Object recognition and 3D reconstruction of occluded objects using binocular stereo

Object recognition is one of the key areas in computer vision which comprises of object detection, recognition and reconstruction. The image of the object to be recognized is captured using camera and matched with pre-stored templates of the model object. Recognizing 3D view of the object is difficult in the presence of object occlusion and view-point invariants. This paper focuses on the problem of occlusion and provides a solution for handling self and inter-object occlusion. Self-occlusion has been addressed by the suitable calibration of the cameras and a novel algorithm has been proposed to address inter-object occlusion. A modified geometric mapping technique has been proposed for the 3D reconstruction of the recognized object. Real-time setup has been used to test the proposed solutions to identify objects of multiple shapes and sizes. The results show that the performance of the algorithm was superior and enabled recognition of objects with 80% occlusion or less.