Research Repository

MAT-CNN-SOPC: Motionless Analysis of Traffic Using Convolutional Neural Networks on System-On-a-Programmable-Chip

Dey, Somdip and Kalliatakis, Grigorios and Saha, Sangeet and Singh, Amit Kumar and Ehsan, Shoaib and McDonald-Maier, Klaus (2018) MAT-CNN-SOPC: Motionless Analysis of Traffic Using Convolutional Neural Networks on System-On-a-Programmable-Chip. In: 2018 NASA/ESA Conference on Adaptive Hardware and Systems (AHS), 2018-08-06 - 2018-08-09, Edinburgh, UK.

[img]
Preview
Text
1807.02098v2.pdf - Accepted Version

Download (1MB) | Preview

Abstract

Intelligent Transportation Systems (ITS) have become an important pillar in modern 'smart city' framework which demands intelligent involvement of machines. Traffic load recognition can be categorized as an important and challenging issue for such systems. Recently, Convolutional Neural Network (CNN) models have drawn considerable amount of interest in many areas such as weather classification, human rights violation detection through images, due to its accurate prediction capabilities. This work tackles real-life traffic load recognition problem on System-On-a-Programmable-Chip (SOPC) platform and coin it as MAT-CNN-SOPC, which uses an intelligent retraining mechanism of the CNN with known environments. The proposed methodology is capable of enhancing the efficacy of the approach by 2.44x in comparison to the state-of-art and proven through experimental analysis. We have also introduced a mathematical equation, which is capable of quantifying the suitability of using different CNN models over the other for a particular application based implementation.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: 2018 NASA/ESA Conference on Adaptive Hardware and Systems (AHS)
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Elements
Date Deposited: 30 Apr 2020 08:09
Last Modified: 30 Apr 2020 08:09
URI: http://repository.essex.ac.uk/id/eprint/27402

Actions (login required)

View Item View Item