文献类型： 外文期刊
作者： Cheng, Zekai 1 ; Huang, Rongqing 1 ; Qian, Rong 2 ; Dong, Wei 2 ; Zhu, Jingbo 2 ; Liu, Meifang 1 ;
作者机构： 1.Anhui Univ Technol, Sch Comp Sci & Technol, Maanshan 243032, Peoples R China
2.Anhui Acad Agr Sci, Inst Agr Econ & Informat, Hefei 230031, Peoples R China
关键词： crop pest detection; parameter; computation; k-means plus plus; lightweight sandglass block; coordinate attention
期刊名称：APPLIED SCIENCES-BASEL （ 影响因子：2.838； 五年影响因子：2.921 ）
ISSN：
年卷期： 2022 年 12 卷 15 期
页码：
收录情况： SCI
摘要： Existing object detection methods with many parameters and computations are not suitable for deployment on devices with poor performance in agricultural environments. Therefore, this study proposes a lightweight crop pest detection method based on convolutional neural networks, named YOLOLite-CSG. The basic architecture of the method is derived from a simplified version of YOLOv3, namely YOLOLite, and k-means++ is utilized to improve the generation process of the prior boxes. In addition, a lightweight sandglass block and coordinate attention are used to optimize the structure of residual blocks. The method was evaluated on the CP15 crop pest dataset. Its detection precision exceeds that of YOLOv3, at 82.9%, while the number of parameters is 5 million, only 8.1% of the number used by YOLOv3, and the number of computations is 9.8 GFLOPs, only 15% of that used by YOLOv3. Furthermore, the detection precision of the method is superior to all other commonly used object detection methods evaluated in this study, with a maximum improvement of 10.6%, and it still has a significant edge in the number of parameters and computation required. The method has excellent pest detection precision with extremely few parameters and computations. It is well-suited to be deployed on equipment for detecting crop pests in agricultural environments.
- 相关文献
作者其他论文 更多>>
-
Causality-inspired crop pest recognition based on Decoupled Feature Learning
作者：Hu, Tao;Yan, Keyu;Hu, Tao;Du, Jianming;Yan, Keyu;Zhang, Jie;Xie, Chengjun;Dong, Wei;Wang, Jun
关键词：pest recognition; Decoupled Feature Learning; causal inference; deep learning
-
CMRD-Net: a deep learning-based Cnaphalocrocis medinalis damage symptom rotated detection framework for in-field survey
作者：Chen, Tianjiao;Wang, Rujing;Du, Jianming;Chen, Hongbo;Zhang, Jie;Chen, Tianjiao;Wang, Rujing;Chen, Hongbo;Wang, Rujing;Dong, Wei;Zhang, Meng
关键词：Cnaphalocrocis medinalis; damage symptom; deep learning; rotated object detection; horizontal object detection
-
Genome-wide detection of CNV regions between Anqing six-end-white and Duroc pigs
作者：Qian, Rong;Kong, JuanJuan;Zhang, Wei;Zhou, Xueli;Wang, Chonglong;Xie, Fei;Li, Xiaojin
关键词：Copy number variation; Genome-wide; Anqing six-end-white pigs; Duroc pigs
-
Development of a Lightweight Crop Disease Image Identification Model Based on Attentional Feature Fusion
作者：Cheng, Zekai;Liu, Meifang;Huang, Rongqing;Qian, Rong;Dong, Wei
关键词：crop diseases identification; ResNet18; DSGIResNet_AFF; lightweight residual blocks; inverted residual blocks; attentional feature fusion
-
Phanuromyia ricaniae Nam, Lee & Talamas sp. n. (Hymenoptera: Scelionidae reared from the eggs of Ricania shantungensis Chou & Lu (Hemiptera: Ricaniidae in Asia
作者：Nam, Sanghyeok;Lee, Seunghwan;Chen, Hua-Yan;Talamas, Elijah J.;Lee, Gwan-Seok;Dong, Wei;Sun, Li-Juan;Lee, Seunghwan
关键词：Biological control; Ricania; Platygastroidea; Phanuromyia
-
SLIC_SVM based leaf diseases saliency map extraction of tea plant
作者：Sun, Yunyun;Jiang, Zhaohui;Rao, Yuan;Zhang, Liping;Dong, Wei
关键词：Tea plant; Leaf disease; SLIC; SVM; Saliency map
-
Multi-level learning features for automatic classification of field crop pests
作者：Xie, Chengjun;Wang, Rujing;Zhang, Jie;Chen, Peng;Li, Rui;Chen, Tianjiao;Chen, Hongbo;Chen, Peng;Dong, Wei
关键词：Pest classification; Unsupervised feature learning; Dictionary learning; Feature encoding
