ABSTRACT
Agricultural pest detection is an important research direction in image detection. Due to the high similarity between many pests and the extremely similar color of pests and background, agricultural pest detection has always been a difficulty. In the early work, many methods were made to improve the detection accuracy by fusing gray space, YUV and HSV. In recent years, with the development of neural networks, the Yolo series began to show better performance in agricultural pest detection. In order to further improve the performance of Yolo series, the method of combining EIOU with Yolov5 is applied in this paper, and the accuracy on IP102 is improved.
- Yi-Fan Zhang, Weiqiang, Zhang Zhang, Zhen Jia, Liang Wang, and Tieniu Tan. Focal and Effcient IoU for Accurate Bounding Box Regression. In CVPR, 2020.Google Scholar
- Zhaohui Zheng, Ping Wang, Wei Liu, Jinze LiRongguang Ye, and Dongwei Ren. Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. In The AAAI Conference on Artificial Intelligence (AAAI),2020.Google Scholar
- Tsung-Yi Lin, Michael Maire, serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollar, and C.Lawrence Zitnick. Microsoft coco:Common objects in context. In David Fleet, Tomas Pajdla, Bernt Schiele, and Tinna TUytelaars, editors, Computer Vision - ECCV 2014, pages 740-755, Cham, 2014. Springer International Publishing.Google ScholarCross Ref
- Ying He, Dinghao Chen, Lin Peng.Research on Economic forest Pest Object Detection algorithm Based on Improved YOLOv5 model. In Journal of Chinese Agricultural Mechanization, 2022.Google Scholar
- Kean Chen, Weiyao Lin, Jianguo Li, John See, Ji Wang, andJunni Zou. AP-loss for Accurate One-Stage Object Detection.IEEE Transactions on Pattern Analysis and Machine Intel-ligence (TPAMI), 43(11):3782–3798, 2020.Google Scholar
- Jiwoong Choi, Dayoung Chun, Hyun Kim, and Hyuk-JaeLee. Gaussian Yolov3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 502–511, 2019.Google ScholarCross Ref
- Shiyu Zhang, Kai Xia, Xiaochen Du, Hailin Feng, Li Chen. A Faster R-CNN Method for Insect Detection in Granary Based on Clustering Feature In Journal of the Chinese Cereals and Oils Association, pages 165-172, 2020.Google Scholar
- Jocher Glenn. Yolov5 release v6.1. https://github.com/ultralytics/Yolov5/releases/tag/v6.1, 2022.Google Scholar
- Golnaz Ghiasi, Tsung-Yi Lin, and Quoc V Le. NAS-FPN:Learning Scalable Feature Pyramid Architecture for Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages7036–7045, 2019.Google Scholar
- Jun Liu, Xuewei Wang. Tomato Diseases and Pest Detection Based on Improved YoloV3 Convolutional Neural Network. In Proceedings of the Science Citation Index(SCI),11:898. dot: 10.3389/fpls.2020.008989.Google Scholar
- R Wang, L Jiao, C Xie, P Chen, J Du and R Li. S-RPN:Sampling-Balanced Region Proposal Network for Small Crop Pest Detection. In Proceedings of Computer. Electron. Agric. 187: 106290 , 2021.Google Scholar
- Jianming Du, Liu Liu, Rui Li, Lin Jiao, Chengjun Xie and Rujing Wang. Towards Densely Clustered Tiny Pest Detection in the Wild environment. In Proceedings of Neurocomputing Volume 490, 14 June 2022, Pages 400-412.Google ScholarDigital Library
- Zheng Xu, Yongqiang Li, Lin Jiao, Mingsheng Wang and Willi Meier. Do NOT Misuse the Markov Cipher Assumption - Automatic Search for Differential and Impossible Differential Characteristics in ARX Ciphers. In Proceedings of the IACR Cryptol. ePrint Arch. 2022: 135.Google Scholar
- Zhengbin Liu, Yongqiang Li, Lin Jiao and Mingsheng Wang. A New Method for Searching Optimal Differential and Linear Trails in ARX Ciphers. In IEEE Trans. Inf. Theory 67(2): 1054-1068 , 2021.Google ScholarCross Ref
- Tingting Liang, Xiaojie Chu, Yudong Liu, Yongtao Wang,Zhi Tang, Wei Chu, Jingdong Chen, and Haibin Ling. CB-NetV2: A Composite Backbone Network Architecture for Object Detection.arXiv preprint arXiv:2107.00420, 2021.Google Scholar
- Yuxuan Liu, Lujia Wang, and Ming Liu. YoloStereo3D:A Step Back to 2D for Dfficient Stereo 3D Detection. In IEEE International Conference on Robotics and Automa-tion (ICRA), pages 13018–13024, 2021.Google Scholar
- Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang,and Jifeng Dai. Deformable DETR: Deformable Transformers for End-to-End Object Detection. In Proceedings of the International Conference on Learning Representations (ICLR), 2021.Google Scholar
- Lin Jiao, Shifeng Dong, Shengyu Zhang, Chengjun Xie and Hongqiang Wang. AF-RCNN:An Anchor-Free Convolutional Neural Network for Multi-categoriesagricultural Pest Detection. In Computers and Electronics in Agriculture Volume 174, July 2020, 105522.Google ScholarCross Ref
- Lin Jiao, Chengjun Xie, Peng Chen, Jianming Du and Jie Zhang. Adaptive Feature Fusion Pyramid Network for Nulti-classes Agricultural Pest Detection. In Proceedings of the Computers and Electronics in Agriculture Volume 195, April 2022, 1068270.Google Scholar
- Stenberg, JA, Swedish Univ Agr Sci, Dept Plant Protect Biol, S-23053 Alnarp, Sweden. A Conceptual Framework for Integrated Pest Management. In Proceedings of TRENDS IN PLANT SCIENCE, September 2017,759.Google Scholar
- Sheng Zhu, Jizhong Deng, Yali Zhang, Chang Yang, Zhiwei Yan, Yaoqing Xie. Study on Weed Distribution Map in rice field Based on UAV low-altitude Remote sensing. In Proceedings of Journal of South China Agricultural University 2020, 41(6): 67-74.Google Scholar
- Xiang Li, Wenhai Wang, Xiaolin Hu, Jun Li, Jinhui Tang, Jian Yang. Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection. In Proceedings of arXiv:2011.12885.Google Scholar
- Li Xi,Zha Yufei,Zhang Tianzhu,Cui Zhen,Zuo Wangmeng. Scale Invariant Feature Transform on the Sphere: Theory and Applications. In Computer Vision, 98(2):217-241.Google Scholar
- Long Zhou. Analysis of intelligent detection methods for stored grain pests. In Grain, Oil and Food Science and Technology Volume 12, Issue 4, 2004.Google Scholar
- Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Network. In Submitted on 4 Jun 2015 (v1), last revised 6 Jan 2016 (this version, v3).Google Scholar
- Minli Tang, Shaomin Xie,Xiangrong Liu. Detection And Recognition of Handwritten characters In ancient Water books Based on Faster-RCNN. In Journal of Xiamen University (Natural Science Edition), Peking University Core 2022.Google Scholar
- Xiaolin Jiang, Sheng Gao, Hongfang Ru,Bo Peng. Improved SSD Target Detection algorithm Based on Dense Network. In Journal of Heilongjiang University of Science and Technology,Vol.30 No.2, Mar.2020.Google Scholar
- LIU Tingna, ZHENG Minhua, ZHU Zhongjie. Real Time Vehicle Detection Based on Improved YOLOv3. In Journal of Zhejiang Wanli University,2022.Google Scholar
- LI Guo-Pu1liguopu, CHEN Sheng-Dong, WANG Liang, ZOU Kai, YUAN Feng. Vehicle-side Target Detection Based on Improved YOLOv5. In Computer system application, 2022.Google Scholar
- Qingshan Hou, Jinsheng Xing. SSD Object Detection algorithm Based on Grad-CAM and KL loss. In Electronic journal,2020.Google Scholar
- Minli Tang, Shaomin Xie,Xiangrong Liu. Detection of tea inchworm in Complex background Image Based on Improved YOLOv5 Network. In Transactions of the Chinese Society of Agricultural Engineering, Vol.37 No.21 Nov.2021,191.Google Scholar
- Ying She, Ling Wu, Luquan Shan.Improved Identification Method of Rice pests Based on SSD Network Model. In Journal of Zhengzhou University, 2022.Google Scholar
- Runmei Luo, Huili Yin, Kai Hu. Identification of Diseases and Pests of Guangfo Hand Based on YOLOv5-C. In Journal of South China Agricultural University, 2022.Google Scholar
- Jun Liu, Xuewei Wang. Tomato Diseases and Pests Detection Based on Improved Yolo V3 Convolutional Neural Network. In Facifity Horticlture Laboratory of Universities in Shandong,Weifang University OF Science and Technology,2020.Google ScholarCross Ref
- ZHOU Wei, NIU Yong-zhen,WANG Ya-wei,LI Dan. Rice pests and diseases identification method based on improved YOLOv4-GhostNet. In Journal of Jiangsu Agriculture,2022.Google Scholar
Index Terms
- Agricultural Pest Detection based on Improved Yolov5
Recommendations
Real-time and effective detection of agricultural pest using an improved YOLOv5 network
AbstractPest detection and control can effectively guarantee the quality and yield of crops. The existing CNN-based object detection methods provide feasible strategies for pest detection; however, their low accuracy and speed have restricted the ...
Vision-based pest detection based on SVM classification method
Detection of thrips in strawberry greenhouse.Detection based on SVM classification method.Pest detection using visible image processing.Real-time detection.Detection under the natural light. Automatic pest detection is a useful method for greenhouse ...
Agricultural drought monitoring using MODIS-based drought indices over the USA Corn Belt
In 2012, the USA Corn Belt, an intensive agricultural region of the USA, was hit by a widespread severe drought, affecting states such as Illinois, Iowa, Nebraska, and Indiana. In this study, time series 2000–2012 of Moderate Resolution Imaging ...
Comments