Abstract
This paper presents a simple but effective technique to calibrate a PTZ (Pan/Tilt/Zoom) camera by using only two images for five intrinsic parameters: focal length, aspect ratio, the principle point coordinates and the distortion coefficient. In our approach, the SCC-SURF (Shape-Color Combined SURF) descriptor is first employed to obtain robust point correspondences in a pair of color images taken before and after the camera undergoing an arbitrary pan-tilt rotation respectively. Based on the radial lens distortion division model, the point correspondences between these two images are applied to calculate the homography and the distortion coefficient simultaneously. The estimated homography is proved more precise with our novel framework CWRLD (Covariance Weighted Ransac under Lens Distortion), which employs a covariance matrix in the presence of feature location noise. Finally, the remaining four intrinsic parameters are solved using directly decomposing estimated homography with a series of Givens rotations. Both synthetic and real data are provided to verify that our proposed technique is precise, convenient, and applicable for online calibration without regard for a specific imaged environment.
Highlights
Owing to their pan, tilt and zooming abilities, PTZ(Pan/Tilt/ Zoom) cameras, which can observe a larger field of view and act as high-resolution sensors, have a wide range of applications such as object tracking [1], intelligent teaching systems [2],as well as in early detection of building destruction [3]
EXPERIMENTAL RESULTS AND ANALYSIS we present an extensive set of experimental results in two parts, i.e. the proposed homography estimation and the whole PTZ camera calibration
HOMOGRAPH ESTIMATION EXPERIMENT RESULTS In this experiment, we study the effects of the interior point ratio as well as noise level on the homography estimation and compare our homography estimation method derived from CWRLD framework with other related methods
Summary
Tilt and zooming abilities, PTZ(Pan/Tilt/ Zoom) cameras, which can observe a larger field of view and act as high-resolution sensors, have a wide range of applications such as object tracking [1], intelligent teaching systems [2],as well as in early detection of building destruction [3]. In Ziyan Wu’s work, the lens distortion coefficient as well as the intrinsic parameters (i.e., focal length, aspect ratio, and principal point coordinates) are proceeded in several steps on ten images Another camera self-calibration and automatic radial Distortion correction method is proposed by Zheng Tang et al [26], but this approach need walking humans as calibration targets and depends on reliable human body segmentation to robust track object. We proposed a new descriptor—SCC-SURF(Shape-Color Combined SURF) for more robust and fast point matching All of these creative works guarantee our proposed scheme is precise, convenient, and applicable for online determining the internal parameters of PTZ camera, which is free to rotate and zoom.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
