English

Journal of Chinese Agricultural Mechanization

Journal of Chinese Agricultural Mechanization ›› 2023, Vol. 44 ›› Issue (5): 170-175.DOI: 10.13733/j.jcam.issn.2095-5553.2023.05.023

Previous Articles     Next Articles

Online detection method of detecting crushing rate of soybean harvesters based on DeepLabV3+ network

Liu Shikun1, 2, Jin Chengqian1, Chen Man1, Yang Tengxiang1, Xu Jinshan1   

  • Online:2023-05-15 Published:2023-06-02

基于DeepLabV3+网络的机收大豆破碎率在线检测方法

刘士坤1, 2,金诚谦1,陈满1,杨腾祥1,徐金山1   

  1. 1. 农业农村部南京农业机械化研究所,南京市,210014; 2. 安徽农业大学工学院,合肥市,230036
  • 基金资助:
    国家重点研发计划项目(2021YFD2000503);国家自然科学基金(32171911);江苏省自然科学基金(BK20221188);现代农业产业技术体系建设专项资金项目(CARS—04—PS26)

Abstract: In view of the problem that the traditional online detection method of soybean combine crushing rate is timeconsuming and laborintensive by manual detection and is affected by subjective factors, an online detection method of the crushing rate of mechanically harvested soybean based on the DeepLabV3+ network was proposed. The online soybean image acquisition device was used to obtain the soybean image harvested by the combine harvester in realtime, and the images were labeled using the labeling software to construct the data set. To further improve the network training speed, the lightweight convolution network MobileNetV2 was selected to replace the Xception network in the backbone feature extraction network of the DeepLabV3+ network. In the prediction part, black edge cutting and splicing were used to improve the accuracy of image segmentation. The results showed that the comprehensive evaluation index F1 of broken grain identification in the soybean sample image of the test set based on the DeepLabV3+ network model was 89.49%, and the comprehensive evaluation index F1 of complete grain identification was 93.93%. The quantitative model of soybean crushing rate was established, and bench tests were carried out. The average relative error between the online detection method of soybean crushing rate and the average artificial detection result was 0.36%. This paper provides a reference for the online detection of the working quality of soybean combine harvester.

Key words: soybean combine, percent reduction, DeepLabV3+, neural network, semantic segmentation, broken grain

摘要: 针对传统大豆联合收获机破碎率在线检测方法以人工检测耗时耗力且受人为主观因素影响的问题,提出基于DeepLabV3+网络的机收大豆破碎率在线检测方法。利用大豆图像在线采集装置获取联合收获机实时收获的大豆图像,使用标注软件对图像进行标注,构建数据集。为进一步提高网络训练速度,在DeepLabV3+网络中主干特征提取网络选用轻量级卷积网络MobileNetV2替代网络Xception;在预测部分,采用加黑边裁剪拼接的方式,提高图像分割精度。试验结果表明:基于DeepLabV3+网络模型对测试集大豆样本图像中破碎籽粒识别的综合评价指标F1值为89.49%,完整籽粒识别的综合评价指标F1值为93.93%;建立破碎率量化模型,进行台架试验,采用本文提出大豆破碎率在线检测方法检测结果平均值与人工检测结果平均值相对误差0.36%;为大豆联合收获机作业质量在线检测提供参考。

关键词: 大豆联合收获机, 破碎率, DeepLabV3+, 神经网络, 语义分割, 破碎籽粒

CLC Number: