河南农业科学 ›› 2023, Vol. 52 ›› Issue (10): 141-152.DOI: 10.15933/j.cnki.1004-3268.2023.10.015

• 农业信息与工程·农产品加工 • 上一篇    下一篇

基于改进U-Net 的不同容重小麦籽粒识别检测

吕宗旺1,2,王玉琦1,2,孙福艳1,2   

  1. (1.河南工业大学信息科学与工程学院,河南 郑州 450001;2.粮食信息处理与控制教育部重点实验室,河南 郑州 450001)
  • 收稿日期:2023-06-28 出版日期:2023-10-15 发布日期:2023-11-08
  • 通讯作者: 孙福艳(1979-),女,黑龙江海伦人,副教授,博士,主要从事信号与信息处理、混沌理论及应用、密码学等方向的教育工作。E-mail:fuyan_sun@126.com
  • 作者简介:吕宗旺(1979-),男,山东菏泽人,教授,硕士,主要从事粮食信息处理与控制、电子线路设计与智能控制等方向的教育工作。E-mail:zongwang_lyu@haut.deu.cn
  • 基金资助:
    国家重点研发计划课题(2017YFD0401004)

Identification and Detection of Wheat Kernels with Different Volume Weight Based on Improved U‑Net

LÜ Zongwang1,2,WANG Yuqi1,2,SUN Fuyan1,2   

  1. (1.College of Information Science and Engineering,Henan University of Technology,Zhengzhou 450001,China;2.Key Laboratory of Grain Information Processing and Control,Ministry of Education,Zhengzhou 450001,China)
  • Received:2023-06-28 Published:2023-10-15 Online:2023-11-08

摘要: 小麦质量等级检测过程中,容重是一项非常重要的指标。人工检测和传统图像处理方法在小麦质量等级检测方面存在设备昂贵、识别效率低等问题,需要进一步改进。采用自制3种等级小麦籽粒样品作为小麦容重数据集,针对小麦籽粒目标小、边缘分割不清晰等特点对U-Net网络进行改进。在主干网络上,采用残差堆叠模块来减少特征损失,在网络桥接部分嵌入CBAM注意力机制模块来加强对特征的进一步提取,在解码器部分嵌入自注意力机制模块,还原细节信息。结果表明,改进网络模型CBSA_U-Net 的平均交并比(MIoU)为81.5%,比U-Net 模型提升了1.8 百分点,相较于PSPNet、DeepLabv3+模型分别提升了4.2、3.3百分点。

关键词: 小麦, 质量等级, 籽粒识别, 容重, 残差模块, 注意力机制, U-Net模型, 分割

Abstract: Volume weight is a very important index in the process of wheat quality grade detection.Manual detection and traditional image processing methods have problems such as expensive equipment and low recognition efficiency in wheat quality grade detection,which need to be further improved.The self‑made three grades of wheat grain samples were used as the wheat volume weight dataset,and the U‑Net network was improved according to the characteristics of small grain targets and unclear edge segmentation.On the backbone network,the residual stacking module was used to reduce the feature loss,the CBAM attention mechanism module was embedded in the network bridging part to enhance the further extraction of the features,and the self‑attention mechanism module was embedded in the decoder part to restore the detail information. The results showed that MIoU of the improved network model CBSA_U‑Net was 81.5%,which was 1.8 percentage points higher than U‑Net model,4.2 percentage points higher than PSPNet and 3.3 percentage points higher than DeepLabv3+ model.

Key words: Wheat, Quality grade, Kernel identification Volume weight, Residual module, Attention mechanism, U?Net model, Segmentation

中图分类号: