• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 图形与图像 • 上一篇    下一篇

基于卷积神经网络的虫情图像分割和计数方法

王卫民1,符首夫1,顾榕蓉1,王东升1,何林容2,关文斌3   

  1. (1.江苏科技大学计算机学院,江苏 镇江 212003; 2.南京林业大学计算机科学与技术学院,江苏 南京 210037;
    3.江苏慧禾融智信息技术有限公司,江苏 南京 210019)
  • 收稿日期:2019-05-20 修回日期:2019-08-05 出版日期:2020-01-25 发布日期:2020-01-25
  • 基金资助:

    国家自然科学基金(61702234)

An insect image segmentation and counting
method based on convolutional neural network

WANG Wei-min1,FU Shou-fu1,GU Rong-rong1,WANG Dong-sheng1,HE Lin-rong2,GUAN Wen-bin3   

  1. (1.School of Computer,Jiangsu University of Science and Technology,Zhenjiang 212003;
    2.School of Computer Science and Technology,Nanjing Forestry University,Nanjing 210037;
    3.Jiangsu History Roster Info-Tech Information Technology Co.Ltd.,Nanjing 210019,China)

     
  • Received:2019-05-20 Revised:2019-08-05 Online:2020-01-25 Published:2020-01-25

摘要:

为提高虫情图像的分割和计数的准确率,提出了一种基于卷积神经网络的虫情图像分割和计数方法。该方法基于U-Net模型构造了一种昆虫图像分割的模型Insect-Net,将完整的虫情图像和切割后的虫情图像分别输入模型后,提取两者特征进行融合。将融合后的特征输入1个1×1的卷积层得到最终分割结果,再将得到的结果二值化后,采用轮廓检测算法将昆虫目标与背景分离并计数。实验结果表明,该方法在虫情图像中取得了较高的分割正确率和计数正确率,分别为94.4%和89.2%。用深度学习和卷积神经网络的方法有效提高了虫情图像的计数精度,并且为昆虫识别分类提供了大量的无背景数据集。

关键词: 虫情计数, 卷积神经网络, 图像分割, Insect-Net

Abstract:

In order to improve the accuracy of segmentation and counting of insect images, an insect image segmentation and counting method based on convolutional neural network is proposed. Based on the U-Net model, this method constructs an insect image segmentation model named Insect-Net. After inputting the complete insect image and the split insect image into the model, the features of the two images are extracted and merged. The merged features are inputted into a 1×1 convolutional layer to get the final segmentation results. After the obtained results are binarized, the contour detection algorithm is used to extract the contours of the insects and count them. The experimental results show that the method has higher segmentation accuracy and counting accuracy in the detection of insects, which are 89.2% and 94.4% respectively. The idea of deep learning and convolutional neural network effectively improves the counting accuracy of insect images, and provides a large number of non-background datasets for insect identification classification.
 

Key words: insect counting, convolutional neural network, image segmentation, Insect-Net