A comparison of an RGB-D cameras performance and a stereo camera in relation to object recognition and spatial position determination

Results of using an RGB-D camera (Kinect sensor) and a stereo camera, separately, in order to determine the 3D real position characteristic points predetermined object scene are presented. KAZE algorithm was used make recognition, that exploits nonlinear scale space through diffusion filtering; coordinates centroid were calculated employing calibration information depth parameter provided by Kinect sensor camera. Experimental results show it is possible get required with both cameras locate robot, although balance distance where placed must be guaranteed: no fewer than 0.8 m from guarantee information, due operating range; 0.5 but not 1 away have suitable rate besides, has more precision measures regarding