Traffic surveillance video summarization for detecting traffic rules violators using R-CNN

Veena Mayya, Aparna Nayak

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Many a times violating traffic rules leads to accidents. Many countries have adopted systems involving surveillance cameras at accident zones. Monitoring each frame to detect the violators is unrealistic. Automation of this process is highly desirable for reliable and robust monitoring of traffic rules violations. With deep learning techniques on GPU, the violation detection can be automated and performed in real time on surveillance video. This paper proposes a novel technique to summarize the traffic surveillance videos that uses Faster Regions with Convolutions Neural Networks(R-CNN) to automatically detect violators. As the proof of concept, an attempt is made to implement the proposed method to detect the two-wheeler riders without helmet. Long duration videos can be summarized into very short video that includes details about only rules violators.

Original languageEnglish
Title of host publicationAdvances in Computer Communication and Computational Sciences - Proceedings of IC4S 2017
EditorsSanjiv K. Bhatia, Shailesh Tiwari, Munesh C. Trivedi, Krishn K. Mishra
PublisherSpringer Verlag
Pages117-126
Number of pages10
ISBN (Print)9789811303401
DOIs
Publication statusPublished - 01-01-2019
EventInternational Conference on Computer, Communication and Computational Sciences, IC4S 2017 - Kathu, Thailand
Duration: 11-10-201712-10-2017

Publication series

NameAdvances in Intelligent Systems and Computing
Volume759
ISSN (Print)2194-5357

Conference

ConferenceInternational Conference on Computer, Communication and Computational Sciences, IC4S 2017
CountryThailand
CityKathu
Period11-10-1712-10-17

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Traffic surveillance video summarization for detecting traffic rules violators using R-CNN'. Together they form a unique fingerprint.

Cite this