PROJECT TITLE :

Camera calibration and Pose Estimation from planes

ABSTRACT:

Camera calibration plays a key role in each computer vision application dealing with the problems of recovering a camera's geometry with respect to a 3D world reference, creating 3D measurement in a captured scene or extracting 3D information from observed objects. These problems emerge in various applications such as structure from motion, robotics, augmented reality, 3D object recognition, and Simultaneous Localization And Mapping (SLAM). Employing a camera as a measuring device is becoming an vital trend [one], and as a consequence the requirement for calibrating this instrument additionally becomes of prime importance. Cameras are, by nature, projective devices that map our 3D world onto a 2D image. Their prime use is to create representations (i.e., pictures) of an environment and its actors as pictured from a explicit viewpoint at an explicit moment in time. Extracting 3D knowledge from such devices is thus inherently tough. The camera measures the intensity of the light emitted or reflected from a sure direction; but, the depth data is lost. The projective method also implies that, in the absence of any external reference, the dimensions of the observed objects is undeterminable; that's an object of a given size at a given camera distance will produce the same image as an object of twice the dimensions seen at twice the distance. In spite of those limitations, with a sensible understanding of the camera geometry, 3D Reconstruction can become potential below specific circumstances. In this text, we have a tendency to review some techniques proposed in the literature to parameterize camera metric information, conjointly called camera calibration techniques. We have a tendency to additionally illustrate the utilization of calibrated cameras by describing 2 application examples involving camera pose estimation and distance estimation.