Deep Learning-Based Multiple Droplet Contamination Detector for Vision Systems Using a You Only Look Once Algorithm

被引:1
作者
Kim, Youngkwang [1 ]
Kim, Woochan [1 ]
Yoon, Jungwoo [1 ]
Chung, Sangkug [1 ]
Kim, Daegeun [2 ]
机构
[1] Myongji Univ, Dept Mech Engn, Yongin 17058, South Korea
[2] Microsyst Inc, Yongin 17058, South Korea
关键词
object detection; classification; contamination detection; autonomous driving systems; machine leaning; NEURAL-NETWORKS;
D O I
10.3390/info15030134
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper presents a practical contamination detection system for camera lenses using image analysis with deep learning. The proposed system can detect contamination in camera digital images through contamination learning utilizing deep learning, and it aims to prevent performance degradation of intelligent vision systems due to lens contamination in cameras. This system is based on the object detection algorithm YOLO (v5n, v5s, v5m, v5l, and v5x), which is trained with 4000 images captured under different lighting and background conditions. The trained models showed that the average precision improves as the algorithm size increases, especially for YOLOv5x, which showed excellent efficiency in detecting droplet contamination within 23 ms. They also achieved an average precision (mAP@0.5) of 87.46%, recall (mAP@0.5:0.95) of 51.90%, precision of 90.28%, recall of 81.47%, and F1 score of 85.64%. As a proof of concept, we demonstrated the identification and removal of contamination on camera lenses by integrating a contamination detection system and a transparent heater-based cleaning system. The proposed system is anticipated to be applied to autonomous driving systems, public safety surveillance cameras, environmental monitoring drones, etc., to increase operational safety and reliability.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research
    Agatonovic-Kustrin, S
    Beresford, R
    [J]. JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS, 2000, 22 (05) : 717 - 727
  • [2] Removal of spoiling materials from solar panel surfaces by applying surface acoustic waves
    Alagoz, Serkan
    Apak, Yasin
    [J]. JOURNAL OF CLEANER PRODUCTION, 2020, 253
  • [3] Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
    Alzubaidi, Laith
    Zhang, Jinglan
    Humaidi, Amjad J.
    Al-Dujaili, Ayad
    Duan, Ye
    Al-Shamma, Omran
    Santamaria, J.
    Fadhel, Mohammed A.
    Al-Amidie, Muthana
    Farhan, Laith
    [J]. JOURNAL OF BIG DATA, 2021, 8 (01)
  • [4] [Anonymous], 2016, Road traffic deaths
  • [5] Bayer H., 2022, P 33 FORUM BAUINFORM, DOI [10.14459/2022md1686600, DOI 10.14459/2022MD1686600]
  • [6] Bellis E., 2008, National Motor Vehicle Crash Causation Survey (NMVCCS) SAS Analytical Users Manual, P154
  • [7] Bengio Yoshua, 2007, Large Scale Kernel Machines, DOI DOI 10.7551/MITPRESS/7496.003.0016
  • [8] MCS-YOLO: A Multiscale Object Detection Method for Autonomous Driving Road Environment Recognition
    Cao, Yining
    Li, Chao
    Peng, Yakun
    Ru, Huiying
    [J]. IEEE ACCESS, 2023, 11 : 22342 - 22354
  • [9] Dabral S., 2014, P 2014 IEEE 57 INT M
  • [10] MSFT-YOLO: Improved YOLOv5 Based on Transformer for Detecting Defects of Steel Surface
    Guo, Zexuan
    Wang, Chensheng
    Yang, Guang
    Huang, Zeyuan
    Li, Guo
    [J]. SENSORS, 2022, 22 (09)