Human Detection from RGB Depth Image using Active contour and Grow-cut Segmentation

Computer vision based human detection systems are gaining much significance in modern security and surveillance systems. Recently, advanced camera sensors like Microsoft Kinect came to the scene and such devices are capable of detecting both color and depth details from a captured scene. This article proposes an intelligent human segmentation system by analyzing both color and depth details retrieved by an RGB-Depth camera. Here the depth data is analyzed first, to create an initial segmentation of human factors from the scene. Since depth analysis have restrictions in identifying accurate edge details, post processing steps are used for refurbishing the missed human portions in the frame. The hair regions are first restored first using Chan-vase active contour detection and the subset of foreground pixels thus obtained after this coarse level segmentation are used as seeds to segment the rest of the image frame using Grow-cut segmentation. An iterative cellular automation is employed here to classify the foreground human region. This final segmentation mask thus generated after Grow-cut segmentation can be used for segmenting human region from the original image frame. Experimental results show that the segmentation is helpful for analyzing the human factors in each frame and can be used for further human tracking or activity recognition.