| 基于双目立体视觉的番茄识别与定位技术 |
| |
| 引用本文： | 郑小东,赵杰文,刘木华.基于双目立体视觉的番茄识别与定位技术[J].计算机工程,2004,30(22):155-156,171. |
| |
| 作者姓名： | 郑小东 赵杰文 刘木华 |
| |
| 作者单位： | 江苏大学生物与环境工程学院,镇江,212013 |
| |
| 基金项目： | 江苏省教育重点项目“自然光下番茄的识别与定位技术”(01KJB550001) |
| |
| 摘 要： | 根据颜色特征利用阈值自动设定的方法对图像进行分割,自动、快速识别红色番茄;采用形心匹配取代常规的特征点选择和匹配方法,对双目立体成像测距公式进行了修正,经过验证,当工作距离小于500mm时,距离误差可以控制在±10mm以内。
|
| 关 键 词： | 计算机视觉 图像分割 颜色特征 图像识别 番茄识别 定位技术 双目立体视觉 |
| 文章编号： | 1000-3428(2004)22-0155-02 |
Tomatoes Recognition and Location from Nature Background Based on Binocular Stereo Vision |
| |
| ZHENG Xiaodong,ZHAO Jiewen,LIU Muhua.Tomatoes Recognition and Location from Nature Background Based on Binocular Stereo Vision[J].Computer Engineering,2004,30(22):155-156,171. |
| |
| Authors: | ZHENG Xiaodong ZHAO Jiewen LIU Muhua |
| |
| Abstract: | In this paper, a new method is presented to locate tomatoes from nature background. Color information is used to segment image and th threshold used is selected based on the current image. According to the results of the discriminating and by use of binocular stereo vision technique, th 3-D position of the fruit could be got. In the process of position locating, centroid-mathing is recommended to displace the common object-mathing. A the same time, the formula based on binocular stereo vision to measure distance is revised. The result shows that when the work distance is less tha 500mm, almost all the errors are less than 10mm. |
| |
| Keywords: | Computer vision Location Binocular stereo vision |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
