KAIST Multi-Spectral Day/Night Data Set for Autonomous and Assisted Driving

The authors introduce the KAIST multi-spectral data set, which covers a great range of drivable regions, from urban to residential, for autonomous systems. Their data set provides the different perspectives of the world captured in coarse time slots (day and night), in addition to fine time slots (sunrise, morning, afternoon, sunset, night, and dawn). For all-day perception of autonomous systems, the authors propose the use of a different spectral sensor, i.e., a thermal imaging camera. Toward this goal, they develop a multi-sensor platform, which supports the use of a co-aligned RGB/Thermal camera, RGB stereo, 3-D LiDAR, and inertial sensors (GPS/IMU) and a related calibration technique. They design a wide range of visual perception tasks including the object detection, drivable region detection, localization, image enhancement, depth estimation, and colorization using a single/multi-spectral approach. In this paper, the authors provide a description of their benchmark with the recording platform, data format, development toolkits, and lessons about the progress of capturing data sets.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01664596
  • Record Type: Publication
  • Files: TLIB, TRIS
  • Created Date: Mar 8 2018 3:33PM