多模板优化算法在基于图像的交通肇事现场测距系统中的应用

Multi-templates Optimization Algorithm Applied to Measuring System Based on Images

交通肇事的勘测主要涉及路面两点间距离的测量,因而在路面不平整的情况下,如何确保测量的精度是基于图像的交通肇事现场测距系统所要解决的一个关键技术问题。该文针对这个问题展开了一系列的研究。首先分别给出了单模板算法和多模板优化算法的理论推导;其次对每种算法都做了数值模拟试验,并分析和比较了实验结果。结果表明利用多模板进行优化的算法比单模板算法更加鲁棒。最后还给出了真实图像的实验结果。

Measurement in the traffic accident is mainly concerned with measuring the distance between two points on the road.So,how to insure the accuracy of measurement under the situation that the road isn't level is a key problem in this measuring system.This paper develops a series of research on this problem.First,the single-template algorithm and the multi-templates optimization algorithm are derived.Then,the simulative experiment of each algorithm is given.The analysis and comparison of the results of the experiments are also listed.The results indicate that multi-templates optimization algorithm is more robust than single-template algorithm.At the end,the results of the experiments using true images are displayed.