欢迎您访问《智慧农业(中英文)》官方网站! English

Smart Agriculture ›› 2021, Vol. 3 ›› Issue (4): 111-122.doi: 10.12133/j.smartag.2021.3.4.202101-SA002

• 信息处理与决策 • 上一篇    下一篇

基于密度估计和VGG-Two的大豆籽粒快速计数方法

王莹1(), 李越1, 武婷婷2, 孙石2, 王敏娟1()   

  1. 1.中国农业大学现代精细农业系统集成研究教育部重点实验室,北京 100083
    2.中国农业科学院作物科学研究所/农业农村部北京大豆生物学重点实验室,北京 100081
  • 收稿日期:2021-01-14 修回日期:2021-09-16 出版日期:2021-12-30
  • 基金资助:
    国家自然科学基金面上项目(31971786);山东省自然科学基金面上项目(ZR2021MC021)
  • 作者简介:王 莹(1994-),女,博士研究生,研究方向为大豆表型技术。E-mail:b20213080632@cau.edu.cn
  • 通信作者:

Fast Counting Method of Soybean Seeds Based on Density Estimation and VGG-Two

WANG Ying1(), LI Yue1, WU Tingting2, SUN Shi2, WANG Minjuan1()   

  1. 1.Key Laboratory of Modern Precision Agriculture System Integration Research, China Agricultural University, Beijing 100083, China
    2.Institute of Crop Sciences, Chinese Academy of Agricultural Sciences/Beijing Key Laboratory of Soybean Biology, Ministry of Agriculture and Rural Affairs, Beijing 100081, China
  • Received:2021-01-14 Revised:2021-09-16 Online:2021-12-30
  • Supported by:
    National Natural Science Foundation of China(31971786); Shandong Province Natural Science Foundation General Project (ZR2021MC021)

摘要:

为快速准确计数大豆籽粒,提高大豆考种速度和育种水平,本研究提出了一种基于密度估计和VGG-Two(VGG-T)的大豆籽粒计数方法。首先针对大豆籽粒计数领域可用图像数据集缺乏的问题,提出了基于数字图像处理技术的预标注和人工修正标注相结合的快速目标点标注方法,加快建立带标注的公开可用大豆籽粒图像数据集。其次构建了适用于籽粒图像数据集的VGG-T网络计数模型,该模型基于VGG16,结合密度估计方法,实现从单一视角大豆籽粒图像中准确计数籽粒。最后采用自制的大豆籽粒数据集对VGG-T模型进行测试,分别对有无数据增强的计数准确性、不同网络的计数性能以及不同测试集的计数准确性进行了对比试验。试验结果表明,快速目标点标注方法标注37,563个大豆籽粒只需花费197 min,比普通人工标注节约了1592 min,减少约96%的人工工作量,大幅降低时间成本和人工成本;采用VGG-T模型计数,其评估指标在原图和补丁(patch)情况下的平均绝对误差分别为0.60.2,均方误差为0.6和0.3,准确性高于传统图像形态学操作以及ResNet18、ResNet18-T和VGG16网络。在包含不同密度大豆籽粒的测试集中,误差波动较小,仍具有优良的计数性能,同时与人工计数和数粒仪相比,计数11,350个大豆籽粒分别节省大约2.493?h0.203?h,实现大豆籽粒的快速计数任务。

关键词: 卷积神经网络, 籽粒计数, 籽粒图像, 点标注, 密度图, VGG-Two, 育种

Abstract:

In order to count soybean seeds quickly and accurately, improve the speed of seed test and the level of soybean breeding, a method of soybean seed counting based on VGG-Two (VGG-T) was developed in this research. Firstly, in view of the lack of available image dataset in the field of soybean seed counting, a fast target point labeling method of combining pre-annotation based on digital image processing technology with manual correction annotation was proposed to speed up the establishment of publicly available soybean seed image dataset with annotation. Only 197 min were taken to mark 37,563 seeds when using this method, which saved 1592 min than ordinary manual marking and could reduce 96% of manual workload. At the same time, the dataset in this research is the largest annotated data set for soybean seed counting so far. Secondly, a method that combined the density estimation-based and the convolution neural network (CNN) was developed to accurately estimate the seed count from an individual threshed seed image with a single perspective. Thereinto, a CNN architecture consisting of two columns of the same network structure was used to learn the mapping from the original pixel to the density map. Due to the very limited number of training samples and the effect of vanishing gradients on deep neural networks, it is not easy for the network to learn all parameters at the same time. Inspired by the success of pre-training, this research pre-trained the CNN in each column by directly mapping the output of the fourth convolutional layer to the density map. Then these pre-trained CNNs were used to initialize CNNs in these two columns and fine-tune all parameters. Finally, the model was tested, and the effectiveness of the algorithm through three comparative experiments (with and without data enhancement, VGG16 and VGG-T, multiple sets of test set) was verified, which respectively provided 0.6 and 0.2 mean absolute error (MAE) in the original image and patch cases, while mean squared error (MSE) were 0.6 and 0.3. Compared with traditional image morphology operations, ResNet18, ResNet18-T and VGG16, the method proposed improving the accuracy of soybean seed counting. In the testset containing soybean seeds of different densities, the error fluctuation was small, and it still had excellent counting performance. At the same time, compared with manual counting and photoelectric seed counter, it saved about 2.493 h and 0.203 h respectively for counting 11,350 soybean seeds, realizing rapid soybean seeds counting.

Key words: convolutional neural network, seed counting, seed image, point labeling, density map, VGG-Two, breeding

中图分类号: