| 农作物边缘提取方法研究 |
| |
| 引用本文： | 沈明霞,张瑞合,姬长英.农作物边缘提取方法研究[J].农业机械学报,2000,31(6):49-51. |
| |
| 作者姓名： | 沈明霞 张瑞合 姬长英 |
| |
| 作者单位： | 南京农业大学农业工程学院,南京市,210032 |
| |
| 摘 要： | 为实现复杂农作物边缘检测，提出了用低通滤波对原始图像进行预处理，然后采用给定阈值的图像二值化，再利用二值膨胀滤除细小纹理，最后依照先验知识获得较完善的农作物边缘的方法。通过收获季节实验证明该方法是可靠的，能够得到预期的农作物有效边缘。
|
| 关 键 词： | 农作物 边缘信息 计算机视觉 农业机器人 |
| 修稿时间： | 2000-03-23 |
Study on Extracting Edge of Cropland Scenery |
| |
| Shen Mingxia,Zhang Ruihe,Ji Changying.Study on Extracting Edge of Cropland Scenery[J].Transactions of the Chinese Society of Agricultural Machinery,2000,31(6):49-51. |
| |
| Authors: | Shen Mingxia Zhang Ruihe Ji Changying |
| |
| Institution: | Nanjing Agricultural University |
| |
| Abstract: | An automatic detection of the cropland edges under the complicated background was made in this paper. Some knowledge based approaches were introduced to implement the edges detection. In order to detect edges, a lowpass filter was used to preprocess the original images at first, then a binary image was obtained by means of grad transformation. After the thin texture was moved with thresholding dilation, the complete edge of cropland was obtained. All of the algorithms proposed herein are knowledge based. The procedures of edges extraction are fuzzy and robust. Even the binary images of cropland are occluded or fragmentized, the edges can be detected efficiently and effectively. The experiments show that this method is reliable and the extracted edges are effective. |
| |
| Keywords: | Farm crops Marginal information Computer visio |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
