一种改进的PSO-MBCV算法的车底阴影分割

系统工程与电子技术

一种改进的PSO-MBCV算法的车底阴影分割

付梦印1，2，靳璐1，2，王美玲1，2，杨毅1，2

（1. 北京理工大学自动化学院，北京 100081；
2. 复杂系统智能控制与决策教育部重点实验室，　北京 100081）

出版日期:2014-07-22 发布日期:2010-01-03

Segmentation of bottom shadow of vehicle based on #br# improved PSO-MBCV algorithm

FU Mengyin1，2， JIN Lu1，2， WANG Meiling1，2， YANG Yi

(1. School of Automation, Beijing Institute of Technology, Beijing 100081, China;
2. Key Laboratory of Intelligent Control and Decision of Complex Systems, 
Ministry of Education，Beijing 100081, China)

Online:2014-07-22 Published:2010-01-03

摘要/Abstract

摘要：

针对当前车底阴影分割算法在复杂环境下鲁棒性较差以及最大类间方差（maximum betweenclass variance，　MBCV）多阈值分割算法不能自动确定阈值个数的问题，提出利用峰值自适应方法自动确定MBCV多阈值分割算法中阈值个数；然后，以阈值的个数为粒子群优化算法（particle swarm optimization，　PSO）中粒子的维数，提出了一种改进的PSOMBCV算法的车底阴影分割。实验结果表明，该算法能有较低的误分类误差，能有效地分割出车底阴影。

Abstract:

The current segmentation algorithms of bottom shadow of vehicle have poor robustness, meanwhile, the multilevel thresholds segmentation algorithm of maximum betweenclass variance (MBCV) method does not determine automatically the number of the thresholds. Therefore, firstly, the peak adaptive method based on image histogram is used to determine the number of thresholds; then, the number is considered as the particle dimension of the particle swarm optimization (PSO) algorithm, and the bottom shadow of vehicles based on an improved PSO-MBCV algorithm is proposed. The results show that the misclassification error(ME) can be deduced and the bottom shadow of vehicles can be effectively segmented.

付梦印1，2，靳璐1，2，王美玲1，2，杨毅1，2. 一种改进的PSO-MBCV算法的车底阴影分割[J]. 系统工程与电子技术.

FU Mengyin1，2， JIN Lu1，2， WANG Meiling1，2， YANG Yi. Segmentation of bottom shadow of vehicle based on #br# improved PSO-MBCV algorithm[J]. Systems Engineering and Electronics.