Three-dimensional mapping for data collected using variable stereo baseline

The paper describes a system of 3D mapping of data collected with due regard for variable baseline. This solution constitute an extension to a VisRobot sub-system developed as a subsystem necessary for implementing the generic idea of using mobile robots to explore an indoor static environment. This subsystem is to acquire stereo images, calculate the depth in the images and construct the sought 3D map. Stereo images are obtained at various stereo baselines, resulting in enhanced resolution of depth, especially for distant objects. The length of each baseline is obtained by currently measuring the actual location and angular pose of robotic carrier of camera. Measurement errors bring about inaccuracies in depth. Therefore, we propose an innovative procedure that combine the depth maps gained at variable baselines. The paper presents the resulting improved 3D-map visualization in terms of higher precision, considering two cases: static and cumulative localization errors.