基于暗通道先验知识和ResNet网络的焦炭智能装载溢出检测方法
DOI:
作者:
作者单位:

1.河南工业大学信息科学与工程学院;2.河南工业大学人工智能与大数据学院

作者简介:

通讯作者:

中图分类号:

TP391.41

基金项目:

河南省级科技研发计划联合基金(应用攻关类)(222103810043)


A coke intelligent loading overflow detection method based on dark channel prior knowledge and ResNet network
Author:
Affiliation:

School of Information Science and Engineering, Henan University of Technology

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    高粉尘环境下进行精准的焦炭溢出检测是实现焦炭智能装载的重要挑战之一。针对此问题,本文 提出一种基于暗通道先验知识和ResNet网络的焦炭智能装载溢出检测方法。首先,利用视频采集器获取焦炭装载场景视频信息,并对原始时间序列视频图像帧进行处理以获得下料口及装载器之间感兴趣区域;其次,提出利用暗通道先验知识方法对感兴趣区域进行处理,提升感兴趣区域中目标区域与无关区域之间对比度,以降低粉尘对后续检测模型的影响。再者,根据焦炭实际装载情况对感兴趣区域进行标注将溢出检测问题转化成二分类。最终,提出利用ResNet网络建模完成对模型的训练获得训练模型并在新采集焦炭装载过程中进行实验。实验证明本文的方法在新的数据上测试结果表现优异,整体的准确率达到86.81%,其中溢出类的精确度、召回率和F1分数分别为84.12%、 90.74%和 0.8730。并且在使用了暗通道先验算法处理数据后,溢出类的召回率上升了3.31%。

    Abstract:

    The accurate detection of coke overflow in high-dust environments is a pivotal challenge in achieving intelligent coke loading. This article proposes a method for the intelligent detection of coke loading overflow, which is based on dark channel prior knowledge and the ResNet network. The accurate detection of coke overflow in high-dust environments is a pivotal challenge in achieving intelligent coke loading. This article proposes a method for the intelligent detection of coke loading overflow, which is based on dark channel prior knowledge and the ResNet network.Secondly, the prior knowledge method of dark channels is employed to process the regions of interest. Enhancing the contrast between the target areas and irrelevant areas within the regions of interest, thereby mitigating the effects of dust on subsequent detection models.Moreover, the problem of overflow detection is transformed into a binary classification task by labeling the regions of interest based on the actual loading of coke. Finally, the ResNet network is utilized for modeling, enabling the completion of model training and experimentation during the loading process of newly acquired coke. The experimental results demonstrate that the proposed method exhibits promising performance on new data, achieving an overall accuracy of 86.81%. Specifically, the accuracy, recall, and F1 score for the overflow class are 84.12%, 90.74%, and 0.8730, respectively. Furthermore, the application of the dark channel prior algorithm in data processing results in a notable increase in the recall rate of the overflow class by 3.31%.

    参考文献
    相似文献
    引证文献
引用本文

解康战,侯惠芳,张自豪,等. 基于暗通道先验知识和ResNet网络的焦炭智能装载溢出检测方法[J]. 科学技术与工程, , ():

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:2024-03-26
  • 最后修改日期:2024-06-09
  • 录用日期:2024-07-09
  • 在线发布日期:
  • 出版日期:
×
亟待确认版面费归属稿件,敬请作者关注
《科学技术与工程》入选维普《中文科技期刊数据库》自然科学类期刊月度下载排行榜TOP10