solids can be given, for example fine granulated solids like flour, sugar, sand, grains, and various powders. Examples of more rough solids are pellets, coal, grit, stones, and others. Resulting from the different electrical properties (permittivity and conductivity) and the different sizes and structures, the reflection, scattering, and attenuation properties are strongly different. Radar sensors operating at frequencies up to 24 GHz are already well-established for level measurement applications. Radio regulations and the latest state- of-the-art technology have now also made radar level meters at high frequencies in the 80 GHz range commercially available. In this contribution, first the measurement scenarios and conditions given with liquids and bulk solids are both discussed and compared to each other. Secondly, criteria and technical backgrounds for a suitable choice between 24 GHz and 80 GHz radar systems dependent on the specific level measurement application are motivated and given. Thereafter, the realization of components for according radar sensors is presented and discussed, with a focus on the radio-frequency (RF) front-end electronics using monolithic microwave integrated circuits (MMIC) and different radar antenna concepts. For the latter, the given harsh conditions in the application are a challenge, as will be discussed. Finally, some exemplary results obtained from practical measurements with the discussed radar systems are presented and analyzed.
{"title":"Radar Sensors (24 and 80 GHz Range) for Level Measurement in Industrial Processes","authors":"M. Vogt","doi":"10.1109/ICMIM.2018.8443505","DOIUrl":"https://doi.org/10.1109/ICMIM.2018.8443505","url":null,"abstract":"The measurement of the filling level of liquid and solid goods in storage, process, and other tanks and silos is an important task in many industries. Examples of liquids are oil, gasoline, various chemicals and pharmaceuticals, water, and beverages. Also, a large variety of bulk solids can be given, for example fine granulated solids like flour, sugar, sand, grains, and various powders. Examples of more rough solids are pellets, coal, grit, stones, and others. Resulting from the different electrical properties (permittivity and conductivity) and the different sizes and structures, the reflection, scattering, and attenuation properties are strongly different. Radar sensors operating at frequencies up to 24 GHz are already well-established for level measurement applications. Radio regulations and the latest state- of-the-art technology have now also made radar level meters at high frequencies in the 80 GHz range commercially available. In this contribution, first the measurement scenarios and conditions given with liquids and bulk solids are both discussed and compared to each other. Secondly, criteria and technical backgrounds for a suitable choice between 24 GHz and 80 GHz radar systems dependent on the specific level measurement application are motivated and given. Thereafter, the realization of components for according radar sensors is presented and discussed, with a focus on the radio-frequency (RF) front-end electronics using monolithic microwave integrated circuits (MMIC) and different radar antenna concepts. For the latter, the given harsh conditions in the application are a challenge, as will be discussed. Finally, some exemplary results obtained from practical measurements with the discussed radar systems are presented and analyzed.","PeriodicalId":342532,"journal":{"name":"2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116914516","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 : 2018-04-01DOI: 10.1109/ICMIM.2018.8443487
S. Hastürkoğlu, S. Lindenmeier
An automotive antenna set of four collinear arrays between 24.25 GHz and 29.5 GHz is introduced for application of 5G mobile communication in roof radomes of future cars. Each of the single antenna elements combines high gain in horizontal direction with an omnidirectional pattern which is well suited for application in multiple input multiple output (MIMO) transmission. In a phased array application the four antenna elements yield in the horizontal plane a high gain of 16 dBi at driving direction and 10.5 dBi in lateral direction which yields good access along the driving path. The gain of the antenna elements, efficiency, mutual coupling and the variable radiation characteristics of the antenna array are investigated by means of simulation and measurement.
{"title":"An Automotive Antenna Set at 26.5 GHz for 5G-Mobile Communication","authors":"S. Hastürkoğlu, S. Lindenmeier","doi":"10.1109/ICMIM.2018.8443487","DOIUrl":"https://doi.org/10.1109/ICMIM.2018.8443487","url":null,"abstract":"An automotive antenna set of four collinear arrays between 24.25 GHz and 29.5 GHz is introduced for application of 5G mobile communication in roof radomes of future cars. Each of the single antenna elements combines high gain in horizontal direction with an omnidirectional pattern which is well suited for application in multiple input multiple output (MIMO) transmission. In a phased array application the four antenna elements yield in the horizontal plane a high gain of 16 dBi at driving direction and 10.5 dBi in lateral direction which yields good access along the driving path. The gain of the antenna elements, efficiency, mutual coupling and the variable radiation characteristics of the antenna array are investigated by means of simulation and measurement.","PeriodicalId":342532,"journal":{"name":"2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122290574","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 : 2018-04-01DOI: 10.1109/ICMIM.2018.8443525
Christopher Grimm, Tobias Breddermann, Ridha Farhoud, T. Fei, Ernst Warsitz, R. Haeb-Umbach
In this paper, we present a neural network based classification algorithm for the discrimination of moving from stationary targets in the sight of an automotive radar sensor. Compared to existing algorithms, the proposed algorithm can take into account multiple local radar targets instead of performing classification inference on each target individually resulting in superior discrimination accuracy, especially suitable for non rigid objects, like pedestrians, which in general have a wide velocity spread when multiple targets are detected.
{"title":"Discrimination of stationary from moving targets with recurrent neural networks in automotive Radar","authors":"Christopher Grimm, Tobias Breddermann, Ridha Farhoud, T. Fei, Ernst Warsitz, R. Haeb-Umbach","doi":"10.1109/ICMIM.2018.8443525","DOIUrl":"https://doi.org/10.1109/ICMIM.2018.8443525","url":null,"abstract":"In this paper, we present a neural network based classification algorithm for the discrimination of moving from stationary targets in the sight of an automotive radar sensor. Compared to existing algorithms, the proposed algorithm can take into account multiple local radar targets instead of performing classification inference on each target individually resulting in superior discrimination accuracy, especially suitable for non rigid objects, like pedestrians, which in general have a wide velocity spread when multiple targets are detected.","PeriodicalId":342532,"journal":{"name":"2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122165949","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：