Improved illumination assessment for vision-based traffic monitoring

Vision systems that must operate autonomously over varying environment conditions often must use different parameter values or algorithms depending on these conditions. A key problem is how to automatically assess the incoming imagery to determine these appropriate parameters and algorithms. This paper presents methods for such assessment. Specifically it presents measures for determining whether the scene is well-lit (i.e. whether objects' entire extent is visible, versus just their lights), whether the scene has sufficient contrast, and whether objects are casting shadows. The methods are applied in the domain of traffic monitoring, are based on empirical data, and have been deployed in hundreds of installed traffic monitoring systems. Here, we present data obtained videotape segments covering 34 representative installations. The paper includes performance data and an improved algorithm for determining whether the scene is well-lit.