Direct Iterative Closest Point for real-time visual odometry

In RGB-D sensor based visual odometry the goal is to estimate a sequence of camera movements using image and/or range measurements. Direct methods solve the problem by minimizing intensity error. In this work a depth map obtained from a RGB-D sensor is considered as a new measurement which is combined with a direct photometric cost function. The minimization of the bi-objective cost function produces 3D camera motion parameters which registers two 3D surfaces within a same coordinate system. The given formulation does not require any predetermined temporal correspondencies nor feature extraction when having a sufficient frame rate. It is shown how incorporating the depth measurement robustifies the cost function in case of insufficient texture information and non-Lambertian surfaces. Finally the method is demonstrated in the Planetary Robotics Vision Ground Processing (PRoVisG) competition where visual odometry and 3D reconstruction results are solved for a stereo image sequence captured using a Mars rover.