首页 | 本学科首页   官方微博 | 高级检索  
     检索      

采用改进YOLOv4-Tiny模型的柑橘木虱识别
引用本文:胡嘉沛,李震,黄河清,洪添胜,姜晟,曾镜源.采用改进YOLOv4-Tiny模型的柑橘木虱识别[J].农业工程学报,2021,37(17):197-203.
作者姓名:胡嘉沛  李震  黄河清  洪添胜  姜晟  曾镜源
作者单位:1. 华南农业大学电子工程学院,广州 510642;;1. 华南农业大学电子工程学院,广州 510642; 2. 国家柑橘产业技术体系机械研究室,广州 510642;;2. 国家柑橘产业技术体系机械研究室,广州 510642; 3. 华南农业大学工程学院,广州 510642;;4. 广东省山区特色农业资源保护与精准利用重点实验室,梅州 514015;
基金项目:国家自然科学基金项目(31971797,61601189);国家重点研发计划子课题(2020YFD1000107);国家柑橘产业技术体系专项资金(CARS-26);广东省农村科技特派员重点派驻任务(KTP20200281);广州市科技计划项目(201803020037)
摘    要:黄龙病是一种以柑橘木虱为传播媒介的毁灭性病害,其关键预防措施是在果园现场环境对柑橘木虱识别监测,辅助果农进行早期防治。该研究基于YOLOv4-Tiny模型提出一种适用于嵌入式系统的柑橘木虱识别模型。通过改进YOLOv4-Tiny模型的颈部网络,利用浅层网络的细节信息以提高模型识别柑橘木虱的平均精度;采用交叉小批量归一化(Cross mini-Batch Normalization,CmBN)方法代替批归一化(Batch Normalization,BN)方法,通过累计卷积层的输出,提升统计信息的准确度;针对柑橘木虱易被遮挡的问题,模型训练时使用Mosaic数据增强,提升模型对遮挡目标的识别能力。通过自行建立的柑橘木虱图像数据集完成模型的试验验证。结果表明,该模型的柑橘木虱平均识别精度为96.16%,在图形处理器(Graphics Processing Unit, GPU)上的推理速度为3.63 ms/帧,模型大小为24.5 MB,实现了果园环境下快速准确地识别柑橘木虱,可为黄龙病防治技术的进一步发展提供参考。

关 键 词:图像处理  图像识别  模型  柑橘木虱  精准农业  人工智能
收稿时间:2020/12/14 0:00:00
修稿时间:2021/2/28 0:00:00

Citrus psyllid detection based on improved YOLOv4-Tiny model
Hu Jiapei,Li Zhen,Huang Heqing,Hong Tiansheng,Jiang Sheng,Zeng Jingyuan.Citrus psyllid detection based on improved YOLOv4-Tiny model[J].Transactions of the Chinese Society of Agricultural Engineering,2021,37(17):197-203.
Authors:Hu Jiapei  Li Zhen  Huang Heqing  Hong Tiansheng  Jiang Sheng  Zeng Jingyuan
Institution:1. College of Electronic Engineering, South China Agricultural University, Guangzhou 510642, China;;1. College of Electronic Engineering, South China Agricultural University, Guangzhou 510642, China; 2. Division of Citrus Machinery, China Agriculture Research System, Guangzhou 510642, China;;2. Division of Citrus Machinery, China Agriculture Research System, Guangzhou 510642, China; 3. College of Engineering, South China Agricultural University, Guangzhou 510642, China;; 4. Guangdong Provincial Key Laboratory of Conservation and Precision Utilization of Characteristic Agricultural Resources in Mountainous Areas, Meizhou 514015, China;
Abstract:Citrus psyllids have widely been served as transmitted vectors for a devastating Huanglong disease. It is highly urgent to rapidly identify and monitor citrus psyllids in orchard sites in real-time. The specific measures can be taken for the early prevention and control of disease. However, the field environments are unsuitable for deploying servers. In this study, a citrus psyllid identification was proposed suitable for embedded systems using YOLOv4-Tiny model. A feature fusion network was developed to improve the accuracy of model in recognizing citrus psyllids. A key path was added to reduce the loss of semantic information in the shallow network layer. At the same time, an output feature map was added, which was down sampled eight times relative to the input image. For an image with a 416 × 416 input, the improved feature fusion network outputted feature maps of three scales, with pixels of 13 × 13, 26 × 26, and 52 × 52. Cross mini-batch normalization was used instead of batch normalization, due to that this normalization combined the output information of previous mini-batch to calculate the average and standard deviation of current mini-batch. The outputs of convolutional layers were converted into the normal layers with a mean of 0 and a variance of 1 distribution. Learnable parameters were used in linearly transforming the outputs of standardized convolutional layers. Owing to the accumulation of output features, the accuracy of statistical information was improved, thereby improving the recognition accuracy of the model. The ability of model to recognize occluded targets was also improved using mosaic data augmentation during model training, particularly for the occluded citrus psyllids. More importantly, four images were randomly cropped in the training set and then stitched them into a single image. The intersection-over-union indicator was also used to filter the ambiguous target frame in the image generated by mosaic data augmentation. The improved mosaic data augmentation was used to simulate the occlusion of citrus psyllids, thereby to weaken the dependence of model on the characteristics of targets. A handheld camera was used to capture the images of adult citrus psyllids in field environments. Data augmentation was then used to obtain a dataset containing 21 410 images, which was divided into the training set, validation set, and test set in a ratio of 7:1:2, respectively. Various improvements were introduced further to verify by experiments. Results showed that the improved feature fusion network, the introduction of cross mini-batch normalization, and the improved mosaic data augmentation greatly increased the average precision of model in the test set. The differences between the proposed model and existing networks were analyzed, where the same training set was used to train YOLOv4, YOLOv4-Tiny, Faster R-CNN, and the proposed model. Furthermore, comparative tests were performed in the test set, where the model was evaluated in terms of average precision, inference speed, and model size. Specifically, the average precision of the proposed model was 96.16%, the inference speed on the Graphics Processing Unit (GPU) was 3.63 ms/frame, and the model size was 24.5 MB. Consequently, the new model can be expected to accurately and quickly identify citrus psyllids for early warning suitable for the deployment in embedded devices.
Keywords:image processing  image recognition  models  citrus psyllid  precision agriculture  artificial intelligence
点击此处可从《农业工程学报》浏览原始摘要信息
点击此处可从《农业工程学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号