2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT) · 2020 · 16 citations · 11 references
ComputingComputer ScienceCybersecurityComputer SecurityMachine LearningSecurity ArchitectureDigital SurveillanceObject RecognitionSurveillance ApplicationsBlockchain CryptographyFacial Recognition SurveillanceMachine Learning Detection ModelsMachine Learning SurveillanceNational Security SurveillanceReal-time SurveillanceSurveillance In Blockchain TransactionsSurveillance Infrastructure
National security is a top priority to mitigate intrusions and criminal acts. Governments require robust national surveillance system that can cover all geographical areas, including the blind spots that may hold violence and criminal incidents' triggers i.e. malls, stadiums, airports, and other key sites. Integrating existing surveillance infrastructures rather than creating centralized solutions will have great potential on scalability as well as providing more liberal framework that is not run by a single point of control. However, this definitely requires establishing secure communication and mutual trust amongst these entities, which is a real challenge. Towards this end, we propose an efficient smart surveillance architecture that combines machine learning and Blockchain technologies to facilitate the exchange of relevant surveillance events as admitted transactions into a permissioned Hyperledger fabric Blockchain. We conducted comprehensive analysis to demonstrate the feasibility of blockchain and the efficiency of the machine learning-based face recognition and matching for real-time surveillance of suspects using heterogeneous surveillance infrastructure. The proposed architecture proved scalability and real-time behavior after putting the system through multiple test cases. With very high matching accuracy, and end-to-end latency of less than 12.8 seconds, the system proves to be scalable, and fast enough for a smart surveillance use case.
11
Rapid object detection using a boosted cascade of simple features
Paul Viola, Michael Jones · 2005 · 18.2K citations
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke et al. · 2017 · 12.6K citations · Full text
FaceNet: A unified embedding for face recognition and clustering
2015 · 11.2K citations · Full text
Omkar Parkhi, Andrea Vedaldi, Andrew Zisserman · 2015 · 5.1K citations · Full text
Blockchain application and outlook in the banking industry
Ye Guo, Liang Chen · Financial Innovation · 2016 · 958 citations · Full text
Law, Finance, Bank Regulation +15