Volume 50 Issue 1
Jan.  2024
Turn off MathJax
Article Contents
Article Navigation >  Journal of Mine Automation  > 2024  >  50(1): 49-56, 114
GU Qinghua, SU Cunling, WANG Qian, et al. A multi-target road detection model in a low-light environment in an open-pit mining area based on hyperbolic embedding[J]. Journal of Mine Automation，2024，50（1）：49-56, 114.  doi: 10.13272/j.issn.1671-251x.2023060021
Citation: GU Qinghua, SU Cunling, WANG Qian, et al. A multi-target road detection model in a low-light environment in an open-pit mining area based on hyperbolic embedding[J]. Journal of Mine Automation，2024，50（1）：49-56, 114.  doi: 10.13272/j.issn.1671-251x.2023060021
shu

A multi-target road detection model in a low-light environment in an open-pit mining area based on hyperbolic embedding

doi: 10.13272/j.issn.1671-251x.2023060021
  • 1.

    School of Resource Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China

  • 2.

    Xi'an Key Laboratory of Industrial Perceptual Computing and Decision, Xi'an University of Architecture and Technology, Xi'an 710055, China

  • 3.

    The Department of Computer, Mathematics and Physical Science Sul Ross State University, Alpine, TX 79830, USA

  • Received Date: 2023-06-07
  • Rev Recd Date: 2024-01-03
    • Available Online: 2024-01-31
    Abstract
  • The environment of open-pit mines is distinctive, and the conditions of the roads in them are complex and constantly changing. Insufficient lighting in the area being mined can make it challenging to identify and position multiple targets on the roads. This, in turn, affects the results of detection and poses serious risks to the safe operation of uncrewed mining trucks.Currently available models to identify obstacles on roads cannot accommodate the impact of poor lighting, and thus, yield inaccurate results. They also have significant shortcomings in identifying small obstacles in the mining area. In this study, we develop a multi-target model of detection for the dark/light environment of an open-pit mine using hyperbolic embedding to address the above-mentioned issues. We introduce the Retinex-Net convolutional neural network to the image preprocessing stage of the detection model to enhance dark images and improve their clarity. To address the issue of an excessively large number of features in the dataset without a clear preference for focus, we incorporate the global attention mechanism into the improved process of feature extraction. This enabled the collection of critical feature-related information in three dimensions. Finally, we incorporate a fully connected hyperbolic layer into the prediction stage of the model to minimize feature loss and prevent overfitting. The results of experiments to verify the proposed model showed that ① it could reliably classify and accurately identify large-scale targets in the low-light environment of the open-pit mining area, and was able to highly accurately identify mining trucks and small vehicles over long distances. It could also accurately identify and locate scaled targets, including pedestrians, such that this satisfies meeting the safety-related requirements of uncrewed mining trucks operating in diverse environments.② The model achieved an accuracy of detection of 98.6% while maintaining a speed of 51.52 frames/s, where this was 20.31%, 18.51%, 10.53%, 8.39%, and 13.24% higher than the accuracies of the SSD, YOLOv4, YOLOv5, YOLOx, and YOLOv7, respectively. Its accuracy of detection of pedestrians, mining trucks, and excavators on mining roads exceeded 97%.

     

    • FullText(HTML)
  • loading
    • References(30)
  • [1]
    ZHANG Shifeng,WEN Longyin,BIAN Xiao,et al. Occlusion-aware R-CNN:detecting pedestrians in a crowd[C]. European Conference on Computer Vision,Munich,2018. DOI: 10.1007/978-3-030-01219-9_39.
    [2]
    LI Jianan,LIANG Shengmei,XU Tingfa,et al. Scale-aware fast R-CNN for pedestrian dettion[J]. IEEE Transactions on Multimedia,2018,20(4):985-996.
    [3]
    CHENG Bowen,WEI Yunchao,SHI Honghui,et al. Revisiting R-CNN:on awakening the classification power of faster R-CNN[C]. European Conference on Computer Vision,Munich,2018:8-14.
    [4]
    秦振,李学伟,刘宏哲. 基于改进SSD的鲁棒小目标检测算法[J]. 东北师大学报(自然科学版),2023,55(4):59-66.

    QIN Zhen,LI Xuewei,LIU Hongzhe. Robust small target detection algorithm based on improved SSD[J]. Journal of Northeast Normal University(Natural Science Edition),2023,55(4):59-66.
    [5]
    FU Chengyang,LIU Wei,RANGA A,et al. DSSD:deconvolutional single shot detector[Z/OL]. arXiv,2017. https://arxiv.org/abs/1701.06659.
    [6]
    LI Z X,ZHOU Fuqiang. FSSD:feature fusion single shot multibox detector[Z/OL]. arXiv E-Prints,2017. https://doi.org/10.48550/arXiv.1712.00960.
    [7]
    REDMON J,DIVVALA S,GIRSHICK R,et al. You only look once:unified,real-time object detection[C]. IEEE International Conference on Computer Vision,Los Alamitos,2016:779-788.
    [8]
    REDMON J,FARHADI A. Yolo9000:better,faster,stronger[C]. IEEE Conference on Computer Vision and Pattern Recognition,Honolulu,2017:6517-6525.
    [9]
    REDMON J,FARHADI A. Yolov3:an incremental improvment[Z/OL]. arXiv E-Prints,2018. https://arxiv.org/abs/1804.02767.
    [10]
    BOCHKOVSKIY A,WANG C Y,LIAO H Y M. Yolov4:optimal speed and accuracy of object detection[Z/OL]. arXiv E-Prints,2020. https://arxiv.org/abs/2004.10934.
    [11]
    YAN Mingyang,SUN Jianbo. A dim-small target real-time detection method based on enhanced YOLO[C]. IEEE International Conference on Electrical Engineering,Big Data and Algorithms,Changchun,2022:567-571.
    [12]
    LIU Wei,ANGUELOV D,ERHAN D,et al. SSD:single shot multibox detector[C]. European Conference on Computer Vision,Cham,2016:21-37.
    [13]
    ZHANG Sheng,WANG Xu,LI Ping,et al. An improved YOLO algorithm for rotated object detection in remote sensing images [C]. IEEE 4 th Advance Information Management,Communicates,Electronic and Automation Control Conference,Chongqing,2021:840-845.
    [14]
    MATTHIES L,RANKIN A. Negative obstacle detection by thermal signature[C]. IEEE/RSJ International Conference on Intelligent Robots and Systems,Las Vegas,2003. DOI: 10.1109/IROS.2003.1250744.
    [15]
    SVENNINGSSON P,FIORANELLI F,YAROVOY A. Radar-pointGNN:graph based object recognition for unstructured radar point-cloud data[C]. IEEE Radar Conference,Atlanta,2021. DOI: 10.1109/RadarConf2147009.2021.9455172.
    [16]
    KUMAR R,JAYASHANKAR S. Radar and camera sensor fusion with ROS for autonomous driving[C]. 2019 Fifth International Conference on Image Information Processing,Shimla,2019:568-573.
    [17]
    JIN Yi,KUANG Yongshao,HOFFMANN M,et al. Radar and lidar deep fusion:providing doppler contexts to time-of-flight lidar[J]. IEEE Sensors Journal,2023,23(20):25587-25600. doi: 10.1109/JSEN.2023.3313093
    [18]
    BORJI A,ITTI L. State-of-the-art in visual attention modeling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(1):185-207. doi: 10.1109/TPAMI.2012.89
    [19]
    KUANG Hulin,ZHANG Xianshi,LI Yongjie,et al. Nighttime vehicle detection based on bio-inspired image enhancement and weighted score-level feature fusion[J]. IEEE Transactions on Intelligent Transportation Systems,2017,18:927-936. doi: 10.1109/TITS.2016.2598192
    [20]
    KAEWTRAKULPONG P,BOWDEN R. An improved adaptive background mixture model for real-time tracking with shadow detection[C]. Processing of European Workshop Advanced Video Based Surveillance Systems,2002. DOI: 10.1007/978-1-4615-0913-4_11.
    [21]
    WANG C Y,LIAO H Y,YEH I H,et al. CSPNet:a new backbone that can enhance learning capability of CNN[C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops,Seattle,2020:1571-1580.
    [22]
    HE Kaiming,ZHANG Xiangyu,REN Shaoping,et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence,2015,37(9):1904-1916.
    [23]
    LIN T Y,DOLLAR P,GIRSHICK R,et al. Feature pyramid networks for object detection[C]. IEEE Conference on Computer Vision and Pattern Recognition,Honolulu,2017:936-944.
    [24]
    HU Jianfang,SUN Jiangxin,LIN Zihang,et al. APANet:auto-path aggregation for future instance segmentation prediction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(7):3386-3403.
    [25]
    WEI Chen,WANG Wenjing,YANG Wenhan,et al. Deep retinex decomposition for low-light enhancement[J]. arXiv E-Prints,2018. DOI: 10.48550/arXiv.1808.04560.
    [26]
    李正龙,王宏伟,曹文艳,等. 基于含噪Retinex模型的煤矿低光照图像增强方法[J]. 工矿自动化,2023,49(4):70-77.

    LI Zhenglong,WANG Hongwei,CAO Wenyan,et al. A method for enhancing low light images in coal mines based on Retinex model containing noise[J]. Journal of Mine Automation,2023,49(4):70-77.
    [27]
    LIU Yichao,SHAO Zongru,HOFFMANN N. Global attention mechanism:retain information to enhance channel-spatial interactions[J]. arXiv E-Prints,2021. DOI: 10.48550/arXiv.2112.05561.
    [28]
    LIN H,TEGMARK M,TEGMARK M E. Critical behavior in physics and probabilistic formal languages[J]. Entropy,2019,19(7):299.
    [29]
    KATAYAMA K,MAINA E W. Indexing method for hierarchical graphs based on relation among interlacing sequences of eigenvalues[J]. Ipsj Journal,2015,56(2):210-220.
    [30]
    BRONSTEIN M M,BRUNA J,LECUN Y,et al. Geometric deep learning:going beyond euclidean data[J]. IEEE Signal Processing Magazine,2017. DOI: 10.1109/msp.2017.2693418.
    • Relative Articles
    • Supplements(0)
    • Cited By
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(8)  / Tables(5)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (166) PDF downloads(54) Cited by()
    Proportional views
    Related

    苏ICP备 05016349号-2

    Supported by: Beijing Renhe Information Technology Co. Ltd.  Visits：    

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return