您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Rapid Detection of Ripe Tomatoes in Unstructured Environments

文献类型： 外文期刊

作者： Qi, Jiangtao 1 ; Cong, Xv 1 ; Zhang, Weirong 1 ; Gao, Fangfang 1 ; Zhao, Bo 4 ; Guo, Hui 1 ;

作者机构： 1.Jilin Univ, Coll Biol & Agr Engn, Changchun, Peoples R China

2.Jilin Univ, Minist Educ, Key Lab Engn Bion, Changchun, Peoples R China

3.Jilin Univ, Weihai Inst Bion, Weihai, Peoples R China

4.Chinese Acad Agr Mechanizat Sci Grp Co Ltd, Beijing, Peoples R China

关键词： DBB heavy parameter; FasterNet; Global attention mechanism; Object detection; Tomato; Unstructured environments; YOLOv7

期刊名称：JOURNAL OF FIELD ROBOTICS （ 影响因子：5.2； 五年影响因子：7.5 ）

ISSN： 1556-4959

年卷期： 2025 年 42 卷 6 期

页码：

收录情况： SCI

摘要： To achieve efficient detection of ripe tomatoes in unstructured environments, this paper proposed an improved YOLOv7 rapid detection network model for ripe tomatoes. Firstly, the original YOLOv7 backbone network's CSP-Darknet53 structure was replaced by the FasterNet network structure to enhance model detection efficiency and reduce the parameters of the model. Secondly, the Global Attention Mechanism (GAM) was introduced to improve the tomato feature expression ability with a small increase in model parameters. Next, a Diverse Branch Block (DBB) module was integrated into the ELAN module in the head structure to improve the model's inference efficiency. Finally, the batch normalization layer gamma was selected as the parameter of the sparsity factor in the algorithm. The L1 regularization term was used to train the original model for sparsity, and the slim pruning algorithm was used for global channel pruning to compress the model size. The pruned model was retrained through model fine-tuning to adjust the detection accuracy to near the level before pruning. The experimental results show that the improved model has a mean average precision of 96.49%, which is basically unchanged compared to the original model. However, the model parameter count, the computation, and the model size were reduced by 52.16%, 56.84%, and 36.95%, respectively, resulting in a 32.09% increase in the recognition frame rate. Compared to similar object detection models, such as SSD, YOLOv3, YOLOv4, YOLOv5s, YOLOX, and YOLOv8, the Improved-YOLOv7 model reduced the parameter by 4.44% to 89.05%, computational complexity by 30.37% to 91.18%, and model size by 26.43% to 72.16%. This paper provided technical support for the recognition of ripe tomatoes in unstructured environments.

  • 相关文献

[1]Rapid Detection of Ripe Tomatoes in Unstructured Environments. Qi, Jiangtao,Cong, Xv,Zhang, Weirong,Gao, Fangfang,Guo, Hui,Qi, Jiangtao,Cong, Xv,Zhang, Weirong,Gao, Fangfang,Guo, Hui,Qi, Jiangtao,Cong, Xv,Zhang, Weirong,Gao, Fangfang,Guo, Hui,Zhao, Bo. 2025

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：中国农业科学院

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