Coordination of SLAM and Artificial Landmark Recognition using 2D/3D Sensors for Mobile Robot Vision

Abstract

Besides the high performance simultaneous localization and mapping algorithm (SLAM) has to build the 3D mapping at the same time and to estimate the pose of the locomotion in real time, the flawlessly mobile robotic application tasks, meanwhile should be able to recognize objects in the environment in order to achieve the variety practical missions. This paper hence presents a coordination between the real-time SLAM and artificial landmark recognition by fusion data from the 2D/3D sensors. The new 3D sensor namely the Photonic Mixer Devices (PMD) purposes real-time capturing the surrounding volume. The 2D high resolution image is registered on the 3D volume subsequently rescaling and calibration both sensors. Visual input from the 2D camera not only delivers high resolution texture data on 3D volume but also use for object recognition. Moreover, the ICP algorithm is taken over the theatrical image registration due to yield the real time data frames registration.