Research on Indoor 3D SLAM Fusing Color and Depth Information

This book is suited for computer science students and provides valuable knowledge to the intermediate scholars. Simultaneous Localization and Mapping (SLAM) is the basis for mobile robot autonomous navigating in unknown environment. This book introduces SLAM based on RGB-D color information and depth information for indoor unknown environment, which includes RGB-D depth distortion correction, feature detection, feature description and feature association. Without any prior knowledge, a Kinect does 6-DOF motion in indoor scenes and perceives the surrounding environment information, extracting stable feature points of the environment to represent the actual physical point in 3D space which is used as landmarks to create feature-based geometry map of the environment. The VO-EIF SLAM system and the loop closing detection system are conducted. All experimental studies are completed on the ROS platform in the Ubuntu environment. Key highlight areas include: Depth Distortion Correction; feature detection; feature description; RGB-D SLAM; Loop Closing.