RECOGNITION METHOD FOR SEED POTATO BUDS BASED ON IMPROVED YOLOv3-TINY
-
Published:2022-08-31
Issue:
Volume:
Page:364-373
-
ISSN:2068-2239
-
Container-title:INMATEH Agricultural Engineering
-
language:en
-
Short-container-title:INMATEH
Author:
ZHANG Wanzhi1, HAN Yuelin2, HUANG Chen2, CHEN Zhiwei2
Affiliation:
1. College of Mechanical and Electronic Engineering, Shandong Agricultural University, /China, Shandong Provincial Key Laboratory of Horticultural Machinery and Equipment/China, Nanjing Research Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs/China 2. College of Mechanical and Electronic Engineering, Shandong Agricultural University, /China, Shandong Provincial Key Laboratory of Horticultural Machinery and Equipment/China
Abstract
This paper proposed a method of seed potato buds recognition based on improved YOLOv3-tiny. K-means clustering based on IoU is used to obtain the anchor box that meets the size of buds. Mosaic online data enhancement is used to increase image diversity and model generalization ability. The CIoU bounding box regression loss function is introduced to improve the regression effect of buds recognition. The results show that the precision (P), the recall (R), the average precision (AP), and the F1 score of the model for seed potato buds recognition are 88.33%, 85.97%, 91.18% and 87.13% respectively. The real-time recognition speed of seed potato buds on the embedded platform NVIDIA Jetson Nano can reach 40FPS. The method proposed in this paper can meet the needs of real-time recognition of seed potato buds on the embedded platform.
Publisher
INMA Bucharest-Romania
Subject
Industrial and Manufacturing Engineering,Mechanical Engineering,Food Science
Reference17 articles.
1. Coates, A., Ng, A. Y., (2012), Learning Feature Representations with K-means, Lecture Notes in Computer Science, Vol. 7700, pp. 561-580, Berlin/Germany. 2. Li, T., Yang, M., Zhang, X., et al., (2020), Potato Production Technology and Difference of Mechanization Level in Northwest China (西北地区马铃薯机械化生产技术与差异性研究), Transactions of the Chinese Society for Agricultural Machinery, Vol. 51, Issue s1, pp. 307-313, Beijing/China. 3. Li, W., Zhang, Y., Mo, J., et al., (2020), Detection of Pedestrian and Agricultural Vehicles in Field Based on Improved YOLOv3-tiny (基于改进YOLOv3-tiny的田间行人与农机障碍物检测), Transactions of the Chinese Society for Agricultural Machinery, Vol. 51, Issue s1, pp.1-8, Shanghai/China. 4. Li, Y., Li, T., Niu, Z., et al., (2018), Potato bud eyes recognition based on three-dimensional geometric features of color saturation(基于色饱和度三维几何特征的马铃薯芽眼识别), Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), Vol. 34, Issue 24, pp. 158 -164, Shandong/China. 5. Li, Z., Wen, X., Lv, J., et al., (2019), Analysis and prospect of research progress on key technologies and equipment of mechanization of potato planting (马铃薯种植机械化关键技术与装备研究进展分析与展望), Transactions of the Chinese Society for Agricultural Machinery, Vol. 50, Issue3, pp. 1-16, Hebei/China.
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
|
|