01099351

Component

https://doi.org/10.3141/2086-04

http://scholar.google.com...asua&publication_year=2008

Vision-based automatic traffic monitoring systems require a calibrated camera to measure the speeds of tracked vehicles. Typically this calibration is done by hand. An automatic technique was developed to calibrate the camera for typical viewpoints on highways using a real-time boosted cascade vehicle detector (BCVD). Image processing is used to estimate the two vanishing points, from which the camera height, focal length, and pan and tilt angles are calculated. The key contribution of the proposed approach is its applicability to a wide variety of environmental conditions. The technique does not rely on background subtraction, nor does it require scene-specific features such as pavement markings. As a result, it is unaffected by the presence of shadows, adverse weather conditions, headlight reflections, lack of ambient light, or spillover caused by low-mounted cameras. Speed estimation within 10% of ground truth is shown for sequences obtained during daylight, nighttime, and rain, and including shadows and severe occlusion.

01120900

English

pp 30-39

2008

Transportation Research Record: Journal of the Transportation Research Board

9780309125987

Print

Appendices (1) ; Figures; Photos; References (18) ; Tables (3)

Automation; Calibration; Image processing; Traffic speed; Video cameras

Boosted cascade vehicle detectors; Speed cameras

Highways; Operations and Traffic Management; I73: Traffic Control

TRIS, TRB, ATRI

Jan 29 2008 5:31PM

• Determinants of Route Choice and Value of Traveler Information: A Field Experiment
• Distributed Controller Design Approach to Dynamic Speed Limit Control Against Shockwaves on Freeways
• Effectiveness and Acceptance of Adaptive Intelligent Speed Adaptation Systems
• Evaluating Traveler Information Effects on Commercial and Noncommercial Users
• Evaluation of Cell Phone Traffic Data in Minnesota
• Evaluation of Route Guidance Strategies Based on Vehicle–Infrastructure Integration Under Incident Conditions
• Implementing Vehicle–Infrastructure Integration: Real-World Challenges
• Mobility and Commute Disutility Effects of 511 Deployment in Salt Lake City, Utah
• Operation Data for Evaluating Benefits and Costs of Advanced Traffic Management Components
• Real Options to Increase the Value of Intelligent Transportation Systems
• Real-Time Vehicle Classification Using Inductive Loop Signature Data
• Simple Mixed Reality Infrastructure for Experimental Analysis of Route Choice Behavior: Applications of Intelligent Transportation Systems
• Traffic Probe Data Processing for Full-Scale Deployment of Vehicle–Infrastructure Integration
• Vehicle Detection in Far Field of View of Video Sequences
• Wireless Infrastructure-to-Vehicle Communication Technologies to Increase Road Safety Along Motorways