全方位高速瓜果图像采集系统的研究  

Multidirectional high speed imaging system for fruit sorting

作　　者：郭峰[1] 曹其新[1] 周金良[1] 朱伟华[1] 

机构地区：[1]上海交通大学机器人研究所,上海200030

出　　处：《农业工程学报》2004年第2期148-151,共4页Transactions of the Chinese Society of Agricultural Engineering

基　　金：上海市科技兴农重点攻关项目(农科攻字(2001)第2-1号)

摘　　要：快速可靠的图像采集系统是实现对瓜果进行准确分拣的基础。介绍了一种全方位高速瓜果图像采集系统。该系统实现了果实多个表面图像的同步采集,采用多线程程序结构提高图像采集速度,采用单场提取模式提高图像质量。利用开发的智能瓜果精选分级试验样机对图像采集系统的性能进行了试验,试验结果证明获得的图像质量和采集速度可以满足实时瓜果分级系统的需要。High-speed and reliable imaging system is the foundation to realize correct fruit sorting. This paper introduces a multidirectional high-speed fruit imaging system, which can realize synchronic acquisition of multidirectional images of fruit surface. Multi-threads program structure is adopted to improve grabbing speed; single field grabbing mode is adopted to improve image quality. The performance of imaging system is tested with the developed intelligent fruit sorting experimental prototype, and the experiment result shows image quality and imaging speed can satisfy the requirements of real-time fruit sorting system.

关 键 词：全方位图像采集系统 瓜果分拣 机器视觉 单场提取 

分 类 号：TP274.3[自动化与计算机技术—检测技术与自动化装置]