Real-Time Detection of Motorcyclist without Helmet using Cascade of CNNs on Edge-device

Singh, Dinesh and Vishnu, C. and Mohan, C. Krishna (2020) Real-Time Detection of Motorcyclist without Helmet using Cascade of CNNs on Edge-device. In: 23rd IEEE International Conference on Intelligent Transportation Systems, ITSC 2020, 20-23 September 2020, Rhodes.

[img] Text
2020_IEEE_23rd_International Conference.pdf - Published Version
Available under License Creative Commons Attribution.

Download (3MB)

Abstract

The real-time detection of traffic rule violators in a city-wide surveillance network is a highly desirable but challenging task because it needs to perform computationally complex analytics on the live video streams from large number of cameras, simultaneously. In this paper, we propose an efficient framework using edge computing to deploy a system for automatic detection of bike-riders without helmet. First, we propose a novel robust and compact method for the detection of the motorcyclists without helmet using convolutional neural networks (CNNs). Then, we scale it for the real-time performance on an edge-device by dropping redundant filters and quantizing the model weights. To reduce the network latency, we place the detector module on edge-devices in the cameras. The edge-nodes send their detected alerts to a central alert database where the end users access these alerts through a web interface. To evaluate the proposed method, we collected two datasets of real traffic videos, namely, IITH-Helmet-1 which contains sparse traffic and IITH-Helmet-2 which contains dense traffic. The experimental results show that our method achieves a high detection accuracy of˜95% while maintaining the real-time processing speed of ˜22fps on NVIDIA-TXI. © 2020 IEEE.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Mohan, C. Krishnahttps://orcid.org/0000-0002-7316-0836
Item Type: Conference or Workshop Item (Paper)
Additional Information: This work has been conducted as the part of SATREPS project entitled on “ Smart Cities For Emerging Countries Based on Sensing, Network, and Big Data Analysis of Multimodal Regional Transport System” funded by JST and JICA.
Uncontrolled Keywords: Cameras; Convolutional neural networks; Intelligent systems; Intelligent vehicle highway systems; Scales (weighing instruments); Security systems; Signal detection
Subjects: Computer science
Others > Transportation Science Technology
Divisions: Department of Computer Science & Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 23 Nov 2022 09:11
Last Modified: 23 Nov 2022 09:11
URI: http://raiithold.iith.ac.in/id/eprint/11312
Publisher URL: https://doi.org/10.1109/ITSC45102.2020.9294747
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 11312 Statistics for this ePrint Item