Error Accuracy Estimation of 3D Reconstruction and 3D Camera Pose from RGB-D Data

Abstract

We propose an approach to predict accuracy for three-dimensional reconstruction and camera pose using a generic RGB-D camera on a robotic platform. We initially create a ground truth of 3D points and camera poses using a set of smart markers that we specifically devised and constructed for our approach. Then, we compute actual errors and their accuracy during the motion of our mobile robotic platform. The error modeling is then provided, which is used as input to a deep multi-layer perceptron in order to estimate accuracy as a function of the camera’s distance, velocity, and vibration of the vision system. The network outputs are the root mean squared errors for the 3D reconstruction and the relative pose errors for the camera. Experimental results show that this approach has a prediction accuracy of ±1% for the 3D reconstruction and ±2.5% for camera poses, which shows a better performance in comparison with state-of-the-art methods.