{"title":"LifeCount: A Device-free CSI-based Human Counting Solution for Emergency Building Evacuations","authors":"Daniel Konings, F. Alam","doi":"10.1109/SAS48726.2020.9220032","DOIUrl":"https://doi.org/10.1109/SAS48726.2020.9220032","url":null,"abstract":"During large scale building evacuations, it is difficult to ascertain how many people have left the premises safely. To assist in the rescue effort, indoor counting solutions can provide emergency personnel with the number of people who have evacuated the building, and from which floors. LifeCount implements a novel two stage neural network-based algorithm to accurately count the number of people passing through a hallway. Experimental results show that LifeCount can attain a zero counting error accuracy of 96.9%.","PeriodicalId":223737,"journal":{"name":"2020 IEEE Sensors Applications Symposium (SAS)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127308855","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}
{"title":"Design of Cyanobyte: An Intermediate Representation to Standardize Digital Peripheral Datasheets for Automatic Code Generation","authors":"Nick Felker","doi":"10.1109/SAS48726.2020.9220074","DOIUrl":"https://doi.org/10.1109/SAS48726.2020.9220074","url":null,"abstract":"This is a design for a static configuration representing the registers and functions of a hardware peripheral. This allows for datasheet content to be processed directly in a machine-readable format. This can be used to generate drivers for the peripheral on any variety of hardware and software platforms without manual work in building every driver.","PeriodicalId":223737,"journal":{"name":"2020 IEEE Sensors Applications Symposium (SAS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128634114","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}
P. Ferrari, E. Sisinni, D. F. Carvalho, A. Depari, G. Signoretti, M. Silva, I. Silva, D. Silva
{"title":"On the use of LoRaWAN for the Internet of Intelligent Vehicles in Smart City scenarios","authors":"P. Ferrari, E. Sisinni, D. F. Carvalho, A. Depari, G. Signoretti, M. Silva, I. Silva, D. Silva","doi":"10.1109/SAS48726.2020.9220069","DOIUrl":"https://doi.org/10.1109/SAS48726.2020.9220069","url":null,"abstract":"Automotive world is changing with the introduction of Intelligent Vehicles. Today, an increasing number of vehicles may send data to the Internet, helping car manufacturer to implement the Industry 4.0 paradigm. The collected data during the lifetime of the vehicles can be used to improve both product and production facilities. Moreover, the availability of additional data coming from onboard sensors could be used to obtain information about the environment surrounding the vehicle. The Smart City scenario includes an extraordinary number of new sensors (in urban area) and vehicles can be thought as additional mobile sensors. This paper describes the prototype of a Vehicle-to-Cloud interface with OBD-II (On Board Diagnostic) communication, 3G/4G connectivity, and LoRaWAN [used as backup channel]. LoRaWAN infrastructures are largely diffused in Smart Cities and they can provide a suitable alternative to cover some areas when 3G/4G fails. Last, considering the Smart City scenarios, this paper discusses the application constrains and design directions to achieve a correct integration between LoRaWAN infrastructure and the Internet of Intelligent Vehicles.","PeriodicalId":223737,"journal":{"name":"2020 IEEE Sensors Applications Symposium (SAS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126484152","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}
Xiaying Wang, L. Cavigelli, M. Eggimann, M. Magno, L. Benini
{"title":"HR-SAR-Net: A Deep Neural Network for Urban Scene Segmentation from High-Resolution SAR Data","authors":"Xiaying Wang, L. Cavigelli, M. Eggimann, M. Magno, L. Benini","doi":"10.1109/SAS48726.2020.9220068","DOIUrl":"https://doi.org/10.1109/SAS48726.2020.9220068","url":null,"abstract":"Synthetic aperture radar (SAR) data is becoming increasingly available to a wide range of users through commercial service providers with resolutions reaching 0.5 m/px. Segmenting SAR data still requires skilled personnel, limiting the potential for large-scale use. We show that it is possible to automatically and reliably perform urban scene segmentation from next-gen resolution SAR data (0.15 m/px) using deep neural networks (DNNs), achieving a pixel accuracy of 95.19% and a mean intersection-over-union (mIoU) of 74.67% with data collected over a region of merely 2.2km2. The presented DNN is not only effective, but is very small with only 63k parameters and computationally simple enough to achieve a throughput of around 500 Mpx/s using a single GPU. We further identify that additional SAR receive antennas and data from multiple flights massively improve the segmentation accuracy. We describe a procedure for generating a high-quality segmentation ground truth from multiple inaccurate building and road annotations, which has been crucial to achieving these segmentation results.","PeriodicalId":223737,"journal":{"name":"2020 IEEE Sensors Applications Symposium (SAS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122297182","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}