基于改进Multi-ResUnet算法的黏结集料图像分割方法
CSTR:
作者:
作者单位:

1.长安大学 信息工程学院,陕西 西安 710064;2.安徽科力信息产业有限责任公司 智能交通安徽省重点实验室,安徽 合肥 230088

作者简介:

郝雪丽(1987—),女,高级工程师,工学博士,主要研究方向为道路交通智能检测、交通大数据挖掘与分析。E-mail: xuelihao_lucky@126.com

通讯作者:

李 伟(1981—),男,教授,博士生导师,工学博士,主要研究方向为机器学习与数据挖掘技术、智能化检测仪器制造技术。E-mail: grandy@chd.edu.cn

中图分类号:

U414

基金项目:

国家自然科学基金(51908059,52178407,51978071);中央高校基本科研业务费专项资金(300102240206,300102249301)


Image Segmentation Method for Cohesive Aggregates Based on Improved Multi-ResUnet Algorithm
Author:
Affiliation:

1.School of Information Engineering, Chang’an University, Xi’an 710064,China;2.Anhui Key Laboratory of Intelligent Transportation, Anhui Keli Information Industry Co., Ltd., Hefei 230088,China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [20]
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    为提高黏结集料图像的分割精度,提出了基于Inception网络与残差连接优化的黏结集料图像分割模型(Multi-ResUnet模型)。利用实验室自主研发的集料三维特性分析系统V3.0对黏结集料图像进行采集,并建立图像分割模型样本集,然后采用图像分割模型对样本集进行训练。结果表明:相较于分水岭算法和Unet模型,该图像分割模型的精确率分别提升了30.46%和2.11%,召回率分别提升了4.68%和1.85%,准确率分别提升了25.95%和2.47%。

    Abstract:

    In order to improve the image segmentation accuracy for cohesive aggregates, a image segmentation model (Multi-ResUnet model)based on Inception network and residual connection optimization was proposed. The three-dimensional aggregate characterization system V3.0 developed by the laboratory itself was used to collect the images of cohesive aggregates and the sample set of the image segmentation model was created. Then, the image segmentation model was used to train the sample set. It is shown that compared with the Watershed algorithm and Unet model,the image segmentation model improves 30.46% and 2.11% in precision, 4.68% and 1.85% in recall, and 25.95% and 2.47% in accuracy, respectively.

    参考文献
    [1] 丛林,谭乐,吴敏,等.基于集料特性的沥青混合料长期抗滑性能衰减模型[J].同济大学学报(自然科学版),2019,47(5):668.
    [2] SU D, YAN W M. Quantification of angularity of general-shape particles by using Fourier series and a gradient-based approach[J]. Construction and Building Materials, 2018, 161: 547.
    [3] ARAUJO S, BICALHO V, TRISTAO A. Use of digital image analysis combined with fractal theory to determine particle morphology and surface texture of quartz sands[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2017, 9(6): 1131.
    [4] 丁旭东, 耿超, 崔珊珊. 基于结构光的粗集料颗粒粒径计算方法研究[J]. 现代交通技术, 2018, 15(3): 9.
    [5] 裴莉莉,孙朝云,户媛姣.基于多特征因子的路用集料粒径计算神经网络模型[J].华南理工大学学报(自然科学版), 2020, 48(6): 77.
    [6] ZHANG Guoying, LIU Guanzhou, ZHU Hong. Segmentation algorithm of complex ore images based on templates transformation and reconstruction[J]. International Journal of Minerals, Metallurgy, and Materials, 2011, 18(4): 385.
    [7] AMANKWAH A, ALDRICH C. Automatic ore image segmentation using mean shift and Watershed transform[C]//Proceedings of the 21st International Conference on Radioelektronika 2011. Brno: IEEE, 2011: 978-981.
    [8] MALLADI S R S P, RAM S, RODRIGUEZ J J. Superpixels using morphology for rock image segmentation[C]//2014 IEEE Southwest Symposium on Image Analysis and Interpretation. San Diego:[s.n.], 2014: 145-148.
    [9] SULAIMAN M, SINNAKAUDAN S K, NG S F, et al. Application of automated grain sizing technique (AGS) for bed load samples at Rasil River: a case study for supply limited channel[J]. Catena,2014,121: 330.
    [10] XU Yazhi, ZHENG Chuanfeng, FENG Yupeng, et al. Low-temperature cohesive and adhesive strength testing of contact surface between bitumen and mineral aggregates by image analysis[J]. Construction and Building Materials, 2018, 183: 95.
    [11] WANG R, ZHANG W, SHAO L. Research of ore particle size detection based on image processing[C]//Chinese Intelligent Systems Conference. Singapore: Springer, 2018: 505-514.
    [12] LI Y, DUAN Y Y. Intelligent computing methodologies[M]. Berlin:Springer, 2018.
    [13] 满新耀, 易强, 邹晓明. 基于数字图像处理技术的沥青混合料内部粗集料接触状态分析[J]. 西部交通科技, 2020(2): 5.
    [14] RAJAN B, SINGH D. Quantify effects of stage crushing on dimensional distribution of basaltic aggregates using image technique[J]. International Journal of Pavement Research and Technology, 2019, 12(5): 497.
    [15] MA Xiqi, ZHANG Pengyu, MAN Xiaofei, et al. A new belt ore image segmentation method based on the convolutional neural network and the image-processing technology[J]. Minerals, 2020, 10(12): 1115.
    [16] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[M]. Berlin:Springer, 2015.
    [17] SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 1-9.
    [18] 郝雪丽,孙朝云,耿方圆. 基于三维点云数据的集料颗粒棱角性量化评价[J]. 华南理工大学学报(自然科学版), 2021, 49(1): 142.
    [19] PEI L, SUN Z, YU T, et al. Pavement aggregate shape classification based on extreme gradient boosting[J]. Construction and Building Materials, 2020, 256:119356.
    [20] LIU Hanye, SUN Zhaoyun, LI Wei, et al. Evaluating angularity of coarse aggregates using the virtual cutting method based on 3D point cloud images[J]. IEEE Access, 2020, 8:143241.
    相似文献
    引证文献
引用本文

郝雪丽,李玉峰,裴莉莉,李伟,石丽,曹磊.基于改进Multi-ResUnet算法的黏结集料图像分割方法[J].同济大学学报(自然科学版),2022,50(5):741~749

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-06-15
  • 在线发布日期: 2022-06-07
文章二维码