Calibrating an outdoor distributed camera network using Laser Range Finder data

Abstract

Abstract-Outdoor camera networks are becoming ubiquitous in critical urban areas of large cities around the world. Although current applications of camera networks are mostly limited to video surveillance, recent research projects are exploiting advances on outdoor robotics technology to develop systems that put together networks of cameras and mobile robots in people assisting tasks. Such systems require the creation of robot navigation systems in urban areas with a precise calibration of the distributed camera network. Despite camera calibration has been an extensively studied topic, the calibration (intrinsic and extrinsic) of large outdoor camera networks with no overlapping view fields, and likely to suffer frequent recalibration, poses novel challenges in the development of practical methods for user-assisted calibration that minimize intervention times and maximize precision. In this paper we propose the utilization of Laser Range Finder (LRF) data covering the area of the camera network to support the calibration process and develop a semi-automated methodology allowing quick and precise calibration of large camera networks. The proposed methods have been tested in a real urban environment and have been applied to create direct mappings (homographies) between image coordinates and world points in the ground plane (walking areas) to support person and robot detection and localization algorithms.

Global calibration of non-overlapping cameras: State of the art

“…The mirrorbased global calibration method is also a less costly approach, more suitable for the visual systems where the distribution of the cameras is relatively sparse but the cameras changes greatly in orientation. The method based on structure from motion is rarely used for industrial measurement due to the lack of scene information support and low precision, but has a wide Large-range measuring device [7], [11][12][13] [8]…”

“…In order to ensure the accuracy of the global calibration, a high-precision measuring device can be adopted [7][8][9][10][11]13,108,109]. The most common large-range measuring devices are theodolites, laser trackers, and laser range finder.…”

“…It is simple to carry out and can achieve high accuracy, but this method will still be subject to certain light effects. Ortega et al [11] presented a method of calibrating an outdoor distributed camera network having small or inexistent overlapping fields of view using LRF data. This method relies on a LRF data acquired and registered along the complete area of the network using SLAM methodologies.…”

Estimation of camera calibration uncertainty using LIDAR data

“…The next experiment consists in the estimation of pose uncertainty for the calibration of the camera network explained in [5]. Calibration results for a subset of 3 are shown in Fig.…”

“…In this work we consider the calibration methodology proposed in [5], that exploits the use of a rich LIDAR range data and images to calibrate a non-overlapped camera network [6], where a coarse calibration is performed manually, followed by fine calibration matching 3D lines to 2D image lines using the DLT-Lines (Direct Linear Transformation) algorithm [7]. The method provides estimates of the camera's projection matrix from the knowledge of 3D points and 2D lines.…”