您好，欢迎访问北京市农林科学院 机构知识库！
北京市农林科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

USING AN IMPROVED YOLOV4 DEEP LEARNING NETWORK FOR ACCURATE DETECTION OF WHITEFLY AND THRIPS ON STICKY TRAP IMAGES

文献类型： 外文期刊

作者： Wang, Dujin 1 ; Wang, Yizhong 2 ; Li, Ming 1 ; Yang, Xinting 1 ; Wu, Jianwei 4 ; Li, Wenyong 1 ;

作者机构： 1.Beijing Res Ctr Informat Technol Agr, Beijing, Peoples R China

2.Tianjin Univ Sci & Technol, Coll Elect Informat & Automat, Tianjin, Peoples R China

3.Natl Engn Lab Agriprod Qual Traceabil, Beijing, Peoples R China

4.Beijing PAIDE Sci & Technol Dev Co Ltd, Beijing, Peoples R China

关键词： Deep learning; Greenhouse pest management; Image processing; Pest detection; Small object; YOLOv4

期刊名称：TRANSACTIONS OF THE ASABE （ 影响因子：1.188； 五年影响因子：1.695 ）

ISSN： 2151-0032

年卷期： 2021 年 64 卷 3 期

页码：

收录情况： SCI

摘要： Pest detection is the basis of precise control in vegetable greenhouses. To improve the detection accuracy and robustness for two common small pests (whitefly and thrips) in greenhouses, this study proposes a novel small object detection approach based on the YOLOv4 model. Yellow sticky trap (YST) images at the original resolution (2560. 1920 pixels) were collected using pest monitoring equipment in a greenhouse. The images were then cropped and labeled to create subimages (416 x16 pixels) to construct an experimental dataset. The labeled images used in this study (900 training, 100 validation, and 200 test) are available for comparative studies. To enhance the model's ability to detect small pests, the feature map at the 8-fold downsampling layer in the backbone network was merged with the feature map at the 4-fold downsampling layer to generate a new layer and output a feature map with a size of 104 x 104 pixels. Furthermore, the residual units in the first two residual blocks were enlarged by four times to extract more shallow image features and the location information of target pests to withstand image degradation in the field. The experimental results showed that the mean average precision (mAP) for detection of whitefly and thrips using the proposed approach was improved by 8.2% and 3.4% compared with the YOLOv3 and YOLOv4 models, respectively. The detection performance slightly decreased as the pest densities increased in the YST image, but the mAP value was still 92.7% in the high-density dataset, which indicates that the proposed model has good robustness over a range of pest densities. Compared with previous similar studies, the proposed method has better potential to monitor whitefly and thrips using YSTs in field conditions.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：北京市农林科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台