摘要
由于多种因素的影响,PTZ(pan-tilt-zoom)相机经过长时间运行后其参数会偏离真实值,因此有必要对相机参数进行修正。针对现有算法参数修正精度低、适应能力弱等问题,提出了一种改进的基于参数重估计和分层匹配的参数修正算法。算法通过引入参数重估计策略,避免了参数修正过程中的误差累积,提高了参数修正的精度;通过设计分层匹配和特征传播步骤,增强了算法对不同尺度图像的适应性。实际场景中的多组实验结果表明,本文算法可以准确修正PTZ相机参数,并且较现有方法更具优越性。
Most modern surveillance systems make use of pan-tilt-zoom （PTZ） cameras. However, due to the influence of many factors,the （pan and tilt） coordinates reported by the PTZ cameras become inac- curate after many hours of operation. As the existing parameter correction method is not adaptable e- nough for large scale images and provides results with low accuracy, a parameter correction algorithm based on parameter refinement strategy and hierarchical feature matching is presented in this paper. In the offline stage,the parameter refinement strategy is introduced to compute the pose angle of each 3D point in the surveillance scene, which can effectively improve the accuracy of parameter correction. In the online stage, a hierarchical matching and correspondence propagation method is designed to generate pairwise correspondence between observed image and pose angle set, which can effectively improve the a- daptive capacity of parameter correction algorithm for different scale images. Experimental results dem- onstrate that the proposed method can accurately correct the parameters of the PTZ camera, and it has better accuracy compared with the classical method.
出处
《光电子．激光》
EI
CAS
CSCD
北大核心
2015年第10期1997-2007,共11页
Journal of Optoelectronics·Laser
基金
国家自然科学基金(61021063
61225008)资助项目
关键词
PTZ相机
参数修正
参数重估计
分层匹配
特征传播
（pan-tilt-zoom） PTZ camera
parameter correctiom parameter refinement strategy
hierar-chical feature matching
correspondence propagation
