Pub Date : 2020-12-01DOI: 10.1109/CSCI51800.2020.00238
Ryuki Douhara, Ying-Feng Hsu, T. Yoshihisa, Kazuhiro Matsuda, Morito Matsuoka
Edge computing has been attracting attention due to the spread of the Internet of Things. For edge computing, containerized applications are deployed on multiple machines, and Kubernetes is an essential platform for container orchestration. In this paper, we introduce a Kubernetes based power consumption centric workload allocation optimizer (WAO), including scheduler and load balancer. By using WAO built with power consumption and response time models for actual edge computing system, 9.9% power consumption was reduced compared to original Kubernetes load balancer. This result indicates that the WAO developed in this study exhibits promising potential for task allocation modules as a micro service platform.
{"title":"Kubernetes-based Workload Allocation Optimizer for Minimizing Power Consumption of Computing System with Neural Network","authors":"Ryuki Douhara, Ying-Feng Hsu, T. Yoshihisa, Kazuhiro Matsuda, Morito Matsuoka","doi":"10.1109/CSCI51800.2020.00238","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00238","url":null,"abstract":"Edge computing has been attracting attention due to the spread of the Internet of Things. For edge computing, containerized applications are deployed on multiple machines, and Kubernetes is an essential platform for container orchestration. In this paper, we introduce a Kubernetes based power consumption centric workload allocation optimizer (WAO), including scheduler and load balancer. By using WAO built with power consumption and response time models for actual edge computing system, 9.9% power consumption was reduced compared to original Kubernetes load balancer. This result indicates that the WAO developed in this study exhibits promising potential for task allocation modules as a micro service platform.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115447345","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00070
Matthew Meli, E. Gatt, O. Casha, I. Grech, J. Micallef
This paper presents a low cost LoRa-based IoT big data capture and analysis system for indoor air quality monitoring. This system is presented as an alternative solution to expensive and bulky indoor air quality monitors. It enables multiple low cost nodes to be distributed within a building such that extensive location-based indoor air quality data is generated. This data is captured by a gateway and forwarded to a cloud-based LoRaWAN network which in turn publishes the received data via MQTT. A cloud-based data forwarding server is used to capture, format and store this big data on a cloud-based document-oriented database. Cloud-based services are used for data visualization and analysis. Periodic indoor air quality graphs along with air quality index and thermal comfort index heat maps are generated.
{"title":"A Low Cost LoRa-based IoT Big Data Capture and Analysis System for Indoor Air Quality Monitoring","authors":"Matthew Meli, E. Gatt, O. Casha, I. Grech, J. Micallef","doi":"10.1109/CSCI51800.2020.00070","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00070","url":null,"abstract":"This paper presents a low cost LoRa-based IoT big data capture and analysis system for indoor air quality monitoring. This system is presented as an alternative solution to expensive and bulky indoor air quality monitors. It enables multiple low cost nodes to be distributed within a building such that extensive location-based indoor air quality data is generated. This data is captured by a gateway and forwarded to a cloud-based LoRaWAN network which in turn publishes the received data via MQTT. A cloud-based data forwarding server is used to capture, format and store this big data on a cloud-based document-oriented database. Cloud-based services are used for data visualization and analysis. Periodic indoor air quality graphs along with air quality index and thermal comfort index heat maps are generated.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115502961","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00157
M. Park, Seong‐Tae Kim
The COVID-19 pandemic has caused unprecedented impacts along with an enormous number of confirmed cases and deaths in the U.S. This study aims to identify hidden clusters among counties in North Carolina using the COVID-19 data. Since individual states implement their own policies to cope with the COVID-19 pandemic, our study is limited to a single state, North Carolina. We incorporated two clustering techniques, dynamic time warping and deep learning autoeconder. These clustering techniques identified similar upper-level hierarchical clusters separating three metropolitan areas and other regions with slightly different sub-clusters in the county-wise COVID-19 data. Our findings further understanding of county-wise COVID-19 dynamics and its implication.
{"title":"Clustering County-Wise COVID-19 Dynamics in North Carolina","authors":"M. Park, Seong‐Tae Kim","doi":"10.1109/CSCI51800.2020.00157","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00157","url":null,"abstract":"The COVID-19 pandemic has caused unprecedented impacts along with an enormous number of confirmed cases and deaths in the U.S. This study aims to identify hidden clusters among counties in North Carolina using the COVID-19 data. Since individual states implement their own policies to cope with the COVID-19 pandemic, our study is limited to a single state, North Carolina. We incorporated two clustering techniques, dynamic time warping and deep learning autoeconder. These clustering techniques identified similar upper-level hierarchical clusters separating three metropolitan areas and other regions with slightly different sub-clusters in the county-wise COVID-19 data. Our findings further understanding of county-wise COVID-19 dynamics and its implication.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116684554","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00012
D. Esan, P. Owolawi, Chuling Tu
In recent years, surveillance systems have become very important due to security concerns. These systems are widely used in many applications such as airports, railway stations, shopping malls, crowded sports arenas, military etc., [1]. The wide deployment of surveillance systems has made the detection of anomalous behavioral patterns in video streams to become increasingly important. An anomalous event can be considered as a deviation from the regular scene; however, the distribution of normal and anomalous events is severely imbalanced, since the anomalous behavior events do not frequently occur, hence it is imperative to accurately detect anomalous behavioral pattern from a normal pattern in a surveillance system. This paper proposes a Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) technique. The CNN is used to extract the features from the image frames and the LSTM is used as a mechanism for remembrance to make quick and accurate detection. Experiments are done on the University of California San Diego dataset using the proposed anomalous behavioral pattern detection system. Compared with other existing methods, experimental analysis demonstrates that CNN-LSTM technique has high accuracy with better parameters tuning. Different analyses were conducted using the publicly available dataset repository that has been used by many researchers in the field of computer vision in the detection of anomalous behavior. The results obtained show that CNN-LSTM outperforms the others with overall F1-score of 0.94; AUC of 0.891 and accuracy of 89%. This result shows that the deployment of the proposed technique in a surveillance detection system can assist the security personnel to detect an anomalous behavioral pattern in a crowded environment.
{"title":"Anomalous Detection System in Crowded Environment using Deep Learning","authors":"D. Esan, P. Owolawi, Chuling Tu","doi":"10.1109/CSCI51800.2020.00012","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00012","url":null,"abstract":"In recent years, surveillance systems have become very important due to security concerns. These systems are widely used in many applications such as airports, railway stations, shopping malls, crowded sports arenas, military etc., [1]. The wide deployment of surveillance systems has made the detection of anomalous behavioral patterns in video streams to become increasingly important. An anomalous event can be considered as a deviation from the regular scene; however, the distribution of normal and anomalous events is severely imbalanced, since the anomalous behavior events do not frequently occur, hence it is imperative to accurately detect anomalous behavioral pattern from a normal pattern in a surveillance system. This paper proposes a Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) technique. The CNN is used to extract the features from the image frames and the LSTM is used as a mechanism for remembrance to make quick and accurate detection. Experiments are done on the University of California San Diego dataset using the proposed anomalous behavioral pattern detection system. Compared with other existing methods, experimental analysis demonstrates that CNN-LSTM technique has high accuracy with better parameters tuning. Different analyses were conducted using the publicly available dataset repository that has been used by many researchers in the field of computer vision in the detection of anomalous behavior. The results obtained show that CNN-LSTM outperforms the others with overall F1-score of 0.94; AUC of 0.891 and accuracy of 89%. This result shows that the deployment of the proposed technique in a surveillance detection system can assist the security personnel to detect an anomalous behavioral pattern in a crowded environment.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"121 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120851392","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00228
Claudio A. Parra, Travis Yu, Kyu Seon Yum, Arturo Garza, I. Scherson
An in situ rectangular matrix transposition algorithm is presented based on recursively partitioning an original rectangular matrix into a maximum size square matrix and a remaining rectangular sub-matrix. To transpose the maximum size square sub-matrix, a novel cache-friendly, parallel (multithreaded) and scalable in-place square matrix transposition procedure is proposed: it requires a total of Θ(n2/2) simple memory swaps, a single element temporary storage per thread, and does not make use of complex index arithmetic in the main transposition loop. Recursion is used to transpose the remaining rectangular sub-matrix. Dubbed Recursive MaxSquare, the novel proposed rectangular matrix in-place transposition algorithm uses a generalization of the perfect shuffle/unshuffle data permutation to stitch together the recursively transposed square matrices. The shuffle/unshuffle permutations are shown to be efficiently decomposed using basic vector/segment swaps, exchanges and/or cyclic shifts (rotations). A balanced parallel cycles-based transposition is also proposed for comparison.
{"title":"Recursive MaxSquare: Cache-friendly, Parallel, Scalable in situ Rectangular Matrix Transposition","authors":"Claudio A. Parra, Travis Yu, Kyu Seon Yum, Arturo Garza, I. Scherson","doi":"10.1109/CSCI51800.2020.00228","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00228","url":null,"abstract":"An in situ rectangular matrix transposition algorithm is presented based on recursively partitioning an original rectangular matrix into a maximum size square matrix and a remaining rectangular sub-matrix. To transpose the maximum size square sub-matrix, a novel cache-friendly, parallel (multithreaded) and scalable in-place square matrix transposition procedure is proposed: it requires a total of Θ(n2/2) simple memory swaps, a single element temporary storage per thread, and does not make use of complex index arithmetic in the main transposition loop. Recursion is used to transpose the remaining rectangular sub-matrix. Dubbed Recursive MaxSquare, the novel proposed rectangular matrix in-place transposition algorithm uses a generalization of the perfect shuffle/unshuffle data permutation to stitch together the recursively transposed square matrices. The shuffle/unshuffle permutations are shown to be efficiently decomposed using basic vector/segment swaps, exchanges and/or cyclic shifts (rotations). A balanced parallel cycles-based transposition is also proposed for comparison.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"18 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120989253","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00134
Chhayly Lim, Jung-Yeon Kim, Yunyoung Nam
Metabolic syndrome (MetS) is a cluster of metabolic disorders associated with medical conditions: abdominal obesity, high blood pressure, insulin resistance, etc. People with MetS have a higher risk of cardiovascular diseases and type 2 diabetes mellitus. Hence, early detection of MetS can be useful in the field of healthcare. In this paper, we propose a 1D-Convolution Neural Network (1D-CNN) model for classifying the electrocardiogram (ECG) signals of the GBBANet online database into two classes: a group of people with the medical condition (MetS [n=15]) and a control group (CG [n=10]). The dataset consists of 5 ECG recordings per person. The proposed 1D-CNN model has achieved an overall accuracy of 88.32%.
{"title":"ECG Signal Analysis for Patient with Metabolic Syndrome based on 1D-Convolution Neural Network","authors":"Chhayly Lim, Jung-Yeon Kim, Yunyoung Nam","doi":"10.1109/CSCI51800.2020.00134","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00134","url":null,"abstract":"Metabolic syndrome (MetS) is a cluster of metabolic disorders associated with medical conditions: abdominal obesity, high blood pressure, insulin resistance, etc. People with MetS have a higher risk of cardiovascular diseases and type 2 diabetes mellitus. Hence, early detection of MetS can be useful in the field of healthcare. In this paper, we propose a 1D-Convolution Neural Network (1D-CNN) model for classifying the electrocardiogram (ECG) signals of the GBBANet online database into two classes: a group of people with the medical condition (MetS [n=15]) and a control group (CG [n=10]). The dataset consists of 5 ECG recordings per person. The proposed 1D-CNN model has achieved an overall accuracy of 88.32%.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127313750","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00192
M. Tavakolan, Ismaeel A. Faridi
The security risks associated with healthcare Internet of things (HIoT) devices and medical devices includes patient privacy, data confidentiality, and data security. Insecure medical devices allow hackers to infiltrate systems and control medical devices to potentially harm patients and hospitals. HIoT devices have computational and memory limitations, energy limitations, mobility and scalability limitations. Therefore, securing HIoT devices is immensely aggravated due to their resource constrained. Finding a security solution that minimizes resource consumption and thus maximizes security performance is a challenging task in HIoT. This paper proposes adaptive security mechanism that is considering energy level of HIoT devices. This energy-efficient security mechanism considers the residual energy to apply security mechanism and improve lifetime of HIoT devices.
{"title":"Applying an Energy-Aware Security Mechanism in Healthcare Internet of Things","authors":"M. Tavakolan, Ismaeel A. Faridi","doi":"10.1109/CSCI51800.2020.00192","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00192","url":null,"abstract":"The security risks associated with healthcare Internet of things (HIoT) devices and medical devices includes patient privacy, data confidentiality, and data security. Insecure medical devices allow hackers to infiltrate systems and control medical devices to potentially harm patients and hospitals. HIoT devices have computational and memory limitations, energy limitations, mobility and scalability limitations. Therefore, securing HIoT devices is immensely aggravated due to their resource constrained. Finding a security solution that minimizes resource consumption and thus maximizes security performance is a challenging task in HIoT. This paper proposes adaptive security mechanism that is considering energy level of HIoT devices. This energy-efficient security mechanism considers the residual energy to apply security mechanism and improve lifetime of HIoT devices.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124902846","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00241
F. Alqahtani, Salahaldeen Duraibi, Predrag T. Tosic, Frederick T. Sheldon
Data security remains a major concern for organizations considering the use of cloud services to store their confidential, business-critical data. In this paper, we investigate how information flow control can be used in the cloud to enhance the confidence of enterprises, so they can safely and securely adopt cloud solutions for their data storage needs. We discuss how different techniques can be used with the CloudMonitor tool to guarantee the protection of data in the cloud. We then give an overview of how centralized and decentralized information flow control systems operate, and the comparative advantages and disadvantages of each approach. Our analysis suggests that CloudMonitor can achieve better data security with the use of decentralized information flow control. We then discuss different decentralized information flow tracking tools applied to monitoring data in the cloud. CloudMonitor enables the consumers and the providers of cloud services to agree on acceptable security policies as well as their implementation, to ensure secure data storage in the cloud.
{"title":"Information Flow Control to Secure Data in the Cloud","authors":"F. Alqahtani, Salahaldeen Duraibi, Predrag T. Tosic, Frederick T. Sheldon","doi":"10.1109/CSCI51800.2020.00241","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00241","url":null,"abstract":"Data security remains a major concern for organizations considering the use of cloud services to store their confidential, business-critical data. In this paper, we investigate how information flow control can be used in the cloud to enhance the confidence of enterprises, so they can safely and securely adopt cloud solutions for their data storage needs. We discuss how different techniques can be used with the CloudMonitor tool to guarantee the protection of data in the cloud. We then give an overview of how centralized and decentralized information flow control systems operate, and the comparative advantages and disadvantages of each approach. Our analysis suggests that CloudMonitor can achieve better data security with the use of decentralized information flow control. We then discuss different decentralized information flow tracking tools applied to monitoring data in the cloud. CloudMonitor enables the consumers and the providers of cloud services to agree on acceptable security policies as well as their implementation, to ensure secure data storage in the cloud.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125795919","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00191
H. Chamkhia, A. Al-Ali, Amr M. Mohamed, M. Guizani, A. Erbad, A. Refaey
The internet of things (IoT) is becoming part of the infrastructure supporting various services in every day’s life. Due to the complex nature of IoT systems with heterogeneous devices, the needed security and privacy aspects are mostly ignored in the initial system design. One of the proposed solutions to address the security threats from the physical layer perspective is physical-layer security (PLS). We propose the use of 3-D stochastic geometry to accurately model IoT systems in a realistic scenarios, where sensors, access points, and eavesdroppers are randomly located in a 3-D space. We use our model with realistic system deployment parameters to conduct rigorous performance analysis for critical security metrics, such as the successful transmission probability (STP) and the secrecy outage probability (SOP) in different potential IoT scenarios. We finally utilize simulation to validate the theoretical analysis.
{"title":"Performance Analysis of IoT Physical layer Security Using 3-D Stochastic Geometry","authors":"H. Chamkhia, A. Al-Ali, Amr M. Mohamed, M. Guizani, A. Erbad, A. Refaey","doi":"10.1109/CSCI51800.2020.00191","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00191","url":null,"abstract":"The internet of things (IoT) is becoming part of the infrastructure supporting various services in every day’s life. Due to the complex nature of IoT systems with heterogeneous devices, the needed security and privacy aspects are mostly ignored in the initial system design. One of the proposed solutions to address the security threats from the physical layer perspective is physical-layer security (PLS). We propose the use of 3-D stochastic geometry to accurately model IoT systems in a realistic scenarios, where sensors, access points, and eavesdroppers are randomly located in a 3-D space. We use our model with realistic system deployment parameters to conduct rigorous performance analysis for critical security metrics, such as the successful transmission probability (STP) and the secrecy outage probability (SOP) in different potential IoT scenarios. We finally utilize simulation to validate the theoretical analysis.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115103087","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00297
Leonard D. Litvak, L. Deligiannidis
Although there exist many different solutions for securing volumes of space with various kinds of security cameras such as conventional monocular or thermal cameras, using stereo vision has not been attempted as an alternative method. By combining motion detection via image subtraction and range-finding via stereoscopic vision, a single stereo camera can secure a large three-dimensional volume within its field of view. With this, many individual areas can be secured by a single stereo camera placed further away that would otherwise have to be secured by many conventional or thermal cameras placed near areas of interest. Our solution works well for depth-ranges of up to 20 feet. At ranges beyond 20 feet, the disparity map becomes too noisy. Within the 20 feet range, the depth detection is highly accurate with only 0.18% error.
{"title":"Securing Three Dimensional Regions with Stereo Vision","authors":"Leonard D. Litvak, L. Deligiannidis","doi":"10.1109/CSCI51800.2020.00297","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00297","url":null,"abstract":"Although there exist many different solutions for securing volumes of space with various kinds of security cameras such as conventional monocular or thermal cameras, using stereo vision has not been attempted as an alternative method. By combining motion detection via image subtraction and range-finding via stereoscopic vision, a single stereo camera can secure a large three-dimensional volume within its field of view. With this, many individual areas can be secured by a single stereo camera placed further away that would otherwise have to be secured by many conventional or thermal cameras placed near areas of interest. Our solution works well for depth-ranges of up to 20 feet. At ranges beyond 20 feet, the disparity map becomes too noisy. Within the 20 feet range, the depth detection is highly accurate with only 0.18% error.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122931617","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：