Making the Best Use of Fifty (or More) Shades of Gray: Intelligent Contrast Optimisation for Image Segmentation in False-Colour Video

The problem of automatically segmenting images into different components of interest, and then tracking such components through a sequence of frames in a video, is relevant to many applications of video analysis in Intelligent Environments. Several video capture technologies preprocess the image frames, by adding false-colour, in order to improve the contrast for human viewers. However, such false-colouring can make automatic segmentation and object tracking from such videos much more difficult. In this paper, several intelligent dynamic approaches to these problems are proposed and evaluated, in the context of locating, segmenting and tracking salient regions in an example video dataset.