Face Recognition of Pedestrians from Live Video Stream using Apache Spark Streaming and Kafka
Abhinav Pandey1, Harendra Singh2
1Abhinav Pandey, Department of Computer Science & Engineering, Lakshmi Narain College of Technology Excellence, Bhopal (M.P), India.
2Mr. Harendra Singh, Assistant Professor, Department of Computer Science & Engineering, Lakshmi Narain College of Technology Excellence, Bhopal (M.P), India.
Manuscript received on 8 February 2018 | Revised Manuscript received on 15 February 2018 | Manuscript Published on 28 February 2018 | PP: 4-10 | Volume-7 Issue-5, February 2018 | Retrieval Number: E2488027518/18©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Face recognition of pedestrians by analyzing live video streaming, aims to identify movements and faces by performing image matching with existing images using Apache Spark Streaming, Kafka and OpenCV, on distributed platform and derive decisions. Since video processing and analysis from multiple resources become slow when using Cloud or even any single highly configured machine, hence for making quick decisions and actions, Apache Spark Streaming and Kafka have been used as real time analysis frameworks, which deliver event based decisions making on Hadoop distributed environment. If continuous live events analysis is possible then the decision can make there-after or at the same time. And large amount videos in parallel processing are also not a bottleneck after getting the involvement of Hadoop because base of all real time analysis distributed tools is Hadoop. This event based analysis can be applied at any place where an immediate action is required like monitoring border areas of countries by cameras and drones, road traffic monitoring, life science domain, airlines, logo recognition and where-ever continuous monitoring and decision making involved in large scale data set.
Keywords: Distributed System, Hadoop, Spark, Spark Streaming, Kafka, Open CV.
Scope of the Article: Pattern Recognition and Analysis