Embedded planar surface segmentation system for stereo images

摘要: An embedded system is developed to segment stereo images using disparity. The recent developments in the architecture have allowed real time implementation of low-level vision tasks such as disparity computation. At same time, an intermediate level task segmentation rarely attempted system. To solve planar surface problem, which iterative nature, our implements a Segmentation–Estimation framework. In phase, labels are assigned based on underlying plane parameters. Connected component analysis carried out result select largest spatially connected area for each plane. From areas, parameters reestimated. This process was implemented TMS320DM642 that operates at 3–5 frames per second size 320 × 240.