Rice heading stage automatic observation by multi-classifier cascade based rice spike detection method
Rice heading stage automatic observation by multi-classifier cascade based rice spike detection method
复制标题
基于多分类器级联的水稻穗检测方法的水稻抽穗期自动观测
DOI：
10.1016/j.agrformet.2018.05.001
复制
发表时间：
2018-09-15
影响因子：
6.2
通讯作者：
Xie, Jidong
中科院分区：
文献类型：
--
作者：
Bai, Xiaodong;Cao, Zhiguo;Xie, Jidong
水稻抽穗期是水稻生产的重要时期，它直接影响水稻产量。将水稻抽穗期自动观测问题转化为水稻穗位检测问题，提出了一种新的水稻抽穗期自动观测方法。采用一种新的多分类器级联方法实现了水稻穗的检测，该方法包括以下步骤：首先，以颜色特征为输入，利用支持向量机（SVM）将水稻穗图像块与背景块（叶片、土壤、水体等）区分开来;其次，梯度直方图的方法被应用到从考虑中删除黄叶补丁;第三，卷积神经网络（CNN）被用来进一步降低误报率。水稻抽穗期的到来取决于检测到的穗斑数。为了评估所提出的方法，它被应用到自动水稻抽穗期观测的6个图像序列所设计的观测装置在2011年和2013年之间收集的观测。在试验中，所提出的方法产生了类似的结果，传统的人工观测方法在确定水稻抽穗期的到来。该方法与人工方法的误差在两天以内。试验表明，该方法是一种有效的水稻抽穗期自动观测方法，可替代人工观测。
The rice heading stage is an essential phase of rice production as it directly affects the rice yield. This paper transforms the issue of rice heading stage automatic observation into the problem of rice spike detection and proposes a new method for automatic observation of the rice heading stage. Rice spike detection is achieved using a new multi-classifier cascade method comprised of the following steps: First, SVM with color feature as input is utilized to distinguish the rice spike image patches from the background patches (leaf, soil, water, etc.); Second, a gradient histogram method is applied to remove the yellow leaf patches from consideration; Third, a convolutional neural network (CNN) is utilized to further reduce the false positive rate. The arrival of the rice heading stage is determined by the number of the detected spike patches. To evaluate the proposed method, it was applied to the automatic rice heading stage observation of six image sequences collected by the designed observation device between 2011 and 2013. In the experiment, the proposed method produced similar results to the conventional manual observation method in determining the arrival of the rice heading stage. The differences between the proposed method and manual way were within two days. Experiments demonstrated that the proposed method is an effective approach of automatic observation of the rice heading stage in paddy fields and can be utilized to replace the manual observation.