TY - JOUR
T1 - 3D visual perception for self-driving cars using a multi-camera system
T2 - Calibration, mapping, localization, and obstacle detection
AU - Häne, Christian
AU - Heng, Lionel
AU - Lee, Gim Hee
AU - Fraundorfer, Friedrich
AU - Furgale, Paul
AU - Sattler, Torsten
AU - Pollefeys, Marc
PY - 2017/12/1
Y1 - 2017/12/1
N2 - Cameras are a crucial exteroceptive sensor for self-driving cars as they are low-cost and small, provide appearance information about the environment, and work in various weather conditions. They can be used for multiple purposes such as visual navigation and obstacle detection. We can use a surround multi-camera system to cover the full 360-degree field-of-view around the car. In this way, we avoid blind spots which can otherwise lead to accidents. To minimize the number of cameras needed for surround perception, we utilize fisheye cameras. Consequently, standard vision pipelines for 3D mapping, visual localization, obstacle detection, etc. need to be adapted to take full advantage of the availability of multiple cameras rather than treat each camera individually. In addition, processing of fisheye images has to be supported. In this paper, we describe the camera calibration and subsequent processing pipeline for multi-fisheye-camera systems developed as part of the V-Charge project. This project seeks to enable automated valet parking for self-driving cars. Our pipeline is able to precisely calibrate multi-camera systems, build sparse 3D maps for visual navigation, visually localize the car with respect to these maps, generate accurate dense maps, as well as detect obstacles based on real-time depth map extraction.
AB - Cameras are a crucial exteroceptive sensor for self-driving cars as they are low-cost and small, provide appearance information about the environment, and work in various weather conditions. They can be used for multiple purposes such as visual navigation and obstacle detection. We can use a surround multi-camera system to cover the full 360-degree field-of-view around the car. In this way, we avoid blind spots which can otherwise lead to accidents. To minimize the number of cameras needed for surround perception, we utilize fisheye cameras. Consequently, standard vision pipelines for 3D mapping, visual localization, obstacle detection, etc. need to be adapted to take full advantage of the availability of multiple cameras rather than treat each camera individually. In addition, processing of fisheye images has to be supported. In this paper, we describe the camera calibration and subsequent processing pipeline for multi-fisheye-camera systems developed as part of the V-Charge project. This project seeks to enable automated valet parking for self-driving cars. Our pipeline is able to precisely calibrate multi-camera systems, build sparse 3D maps for visual navigation, visually localize the car with respect to these maps, generate accurate dense maps, as well as detect obstacles based on real-time depth map extraction.
KW - Calibration
KW - Fisheye camera
KW - Localization
KW - Mapping
KW - Multi-camera system
KW - Obstacle detection
UR - http://www.scopus.com/inward/record.url?scp=85028449152&partnerID=8YFLogxK
U2 - 10.1016/j.imavis.2017.07.003
DO - 10.1016/j.imavis.2017.07.003
M3 - Article
AN - SCOPUS:85028449152
SN - 0262-8856
VL - 68
SP - 14
EP - 27
JO - Image and Vision Computing
JF - Image and Vision Computing
ER -