CCD Infrared Image Segmentation Using Watershed Algorithm

In recent years, the watershed line has emerged as a primary tool of mathematical morphology for image segmentation, though the application of watershed algorithms to an image is often disappointing. Based on the mathematical morphology, this paper develops a general purpose watershed segmentation algorithm used for the automatic segmentation in regions of pedestrians of infrared image. The approaches of watershed image segmentation algorithm and key processes are presented. Then the experimental system is established by using the infrared CCD device for pedestrian image detection. The image segmentation results, produced by the developed algorithm in the experiment, show that the watershed method can implement the automatic detection and segmentation for the characteristic information in regions of interest of image.