Decentralized face recognition scheme for distributed video surveillance in IoT-cloud infrastructure


Muhamad Amin, Anang Hudaya and Ahmad, Nazrul Muhaimin and Mat Ali, Afiq Muzakkir (2016) Decentralized face recognition scheme for distributed video surveillance in IoT-cloud infrastructure. In: 2016 IEEE Region 10 Symposium (TENSYMP). IEEE, pp. 119-124. ISBN 978-1-5090-0931-2

[img] Text
Restricted to Repository staff only

Download (457kB)


People monitoring and tracking activities in surveillance system usually generate massive amount of data from Internet-of-Things (IoT) devices such as cameras. Several issues need to be addressed, including data migration over limited bandwidth and high latency in communication networks. This paper presents an initiative to develop a decentralized face recognition scheme for distributed surveillance system that make use of an integrated framework of Internet-of-Things (IoT) and cloud computing. The decentralized face recognition approach implements a two-stage procedure, including face detection and extraction and face matching. Face detection and extraction are performed on a cloudlet that is located close to the surveillance cameras, hence minimizing the need for massive data transfer to the remote processing center. On the other hand, face matching process is carried out on the face feature vector within a private cloud environment. A case study conducted on the effectiveness of the proposed scheme in detecting “missing” person indicates that the procedure works effectively in the IoT-Cloud infrastructure.

Item Type: Book Section
Uncontrolled Keywords: Cloud computing, Feature extraction, Face, Internet of things, Face recognition, Surveillance, Cameras
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Suzilawati Abu Samah
Date Deposited: 29 Jan 2018 16:12
Last Modified: 29 Jan 2018 16:12


Downloads per month over past year

View ItemEdit (login required)