您好，欢迎访问四川省农业科学院 机构知识库！

YOLOC-tiny: a generalized lightweight real-time detection model for multiripeness fruits of large non-green-ripe citrus in unstructured environments

文献类型： 外文期刊

作者： Tang, Zuoliang 1 ; Xu, Lijia 1 ; Li, Haoyang 1 ; Chen, Mingyou 3 ; Shi, Xiaoshi 1 ; Zhou, Long 1 ; Wang, Yuchao 1 ; Wu, Zhijun 1 ; Zhao, Yongpeng 1 ; Ruan, Kun 2 ; He, Yong 4 ; Ma, Wei 5 ; Yang, Ning 6 ; Luo, Lufeng 3 ; Qiu, Yunqiao 7 ;

作者机构： 1.Sichuan Agr Univ, Coll Mech & Elect Engn, Yaan, Peoples R China

2.Sichuan Agr Univ, Coll Resources, Chengdu, Peoples R China

3.Foshan Univ, Sch Mechatron Engn & Automat, Foshan, Peoples R China

4.Zhejiang Univ, Coll Biosyst Engn & Food Sci, Hangzhou, Peoples R China

5.Chinese Acad Agr Sci, Inst Urban Agr, Chengdu, Peoples R China

6.Jiangsu Univ, Sch Elect & Informat Engn, Zhenjiang, Peoples R China

7.Sichuan Acad Agr Machinery Sci, Chengdu, Peoples R China

关键词： non-green-ripe citrus; multiripeness fruits; YOLOv7; EfficientNet; CBAM; agricultural robot

期刊名称：FRONTIERS IN PLANT SCIENCE （ 影响因子：4.1； 五年影响因子：5.3 ）

ISSN： 1664-462X

年卷期： 2024 年 15 卷

页码：

收录情况： SCI

摘要： This study addresses the challenges of low detection precision and limited generalization across various ripeness levels and varieties for large non-green-ripe citrus fruits in complex scenarios. We present a high-precision and lightweight model, YOLOC-tiny, built upon YOLOv7, which utilizes EfficientNet-B0 as the feature extraction backbone network. To augment sensing capabilities and improve detection accuracy, we embed a spatial and channel composite attention mechanism, the convolutional block attention module (CBAM), into the head's efficient aggregation network. Additionally, we introduce an adaptive and complete intersection over union regression loss function, designed by integrating the phenotypic features of large non-green-ripe citrus, to mitigate the impact of data noise and efficiently calculate detection loss. Finally, a layer-based adaptive magnitude pruning strategy is employed to further eliminate redundant connections and parameters in the model. Targeting three types of citrus widely planted in Sichuan Province-navel orange, Ehime Jelly orange, and Harumi tangerine-YOLOC-tiny achieves an impressive mean average precision (mAP) of 83.0%, surpassing most other state-of-the-art (SOTA) detectors in the same class. Compared with YOLOv7 and YOLOv8x, its mAP improved by 1.7% and 1.9%, respectively, with a parameter count of only 4.2M. In picking robot deployment applications, YOLOC-tiny attains an accuracy of 92.8% at a rate of 59 frames per second. This study provides a theoretical foundation and technical reference for upgrading and optimizing low-computing-power ground-based robots, such as those used for fruit picking and orchard inspection.

  • 相关文献
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：四川省农业科学院

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