01622727

Component

Real-time traffic measurement from surveillance camera is a fast-developing field for vision techniques. Decrease in hardware cost and increase in application of camera and wireless technology have opened a wide application field for the vision techniques in traffic measurement. This paper presents a wireless real-time traffic measuring system using surveillance camera for both lane-based and non-lane-based traffic streams. The system includes a new background estimation model for foreground segmentation using traditional background subtraction technique (BGS). The background model comprises of luminance and pollution controlling parameters for addressing illumination variation (sudden and gradual) and tail backs from vehicles respectively. Foreground segmentation uses a new heuristic dynamic threshold-difference (t-d) function for determining per pixel threshold. It retards the formation of holes and cavities and breaking vehicles into two or more pieces. The shadow is removed considering its physical characteristics by newly presented PNS (Positive Negative Segmentation) technique. Impulse flow waves and aggregated pictorial speed are computed after shadow correction. Impulse flow waves are eventually rectified and cumulated into actual flow. Pictorial speed is converted into actual speed using calibration equation considering perspective error. PARTS (Pixel Based Heterogeneous Traffic Measurement), a user friendly tool which incorporates the whole system, is developed to facilitate traffic measurement. The data extracted at three different locations having different roadway characteristics shows 90% and 98% correlations in measuring flow and speed respectively.

This paper was sponsored by TRB committee ABJ35 Standing Committee on Highway Traffic Monitoring.

01618707

17-00258

English

21p

2017

Transportation Research Board 96th Annual Meeting

Digital/other

Figures; References; Tables

Automatic vehicle detection and identification systems; Image processing; Luminance; Traffic surveillance; Wireless communication systems

Shadows

Data and Information Technology; Highways

Transportation Research Board Annual Meeting 2017 Paper #17-00258

TRIS, TRB, ATRI

Dec 8 2016 9:59AM