Connected attribute morphology for unified vegetation segmentation and classification in precision agriculture.
Connected attribute morphology for unified vegetation segmentation and classification in precision agriculture.
复制标题
DOI：
10.1016/j.compind.2018.02.003
复制
发表时间：
2018-06
影响因子：
10
通讯作者：
Cielniak G
中科院分区：
文献类型：
--
作者：
Bosilj P;Duckett T;Cielniak G
分割和分类流水线完全依赖于属性形态学。该方法的强局部性避免了产生的前景噪声。分割直接输出区域，避免了组件标记步骤。最大树结构使分割过程中的特征计算。将植物区域竞争性地分类为不同植物类型的作物/杂草。从杂草中识别出有价值的作物是精确农业中的一项重要任务。在本文中，我们提出了一种新的基于属性形态学的图像处理流水线的分割和分类任务。常用的植被分割方法往往依赖于阈值技术，达到他们的决定全球。相比之下，所提出的方法与图像阈值分解，这是自然嵌套在一个层次结构称为最大树，从这些区域计算的各种属性获得的连接组件。图像分割是通过属性过滤来执行的，基于它们的属性值保留或丢弃区域，并允许局部地达到决策。这种分割方法自然选择的前景区域，而不是像素的集合，和用于分割的相同的数据结构可以进一步重用，以提供分类，这是在我们的实验中实现的支持向量机（SVM）的功能。我们将我们的方法应用于归一化差异植被指数（NDVI）图像，并在作者在洋葱田收集的数据集以及公开的甜菜数据集上展示了管道的性能。结果表明，所提出的分割方法可以分割的植物区域的局部细节，在最先进的阈值方法相比，同时提供歧视性的功能，使有效的和有竞争力的分类率作物/杂草歧视。
Segmentation and classification pipeline fully relying on attribute morphology. Strong locality of the approach avoids resulting foreground noise. Segmentation outputs regions directly, avoiding the component labelling step. Max-tree structure enables feature calculation during segmentation. Competitive classification of plant regions into crop/weed for varying plant types. Discriminating value crops from weeds is an important task in precision agriculture. In this paper, we propose a novel image processing pipeline based on attribute morphology for both the segmentation and classification tasks. The commonly used approaches for vegetation segmentation often rely on thresholding techniques which reach their decisions globally. By contrast, the proposed method works with connected components obtained by image threshold decomposition, which are naturally nested in a hierarchical structure called the max-tree, and various attributes calculated from these regions. Image segmentation is performed by attribute filtering, preserving or discarding the regions based on their attribute value and allowing for the decision to be reached locally. This segmentation method naturally selects a collection of foreground regions rather than pixels, and the same data structure used for segmentation can be further reused to provide the features for classification, which is realised in our experiments by a support vector machine (SVM). We apply our methods to normalised difference vegetation index (NDVI) images, and demonstrate the performance of the pipeline on a dataset collected by the authors in an onion field, as well as a publicly available dataset for sugar beets. The results show that the proposed segmentation approach can segment the fine details of plant regions locally, in contrast to the state-of-the-art thresholding methods, while providing discriminative features which enable efficient and competitive classification rates for crop/weed discrimination.
登录
查看更多内容
DOI：
10.1109/tcs.1985.1085740
发表时间：
1985-01-01
期刊：
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS
影响因子：
--
作者：
FITCH, JP;COYLE, EJ;GALLAGHER, NC
通讯作者：
GALLAGHER, NC
DOI：
10.1109/tit.1962.1057692
发表时间：
1962-01-01
期刊：
IRE TRANSACTIONS ON INFORMATION THEORY
影响因子：
--
作者：
HU, M
通讯作者：
HU, M
DOI：
10.3390/s110606270
发表时间：
2011
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Jeon HY;Tian LF;Zhu H
通讯作者：
Zhu H
影响因子：
8.3
作者：
Binch, A.;Fox, C. W.
通讯作者：
Fox, C. W.
影响因子：
5.1
作者：
Bai, Xiaodong;Cao, Zhiguo;Li, Cuina
通讯作者：
Li, Cuina