Linear colour correction for multiple illumination changes and non-overlapping cameras

Many image processing methods, such as techniques for people re-identification, assume photometric constancy between different images. This paper addresses the correction of photometric variations based upon changes in background areas to correct foreground areas. We assume a multiple light source model where all light sources can have different colors and will change over time. In training mode we learn per-location relations between foreground and background color intensities. In correction mode we apply a double linear correction model based on learned relations. This double linear correction includes a dynamic local illumination correction mapping as well as an inter-camera mapping. We evaluate our illumination correction by computing the similarity between two images based on the Earth Mover’s Distance. We compare the results to a representative auto-exposure (AE) algorithm found in the recent literature plus a color correction one based on the inverseintensity chromaticity. Especially in complex scenarios our method outperforms these state-of-the-art algorithms