YUTO MMS: A comprehensive SLAM dataset for urban mobile mapping with tilted LiDAR and panoramic camera integration

Area of Science:

• Robotics
• Computer Vision
• Geomatics Engineering

Background:

• Mobile Mapping Systems (MMS) are crucial for data acquisition in various applications.
• Simultaneous Localization and Mapping (SLAM) algorithms are essential for autonomous navigation and mapping.
• Existing datasets may not fully capture the complexities of real-world urban environments for MMS and SLAM.

Purpose of the Study:

• To introduce and detail the York University Teledyne Optech (YUTO) Mobile Mapping System (MMS) Dataset.
• To establish a benchmark for evaluating contemporary Simultaneous Localization and Mapping (SLAM) systems.
• To provide a foundational resource for future research in SLAM-integrated mobile mapping.

Main Methods:

• Data collection using a specialized vehicle equipped with LiDAR, panoramic camera, GPS, and IMU.
• Acquisition of 20.1 km of data across four sequences in urban environments (York University Keele Campus and Teledyne Optech headquarters).
• Detailed description of dataset collection procedures, sensor configurations, synchronization, data structure, and format.

Main Results:

• The YUTO MMS dataset comprises comprehensive sensor data suitable for SLAM research.
• Performance evaluation of prevailing SLAM systems using the YUTO MMS dataset is presented.
• A baseline performance is established for SLAM systems on this specific dataset.

Conclusions:

• The YUTO MMS dataset serves as a valuable resource for the research community.
• The benchmark results offer insights into the capabilities and limitations of current SLAM systems.
• This work facilitates advancements in the development and application of SLAM-integrated mobile mapping systems.