复杂温室环境中基于 YOLOv8 番茄模型的番茄识别方法

Agronomy Pub Date : 2024-08-12 DOI:10.3390/agronomy14081764
Shuhe Zheng, Xuexin Jia, Minglei He, Zebin Zheng, Tianliang Lin, Wuxiong Weng
{"title":"复杂温室环境中基于 YOLOv8 番茄模型的番茄识别方法","authors":"Shuhe Zheng, Xuexin Jia, Minglei He, Zebin Zheng, Tianliang Lin, Wuxiong Weng","doi":"10.3390/agronomy14081764","DOIUrl":null,"url":null,"abstract":"Tomatoes are a critical economic crop. The realization of tomato harvesting automation is of great significance in solving the labor shortage and improving the efficiency of the current harvesting operation. Accurate recognition of fruits is the key to realizing automated harvesting. Harvesting fruit at optimum ripeness ensures the highest nutrient content, flavor and market value levels, thus maximizing economic benefits. Owing to foliage and non-target fruits obstructing target fruits, as well as the alteration in color due to light, there is currently a low recognition rate and missed detection. We take the greenhouse tomato as the object of research. This paper proposes a tomato recognition model based on the improved YOLOv8 architecture to adapt to detecting tomato fruits in complex situations. First, to improve the model’s sensitivity to local features, we introduced an LSKA (Large Separable Kernel Attention) attention mechanism to aggregate feature information from different locations for better feature extraction. Secondly, to provide a higher quality upsampling effect, the ultra-lightweight and efficient dynamic upsampler Dysample (an ultra-lightweight and efficient dynamic upsampler) replaced the traditional nearest neighbor interpolation methods, which improves the overall performance of YOLOv8. Subsequently, the Inner-IoU function replaced the original CIoU loss function to hasten bounding box regression and raise model detection performance. Finally, the model test comparison was conducted on the self-built dataset, and the test results show that the mAP0.5 of the YOLOv8-Tomato model reached 99.4% and the recall rate reached 99.0%, which exceeds the original YOLOv8 model detection effect. Compared with faster R-CNN, SSD, YOLOv3-tiny, YOLOv5, and YOLOv8 models, the average accuracy is 7.5%, 11.6%, 8.6%, 3.3%, and 0.6% higher, respectively. This study demonstrates the model’s capacity to efficiently and accurately recognize tomatoes in unstructured growing environments, providing a technical reference for automated tomato harvesting.","PeriodicalId":7601,"journal":{"name":"Agronomy","volume":"41 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Tomato Recognition Method Based on the YOLOv8-Tomato Model in Complex Greenhouse Environments\",\"authors\":\"Shuhe Zheng, Xuexin Jia, Minglei He, Zebin Zheng, Tianliang Lin, Wuxiong Weng\",\"doi\":\"10.3390/agronomy14081764\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Tomatoes are a critical economic crop. The realization of tomato harvesting automation is of great significance in solving the labor shortage and improving the efficiency of the current harvesting operation. Accurate recognition of fruits is the key to realizing automated harvesting. Harvesting fruit at optimum ripeness ensures the highest nutrient content, flavor and market value levels, thus maximizing economic benefits. Owing to foliage and non-target fruits obstructing target fruits, as well as the alteration in color due to light, there is currently a low recognition rate and missed detection. We take the greenhouse tomato as the object of research. This paper proposes a tomato recognition model based on the improved YOLOv8 architecture to adapt to detecting tomato fruits in complex situations. First, to improve the model’s sensitivity to local features, we introduced an LSKA (Large Separable Kernel Attention) attention mechanism to aggregate feature information from different locations for better feature extraction. Secondly, to provide a higher quality upsampling effect, the ultra-lightweight and efficient dynamic upsampler Dysample (an ultra-lightweight and efficient dynamic upsampler) replaced the traditional nearest neighbor interpolation methods, which improves the overall performance of YOLOv8. Subsequently, the Inner-IoU function replaced the original CIoU loss function to hasten bounding box regression and raise model detection performance. Finally, the model test comparison was conducted on the self-built dataset, and the test results show that the mAP0.5 of the YOLOv8-Tomato model reached 99.4% and the recall rate reached 99.0%, which exceeds the original YOLOv8 model detection effect. Compared with faster R-CNN, SSD, YOLOv3-tiny, YOLOv5, and YOLOv8 models, the average accuracy is 7.5%, 11.6%, 8.6%, 3.3%, and 0.6% higher, respectively. This study demonstrates the model’s capacity to efficiently and accurately recognize tomatoes in unstructured growing environments, providing a technical reference for automated tomato harvesting.\",\"PeriodicalId\":7601,\"journal\":{\"name\":\"Agronomy\",\"volume\":\"41 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Agronomy\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/agronomy14081764\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Agronomy","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/agronomy14081764","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

番茄是一种重要的经济作物。实现番茄采收自动化对于解决劳动力短缺问题、提高现有采收作业效率具有重要意义。准确识别果实是实现自动化采收的关键。在最佳成熟期收获果实可确保最高的营养含量、风味和市场价值水平,从而实现经济效益最大化。由于叶片和非目标水果会遮挡目标水果,再加上光照会改变水果的颜色,目前识别率较低,存在漏检现象。我们以温室番茄为研究对象。本文提出了一种基于改进的 YOLOv8 架构的番茄识别模型,以适应复杂情况下番茄果实的检测。首先,为了提高模型对局部特征的敏感度,我们引入了 LSKA(Large Separable Kernel Attention)注意力机制,以聚合不同位置的特征信息,从而实现更好的特征提取。其次,为了提供更高质量的上采样效果,超轻量级高效动态上采样器 Dysample(一种超轻量级高效动态上采样器)取代了传统的近邻插值方法,从而提高了 YOLOv8 的整体性能。随后,Inner-IoU 函数取代了原来的 CIoU 损失函数,加速了边界框回归,提高了模型检测性能。最后,在自建数据集上进行了模型测试比较,测试结果表明,YOLOv8-Tomato 模型的 mAP0.5 达到 99.4%,召回率达到 99.0%,超过了原有 YOLOv8 模型的检测效果。与速度更快的 R-CNN、SSD、YOLOv3-tiny、YOLOv5 和 YOLOv8 模型相比,平均准确率分别提高了 7.5%、11.6%、8.6%、3.3% 和 0.6%。这项研究表明,该模型能够在非结构化种植环境中高效、准确地识别番茄,为番茄自动收获提供了技术参考。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Tomato Recognition Method Based on the YOLOv8-Tomato Model in Complex Greenhouse Environments
Tomatoes are a critical economic crop. The realization of tomato harvesting automation is of great significance in solving the labor shortage and improving the efficiency of the current harvesting operation. Accurate recognition of fruits is the key to realizing automated harvesting. Harvesting fruit at optimum ripeness ensures the highest nutrient content, flavor and market value levels, thus maximizing economic benefits. Owing to foliage and non-target fruits obstructing target fruits, as well as the alteration in color due to light, there is currently a low recognition rate and missed detection. We take the greenhouse tomato as the object of research. This paper proposes a tomato recognition model based on the improved YOLOv8 architecture to adapt to detecting tomato fruits in complex situations. First, to improve the model’s sensitivity to local features, we introduced an LSKA (Large Separable Kernel Attention) attention mechanism to aggregate feature information from different locations for better feature extraction. Secondly, to provide a higher quality upsampling effect, the ultra-lightweight and efficient dynamic upsampler Dysample (an ultra-lightweight and efficient dynamic upsampler) replaced the traditional nearest neighbor interpolation methods, which improves the overall performance of YOLOv8. Subsequently, the Inner-IoU function replaced the original CIoU loss function to hasten bounding box regression and raise model detection performance. Finally, the model test comparison was conducted on the self-built dataset, and the test results show that the mAP0.5 of the YOLOv8-Tomato model reached 99.4% and the recall rate reached 99.0%, which exceeds the original YOLOv8 model detection effect. Compared with faster R-CNN, SSD, YOLOv3-tiny, YOLOv5, and YOLOv8 models, the average accuracy is 7.5%, 11.6%, 8.6%, 3.3%, and 0.6% higher, respectively. This study demonstrates the model’s capacity to efficiently and accurately recognize tomatoes in unstructured growing environments, providing a technical reference for automated tomato harvesting.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
The Influence of Sowing Date on the Primary Yield Components of Maize Algorithm for Locating Apical Meristematic Tissue of Weeds Based on YOLO Instance Segmentation Unlocking Cassava Brown Streak Disease Resistance in Cassava: Insights from Genetic Variability and Combining Ability Effects of Spray Adjuvants on Droplet Deposition Characteristics in Litchi Trees under UAV Spraying Operations Synthesis, Herbicidal Activity, and Molecular Mode of Action Evaluation of Novel Quinazolinone—Phenoxypropionate Hybrids Containing a Diester Moiety
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1