Cloud‐based video analytics using convolutional neural networks. (13th September 2018)

• Record Type: Journal Article
• Authors: Yaseen, Muhammad Usman; Anjum, Ashiq; Farid, Mohsen; Antonopoulos, Nick
• Other Names: Somani Gaurav guestEditor.; Zhao Xinghui guestEditor.; Srirama Satish Narayana guestEditor.; Buyya Rajkumar guestEditor.
• Is Part Of: Software, practice & experience. Volume 49:Number 4(2019)
• Page Start: 565
• Page End: 583
• Publication Date: 2018-09-13
• Subjects: cloud computing -- convolutional neural networks -- deep learning -- hyperparameter tuning -- video analytics; Computer software -- Periodicals; Computer programming -- Periodicals; Computer programs -- Periodicals; 005.3
• DOI: 10.1002/spe.2636
• Languages: English
• ISSNs: 0038-0644

Abstract

Summary: Object classification is a vital part of any video analytics system, which could aid in complex applications such as object monitoring and management. Traditional video analytics systems work on shallow networks and are unable to harness the power of distributed processing for training and inference. We propose a cloud‐based video analytics system based on an optimally tuned convolutional neural network to classify objects from video streams. The tuning of convolutional neural network is empowered by in‐memory distributed computing. The object classification is performed by comparing the target object with the prestored trained patterns, generating a set of matching scores. The matching scores greater than an empirically determined threshold reveal the classification of the target object. The proposed system proved to be robust to classification errors with an accuracy and precision of 97% and 96%, respectively, and can be used as a general‐purpose video analytics system.