| 基于形态图的UVMS水下三维目标识别 |
| |
| 引用本文： | 公丕亮,张奇峰,张艾群,李一平. 基于形态图的UVMS水下三维目标识别[J]. 机械设计与制造, 2011, 0(3) |
| |
| 作者姓名： | 公丕亮 张奇峰 张艾群 李一平 |
| |
| 作者单位： | 1. 中国科学院,沈阳自动化研究所,机器人学国家重点实验室,沈阳,110016;中国科学院,研究生院,北京,100049
2. 中国科学院,沈阳自动化研究所,机器人学国家重点实验室,沈阳,110016 |
| |
| 基金项目： | 国家"863"资助项目 |
| |
| 摘 要： | 水下机器人-机械手系统(UVMS)在对水下目标进行自主或半自主作业时,首要及关键的一步是进行目标识别.由于水下环境的特殊性,水下视距很小,光学成像具有噪声大、对比度差等特点;上述因素使得基于局部特征的目标识别对尺度、旋转、光线等变化的敏感度大大增加.借助立体视觉及航向传感器信息,利用水下三维目标的变尺度形态图方法可靠地实现了水下目标识别,并通过实验对该方法进行了验证.
|
| 关 键 词： | 水下机器人-机械手系统 形态图 立体视觉 目标识别 |
Aspect graph based underwater 3D target recognition for UVMS |
| |
| GONG Pi-liang,ZHANG Qi-feng,ZHANG Ai-qun,LI Yi-ping. Aspect graph based underwater 3D target recognition for UVMS[J]. Machinery Design & Manufacture, 2011, 0(3) |
| |
| Authors: | GONG Pi-liang ZHANG Qi-feng ZHANG Ai-qun LI Yi-ping |
| |
| Affiliation: | GONG Pi-liang1,2,ZHANG Qi-feng1,ZHANG Ai-qun1,LI Yi-ping1,2(1State Key Laboratory of Robotics,Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China)(2Graduate University of Chinese Academy of Sciences,Beijing 100049,China) |
| |
| Abstract: | For a UVMS,it is a prime and critical step to recognize the target while conducting autonomouse or semi-autonomous operations.Due to the particularity of underwater imaging,the visibility is quite limited and the images usually have much noise and low contrast.Such factors increases the sensitivity of the recognition based upon local features,to scale,rotation or illumination.With stereo measurement and heading information,a scalable aspect graph method is used to enhance the reliability of underwater targe... |
| |
| Keywords: | Underwater vehicle-manipulator system Aspect graph Stereo vision Target recognition |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
