Effective object detection from traffic camera videos

Honghui Shi, Zhichao Liu, Yuchen Fan, Xinchao Wang, Thomas Huang

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

Abstract

The NVIDIA AI City Challenge[1] is a recent effort to materialize the potential benefits of actionable insights in current traffic systems by utilizing both large amount of richly annotated traffic camera video data captured by growing number of cameras, and advanced technologies developed in recent years in image and video recognition and analysis. In this work, we will compare the AI City dataset with other existing vehicle detection datasets, and illustrate the details of the solution of our winning entries to the 1st NVIDIA AI City Challenge. Our code and models are also available at https://github.com/NVIDIAAICITYCHALLENGE/AICity-Team24.

Original languageEnglish (US)
Title of host publication2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-5
Number of pages5
ISBN (Electronic)9781538604342
DOIs
StatePublished - Jun 26 2018
Event2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - San Francisco, United States
Duration: Apr 4 2017Apr 8 2017

Publication series

Name2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - Conference Proceedings

Other

Other2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017
Country/TerritoryUnited States
CitySan Francisco
Period4/4/174/8/17

Keywords

  • Object detection
  • pedestrian detection
  • traffic cameras
  • traffic light detection
  • vehicle detection
  • video analysis

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management
  • Energy Engineering and Power Technology
  • Safety, Risk, Reliability and Quality
  • Urban Studies

Fingerprint

Dive into the research topics of 'Effective object detection from traffic camera videos'. Together they form a unique fingerprint.

Cite this