A Taxonomy and Analysis of Camera Calibration Methods for Traffic Monitoring Applications

Many vision-based automatic traffic-monitoring systems require a calibrated camera to compute the speeds and length-based classifications of tracked vehicles. A number of techniques, both manual and automatic, have been proposed for performing such calibration, but no study has yet focused on evaluating the relative strengths of these different alternatives. We present a taxonomy for roadside camera calibration that not only encompasses the existing methods (VVW, VWH, and VWL) but also includes several novel methods (VVH, VVL, VLH, VVD, VWD, and VHD). We also introduce an overconstrained (OC) approach that takes into account all the available measurements, resulting in reduced error and overcoming the inherent ambiguity in single-vanishing-point solutions. This important but oft-neglected ambiguity has not received the attention that it deserves; we analyze it and propose several ways of overcoming it. Our analysis includes the relative tradeoffs between two-vanishing-point solutions, single-vanishing-point solutions, and solutions that require the distance to the road to be known. The various methods are compared using simulations and experiments with real images, showing that methods that use a known length generally outperform the others in terms of error and that the OC method reduces errors even further.

I. Introduction

As the cost of cameras and processors continues to decrease, vision-based sensing is becoming an increasingly popular alternative to traditional sensors for collecting traffic data. A number of both research and commercial systems have shown the promise of gathering information, such as volume, speed, classification, incidents, and turning movements from video. In addition to their cost, vision systems are particularly attractive due to their nonintrusiveness and rich data-gathering ability.