| 基于最优阈值和随机标号法的多车辆分割 |
| |
| 引用本文： | 吴忻生,邓军,戚其丰.基于最优阈值和随机标号法的多车辆分割[J].公路交通科技,2011,28(3):125-132. |
| |
| 作者姓名： | 吴忻生 邓军 戚其丰 |
| |
| 作者单位： | 吴忻生,戚其丰,WU Xinsheng,QI Qifeng(华南理工大学精密电子制造装备教育部工程研究中心,广东广州,510640);邓军,DENG Jun(华南理工大学,自动化科学与工程学院,广东广州510640) |
| |
| 基金项目： | 国家自然科学基金资助项目，华南理工大学中央高校基本科研业务费资助项目 |
| |
| 摘 要： | 以选择性背景更新为基础,提出由相似度决定更新速度的新方法.综合颜色差异、连通性和车辆占空比等属性建立分割双阚值的能量函数,并利用模拟退火算法求取全局最优阚值.用最优分割双阚值对车辆图像进行阚值粗分割,再以条件随机域工具整合视频空间中的时间和空间信息建立随机标号域模型,并计算最大后验概率确定粗分割中各像素点的标号(细分割...
|
| 关 键 词： | 交通工程 最优阈值和随机标号法 能量函数 多车辆分割 色彩空间变换 自适应背景更新 最大后验概率 |
Multi-vehicle Segmentation Based on Optimal Threshold and Random Labeling |
| |
| WU Xinsheng,DENG Jun,QI Qifeng.Multi-vehicle Segmentation Based on Optimal Threshold and Random Labeling[J].Journal of Highway and Transportation Research and Development,2011,28(3):125-132. |
| |
| Authors: | WU Xinsheng DENG Jun QI Qifeng |
| |
| Institution: | WU Xinsheng1,DENG Jun2,QI Qifeng1(1.Engineering Research Centre for Precision Electronic Manufacturing Equipment of Ministry of Education,South China University of Technology,Guangzhou Guangdong 510640,China,2.School of Automation Science and Engineering,China) |
| |
| Abstract: | Based on selective background updating,a new updating approach which determining updating speed by similarity was proposed.The energy function for dual-threshold segmentation was constructed based on color difference,connectivity and duty ratio,and the global optimal threshold was determined by simulated annealing algorithm.Coarse segmentation for the vehicle images was performed using optimal dual-threshold,a random label domain model was built by the time and space information in video spaces integrated w... |
| |
| Keywords: | traffic engineering optimal threshold and random labeling energy function muti-vehicle segmentation color space conversion adaptive background refreshing maximum posterior probability |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
