基于超像素分割的田间小麦穗数统计方法

Field Wheat Ears Counting Based on Superpixel Segmentation Method

【目的】小麦穗数是产量构成的重要因素。通过图像处理技术快速准确地统计小麦穗数,为作物长势监测和产量估测提供重要依据。【方法】本研究以经氮肥梯度处理后不同长势的小麦为研究对象,首先,通过简单线性迭代聚类算法(simple linear iterative cluster,SLIC)对田间小麦图像进行超像素分割的预处理;提取并分析图像的部分颜色特征参数,选择适宜的颜色特征参数训练分类器;选择准确率最高的分类器对图像进行分类处理,识别麦穗。其次,对麦穗识别结果进行二值化;经腐蚀、膨胀等一系列形态学计算提取麦穗主体并进行区域统计;提取麦穗骨架,检测骨架角点数,结合角点数与区域统计结果计算小麦穗数;最后,通过线性回归分析方法验证了无氮(0)、低氮(1/2常规施氮量)、正常氮(常规施氮量)、高氮(2倍的常规施氮量)4个氮水平麦穗统计结果。【结果】(1)利用超绿值(E_g)和归一化红绿指数(D_(gr))作为分类特征可以有效地识别麦穗、土壤和叶片;(2)相较于直接基于像素进行图像处理,经超像素分割处理后麦穗识别结果更理想,识别出麦穗主体清晰,形态更为完整;(3)经比较,高氮水平下小麦长势较好,穗数统计准确率最高,为94.4%,无氮水平下小麦长势较差,穗数统计准确率最低,仅为81.9%;排除无氮情况后,长势较均匀的氮水平混合样本中麦穗计数准确率达到92.9%,相较于长势差异较大的混合样本准确率提高了8.3%。【结论】在一般环境下,利用超像素和颜色特征的麦穗自动统计方法可以快速准确地对大田小麦进行穗数计算,长势过弱以及差异过大区域不推荐使用,研究结果为小麦大田估产提供了新的参考。

【Objective】Wheat ears number is a major factor of yield composition and plays an important role in yield estimation and genetic improvement. Using image processing technology to accurately identify and count wheat ears in the field, a new method for obtaining agricultural information was proposed in this paper, which provided a reliable reference for the yield estimation and crop growth monitoring. 【Method】In this paper, wheat with different growth conditions after treatment with nitrogen fertilizer gradient was the research object. Firstly, the simple linear iterative cluster(SLIC) was used to segment the wheat image, and the unit of an image was transformed from pixels to superpixel block. After analyzing the color histograms, the classifiers were trained to identify wheat ears. Then, we performed a simple morphological treatment on the classification results to segment the wheat ears and performed binarization. We obtained the main body of wheat and conducted regional statistics through a series of morphological calculations, such as corrosion and expansion. The wheat ear skeleton was extracted to detect the skeleton corner points to calculate the number of wheat ears. Lastly, the results of counting wheat ears under different nitrogen levels(no nitrogen, low nitrogen, normal nitrogen, high nitrogen) were verified by linear regression analysis. 【Result】(1) Super green value(Eg) and normalized red green index(Dgr) could be used as classification features to effectively identify wheat ears after color histogram analysis.(2) Compared to directly identifying the field image, the main body of wheat identified after superpixel segmentation was more explicit and complete in shape.(3) By comparison, wheat with better growth situation had better ear counting results, which approached 94.4% in high nitrogen level. However, the wheat ear count accuracy was low at a poor nitrogen level, which was only 81.9%. After eliminating the nitrogen-free condition, the overall growth of the mixed sample was uniform, and the wheat ear count accuracy reached 92.9%. The accuracy was improved by 8.3% compared to mixed samples with large differences in growth.【Conclusion】In the general environment, the automatic counting method of wheat ears using superpixels and color features could quickly and accurately calculate the number of wheat ears in field. While the growth vigor was too weak and the difference was too large, this method was not recommended. The research results provided a new reference for wheat field estimation.