The research topics in the areas of photogrammetry and computer vision to Model 3D objects from image sequences are significant for many years. This paper proposes rectification of un-calibrated stereo images and real time depth estimation and measurement of objects using Intel compute stick. The proposed system uses a pair of hand held USB camera with unknown focal length to visualize un-calibrated images and thermal camera (Testo 870-1). The proposed system uses sum of absolute difference (SAD) algorithm to match the strongest points feature in the stereo images. The correctly matching points between the montage images must satisfy the epipolar constraints. The algorithm computes the epipolar fundamental matrix and obtains inliers point in order to get a 3D rectified stereo image. Additionally the propose algorithm perform depth estimation to measure real time distance of objects dynamically. The proposed system uses Intel computer stick with windows 8.1, video graphics array (VGA) to high-definition multimedia interface (HDMI) converter, webcam, thermal camera, MATLAB 14a software. The proposed system finds many applications such as fusion of real virtual scenes, robotic vision, traffic scene analysis, motion tracking and object tracking. Thus the proposed system estimate accurate real time distance of object and obtain 3D rectified stereo images.