We present an abandoned mining cave dataset including vision, distance, inertial measurements. The vision measurements were captured by a stereoscopic camera system constituting of two industrial cameras. A LiDAR sensor provided the distance measurements in the form of point clouds, while an IMU provided the inertial data measured by accelerator and gyroscope. All above sensors were rigidly mounted on a mobile tracked vehicle that was capable of moving in the cave. Because the GPS signal cannot be detected in the cave, the position and attitude of the tracked vehicle were not available using high-precision GPS/INS integrated navigation system. Instead, we used a set of base stations to determine 6 Degrees of Freedom (DoF) ground truth poses for the tracked vehicle. The intrinsic and extrinsic of the sensors were calibrated. Time of sensors and processing units were well synchronized with a high-precision hardware to make our dataset more friendly for research of visual/lidar odometry, structure from motion, SLAM, etc. This paper describes the hardware-software platform and the data format in detail.
Vision-LiDAR-Inertial Localization and Mapping Dataset of a Mining Cave
Lect.Notes Computer
International Conference on Intelligent Robotics and Applications ; 2023 ; Hangzhou, China July 05, 2023 - July 07, 2023
2023-10-21
12 pages
Article/Chapter (Book)
Electronic Resource
English
Stereo vision , LiDAR , IMU , Sensors synchronization , Cave Computer Science , Artificial Intelligence , Software Engineering/Programming and Operating Systems , Computer Applications , Computer Communication Networks , Special Purpose and Application-Based Systems , User Interfaces and Human Computer Interaction
Methods for Localization and Mapping Using Vision and Inertial Sensors
British Library Conference Proceedings | 2008
|