Sensor Setup

Yukyung Choi (Sejong Univ.), Namil Kim (NAVER LABS), Soonmin Hwang (Tesla Inc.), Kibeak Park (KAIST), Jae Shin Yoon (Minnesota Univ.), KyungHwan An (ETRI), In So Kweon (KAIST)

Sensor Setup

This page provides additional information about the recording platform and sensor setup we have used to record this dataset. Our recording platform is a Kia Sorento. We use the following sensors:


  • 2× PointGrey Flea3 RGB camera (FL3-GE-13S2C-C), 1.3 Mega-pixels, 1/3” Sony ICX445 CCD, 1280×960, 400∼ 750nm, GigE, Computar Optics 12mm Lens, 26(H) × 22.1(V)
  • 1× FLIR A655Sc thermal camera, ∼50Hz, 14bits data, 640×480, 17um detector pitch, 7.5∼14um, GigE, 25(H) × 19(V) with 24.3mm lens
  • 1× Velodyne HDL-32E 3D LiDAR, 10Hz, 32beams, 0.16 degree angular resolution, 2cm distance accuracy, collecting 0.7 million points/second, field of view: 360horizontal, 41.34vertical, range: ∼70m
  • 1× OXTS RT2002 inertial and GPS navigation system, 6 axis, 100Hz, L1/L2 RTK, resolution: 0.02m/0.1