计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (22): 160-163.

• 图形、图像、模式识别 • 上一篇    下一篇

模拟退火粒子群优化双目立体测量方法

芮 挺,马光彦,廖 明,甄树新   

  1. 解放军理工大学 工程兵工程学院,南京 210007
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-08-01 发布日期:2011-08-01

Binocular three-dimensional measurement based on simulated annealing Particle Swarm Optimization

RUI Ting,MA Guangyan,LIAO Ming,ZHEN Shuxin   

  1. Engineering Institute of Engineering Corps,PLA University of Science & Technology,Nanjing 210007,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-08-01 Published:2011-08-01

摘要: 摄像机标定和三维信息恢复是实现双目立体测量的关键问题。提出了利用模拟退火粒子群优化算法在解空间的搜索能力,求解摄像机标定模型和三维信息恢复模型两个超定方程的方法,讨论了目标函数的建立方式及算法实现步骤。通过实验,分析了该方法求解的绝对误差与相对误差,实验证实了算法的有效性。

关键词: 非线性模型, 摄像机标定, 三维信息恢复, 模拟退火粒子群优化

Abstract: Camera calibration and three-dimensional information recovery are key issues of binocular three-dimensional measurement.The simulated annealing particle swarm optimization algorithm is used to get the solution of tow overdetermined equations which are camera calibration model and three-dimensional information recovery model is proposed.The method to establish objective function and algorithm steps is discussed in this paper.Experimental results demonstrate the accuracy of the proposed algorithm both in absolute error and relative error.

Key words: nonlinear model, camera calibration, three-dimensional information recovery, simulated annealing particle swarm optimization