Automatic greenhouse insect pest detection and recognition based on a cascaded deep learning classification method
Automatic greenhouse insect pest detection and recognition based on a cascaded deep learning classification method
复制标题
DOI：
10.1111/jen.12834
复制
发表时间：
2020-11-20
影响因子：
1.9
通讯作者：
Lin, Ta-Te
中科院分区：
文献类型：
--
作者：
Rustia, Dan Jeric Arcega;Chao, Jun-Jee;Lin, Ta-Te
检查昆虫粘纸诱捕器是有效的虫害综合管理(IPM)方案的一项基本任务。然而，对卡在陷阱上的害虫进行识别和统计是一项非常繁琐的任务。因此，需要一种有效的方法来缓解这一问题，并及时提供有关害虫的信息。本研究提出了一种基于无线成像设备采集的粘纸诱捕器图像的小型温室害虫多类自动识别方法。开发的算法的特点是级联方法，分别使用卷积神经网络(CNN)对象检测器和CNN图像分类器。在第一阶段，训练目标检测器检测图像中的目标，并应用CNN分类器进一步从检测到的目标中过滤出非昆虫目标。然后在第二阶段使用多类CNN分类器将获得的昆虫对象进一步分类为苍蝇(双翅目：果蝇科)、蚊类(双翅目：蝗科)、蓟马(胸翅目：蓟马科)和粉虱(半翅目：粉虱科)。这种方法的优点包括灵活地向多类昆虫分类器添加更多的类和样本控制策略以提高分类性能。该算法是针对安装在几个温室中的多个无线成像设备在自然和可变光照环境下拍摄的图像进行开发和测试的。基于温室长期实验的测试结果发现，该算法可以达到平均F-1得分为0.92和0.90，平均计数精度为0.91和0.90，分别在单独的6月图像数据集和不同温室的图像数据集上进行测试。本研究提出的方法解决了害虫自动识别的重要问题，并提供了温室害虫发生的即时信息，为开发更有效的农业综合防治策略提供了巨大的潜力。
Inspection of insect sticky paper traps is an essential task for an effective integrated pest management (IPM) programme. However, identification and counting of the insect pests stuck on the traps is a very cumbersome task. Therefore, an efficient approach is needed to alleviate the problem and to provide timely information on insect pests. In this research, an automatic method for the multi-class recognition of small-size greenhouse insect pests on sticky paper trap images acquired by wireless imaging devices is proposed. The developed algorithm features a cascaded approach that uses a convolutional neural network (CNN) object detector and CNN image classifiers, separately. The object detector was trained for detecting objects in an image, and a CNN classifier was applied to further filter out non-insect objects from the detected objects in the first stage. The obtained insect objects were then further classified into flies (Diptera: Drosophilidae), gnats (Diptera: Sciaridae), thrips (Thysanoptera: Thripidae) and whiteflies (Hemiptera: Aleyrodidae), using a multi-class CNN classifier in the second stage. Advantages of this approach include flexibility in adding more classes to the multi-class insect classifier and sample control strategies to improve classification performance. The algorithm was developed and tested for images taken by multiple wireless imaging devices installed in several greenhouses under natural and variable lighting environments. Based on the testing results from long-term experiments in greenhouses, it was found that the algorithm could achieve average F-1-scores of 0.92 and 0.90 and mean counting accuracies of 0.91 and 0.90, as tested on a separate 6-month image data set and on an image data set from a different greenhouse, respectively. The proposed method in this research resolves important problems for the automated recognition of insect pests and provides instantaneous information of insect pest occurrences in greenhouses, which offers vast potential for developing more efficient IPM strategies in agriculture.