DOI

10.5703/1288284317101

Abstract

Indiana Department of Transportation (INDOT) has over 300 digital cameras along highways in populated areas in Indiana. These cameras are used to monitor traffic conditions around the clock, all year round. Currently, the videos from these cameras are observed by human operators. The main objective of this research is to develop an automatic real-time system to monitor traffic conditions using the INDOT CCTV video feeds by a collaborative research team of the Transportation Active Safety Institute (TASI) at Indiana University-Purdue University Indianapolis (IUPUI) and the Traffic Management Center (TMC) of INDOT.

In this project, the research team developed the system architecture based on a detailed system requirement analysis. The first prototype of major system components of the system has been implemented. Specifically, the team has successfully accomplished the following:

  1. An AI based deep learning algorithm provided in YOLO3 is selected for vehicle detection which generates the best results for daytime videos.
  2. The tracking information of moving vehicles is used to derive the locations of roads and lanes.
  3. A database is designed as the center place to gather and distribute the information generated from all camera videos. The database provides all information for the traffic incident detection.
  4. A web-based Graphical User Interface (GUI) was developed.
  5. The automatic traffic incident detection will be implemented after the traffic flow information being derived accurately.

The research team is currently in the process of integrating the prototypes of all components of the system together to establish a complete system prototype.

Report Number

FHWA/IN/JTRP-2019/23

Keywords

traffic incident detection, vehicle classification, deep learning

SPR Number

4305

Performing Organization

Joint Transportation Research Program

Publisher Place

West Lafayette, IN

Date of this Version

2019

Share

COinS