Complex urban dataset with multi-level sensors from highly diverse urban environments

Abstract

The high diversity of urban environments, at both the inter and intra levels, poses challenges for robotics research. Such challenges include discrepancies in urban features between cities and the deterioration of sensor measurements within a city. With such diversity in consideration, this paper aims to provide Light Detection and Ranging (LiDAR) and image data acquired in complex urban environments. In contrast to existing datasets, the presented dataset encapsulates various complex urban features and addresses the major issues of complex urban areas, such as unreliable and sporadic Global Positioning System (GPS) data, multi-lane roads, complex building structures, and the abundance of highly dynamic objects. This paper provides two types of LiDAR sensor data (2D and 3D) as well as navigation sensor data with commercial-level accuracy and high-level accuracy. In addition, two levels of sensor data are provided for the purpose of assisting in the complete validation of algorithms using consumer-grade sensors. A forward-facing stereo camera was utilized to capture visual images of the environment and the position information of the vehicle that was estimated through simultaneous localization mapping (SLAM) are offered as a baseline. This paper presents 3D map data generated by the SLAM algorithm in the LASer (LAS) format for a wide array of research purposes, and a file player and a data viewer have been made available via the Github webpage to allow researchers to conveniently utilize the data in a Robot Operating System (ROS) environment. The provided file player is capable of sequentially publishing large quantities of data, similar to the rosbag player. The dataset in its entirety can be found at http://irap.kaist.ac.kr/dataset.

Drivers’ Visual Perception Quantification Using 3D Mobile Sensor Data for Road Safety

“…We investigated why the six groups occur in this area. By obtaining and investigating road-view panoramic images from Naver maps [ 32 ], we identified road shapes and features that affect the VPD of a driver at observation positions in Pangyo. Accordingly, we identified features such as the tree density, building layout, open space, construction of new buildings, overpasses, and moving objects on roads in Figure 12 .…”

“…In this paper, the proposed visual perception model was applied to mobile laser-scanned data from Pangyo [ 32 ] to evaluate traffic safety in the city. Figure 7 a shows an aerial view of the Pangyo area and Figure 7 b shows the collected point cloud of the same area.…”

“… Aerial view of the test site in Pangyo, South Korea. ( a ) Aerial view (Naver Maps [ 33 ]), ( b ) Collected point cloud data [ 32 ]. …”

“… Top view of the test site in Pangyo, South Korea. ( a ) Collected point cloud data [ 32 ], ( b ) Distribution of observation positions. …”

PanoraMIS: An ultra-wide field of view image dataset for vision-based robot-motion estimation

“…In all cases, car-borne cameras have been installed on the roof or inside the cockpit. For instance, the (Pandey et al, 2011) Omnidirectional multi-camera Car Outdoors, Yes 3D/2D LiDAR, IMU, GPS 2 sequences, '10 km AMUSE (Koschorrek et al, 2013) Omnidirectional multi-camera Car Outdoors, No IMU, GPS, height sensors 7 sequences, 24.4 km KITTI (Geiger et al, 2013 (Maddern et al, 2017) Fisheye, trinocular stereo Car Outdoors, Yes 3D/2D LiDAR, IMU, GPS 1010 km Complex Urban (Jeong et al, 2019) Stereo Car Outdoors, Yes 3D/2D LiDAR, IMU, GPS, 3-axis optic gyroscope 19 sequences, 191 km New College (Smith et al, 2009) Omnidirectional multi-camera, stereo…”