All Issue

2025 Vol.27, Issue 5 Preview Page

Research Paper

Performance analysis of no-reference image quality assessment metrics for high-speed motion blur images in mobile tunnel scanning system

이동식 터널 스캐닝 시스템의 고속 모션 블러 이미지에 대한 무참조 이미지 품질 평가 지표 성능 분석

Chulhee Lee1
,
Dongku Kim1
,
Donggyou Kim2*
이 철희1
,
김 동구1
,
김 동규2*
1Senior Researcher, Dept. of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology
2Senior Research Fellow, Dept. of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology
1정회원, 한국건설기술연구원 지반연구본부 수석연구원
2정회원, 한국건설기술연구원 지반연구본부 선임연구위원
*Corresponding Author
30 September 2025. pp. 489-504
PDF XML Citation
Abstract

This study aims to address the issue of image quality degradation caused by motion blur (MB) in high-speed imaging of the mobile tunnel scanning system (MTSS) and to verify the effectiveness of no-reference image quality assessment (NR-IQA) metrics. For this purpose, a high-speed translational moving panel (HTMP) was developed, and a standardized ISO 12233 environment was employed to construct a high-speed motion blur (HSMB) dataset under various imaging conditions. Physical quality indicators, namely blurred edge width (BEW) and modulation transfer function 50 (MTF50), were measured, and their relationships with both conventional NR-IQA metrics (BRISQUE, NIQE, PIQE, CPBD) and deep learning-based metrics (DBCNN, ARNIQA) were quantitatively analyzed. The experimental results confirmed that as the travel speed increased and shutter exposure time lengthened, motion blur became more severe, leading to blurred image boundaries and the loss of detailed structures. In the correlation analysis, CPBD, a traditional knowledge-based NR-IQA metric, showed the highest correlation with the physical quality metrics. Furthermore, the deep learning-based metrics, DBCNN and ARNIQA, demonstrated significantly superior performance and proved to have very high reliability compared to the other traditional knowledge-based metrics. These results demonstrate that NR-IQA metrics can effectively quantify the image quality degradation in MTSS images. Specifically, this suggests that edge-based metrics could be utilized for real-time quality management in the field, while deep learning-based metrics are suitable tools for post-processing and precise performance verification.

Keywords
No-reference image quality assessment (NR-IQA)
Motion blur
High-speed translational moving panel (HTMP)
Mobile Tunnel scanning system (MTSS)

본 연구는 이동식 터널 스캐닝 시스템의 고속 촬영 과정에서 발생하는 모션 블러로 인한 이미지 품질 저하 문제를 파악하고, 무참조 이미지 품질 평가 지표(no-reference image quality assessment, NR-IQA)의 유효성을 검증하는 것을 목적으로 한다. 이를 위해 자체 개발한 고속 병진 이동 패널과 ISO 12233 표준 환경을 기반으로 다양한 촬영 조건에서 고속 모션 블러 데이터셋을 구축하였다. 물리적 품질 지표인 BEW (blurred edge width)와 MTF (modulation transfer function) 50을 활용하여 이미지 품질 변화를 정량적으로 측정하고, 이를 기준으로 전통적인 지식기반 NR-IQA 지표(BRISQUE, NIQE, PIQE, CPBD)와 딥러닝 기반 지표(DBCNN, ARNIQA)의 성능을 비교 분석하였다. 실험 결과, 이동 속도가 증가하고 셔터 노출 시간이 길어질수록 모션 블러가 심화되어 이미지 경계가 흐려지고 세부 구조가 손실되는 경향을 확인하였다. 상관관계 분석에서는 전통적인 지식기반 NR-IQA 지표 중 CPBD가 물리적 품질 지표와 가장 높은 상관성을 나타냈다. 딥러닝 기반 지표인 DBCNN과 ARNIQA는 다른 전통적인 지식 기반 지표들보다 월등히 우수한 성능을 나타내며 매우 높은 신뢰도를 입증하였다. 이러한 결과는 NR-IQA 지표가 MTSS 이미지의 품질 저하를 효과적으로 정량화할 수 있음을 보여준다. 특히, CPBD는 현장의 실시간 품질 관리에, 딥러닝 기반 지표인 DBCNN과 ARNIQA는 후처리 및 정밀 성능 검증에 적합한 도구로 활용될 수 있음을 시사한다.

키워드
무참조 이미지 품질 평가
모션 블러
고속 병진 이동 패널
이동식 터널 스캐닝 시스템
References
1

Agnolucci, L., Galteri, L., Bertini, M., Del Bimbo, A. (2024), “ARNIQA: Learning distortion manifold for image quality assessment”, Proceedings of the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, pp. 188-197.

10.1109/WACV57701.2024.00026
2

Artmann, U. (2013), “Image quality evaluation using moving targets”, Multimedia Content and Mobile Devices, Vol. 8667, pp. 398-409.

10.1117/12.2003027
3

Chen, W., Tan, X.Y., Yang, J. (2025), “Review of state-of-the-art in structural health monitoring of tunnel engineering”, Smart Underground Engineering, Vol. 1, No. 1, pp. 40-50.

10.1016/j.sue.2025.05.004
4

De, K., Masilamani, V. (2013), “Image sharpness measure for blurred images in frequency domain”, Procedia Engineering, Vol. 64, pp. 149-158.

10.1016/j.proeng.2013.09.086
5

Dinh, H., Wang, Q., Tu, F., Frymire, B., Mu, B. (2023), “Evaluation of motion blur image quality in video frame interpolation”, Electronic Imaging, Vol. 35, No. 8, pp. 262-1-262-5.

10.2352/EI.2023.35.8.IQSP-262
6

Giniatullin, A., Dmitrii, T., Elshin, L. (2024), “On the efficiency of the BRISQUE metric for assessing linearly blurred images when deconvoluted with 3x3 convolution matrices”, Proceedings of the Third International Conference on Optics, Computer Applications, and Materials Science (CMSD-III 2023), Vol. 13065, Dushanbe, Tajikistan, 130650U-1.

10.1117/12.3025069
7

Guo, J., Liu, P., Xiao, B., Deng, L., Wang, Q. (2024), “Surface defect detection of civil structures using images: Review from data perspective”, Automation in Construction, Vol. 158, 105186.

10.1016/j.autcon.2023.105186
8

Huang, H., Sun, Y., Xue, Y., Wang, F. (2017), “Inspection equipment study for subway tunnel defects by grey-scale image processing”, Advanced Engineering Informatics, Vol. 32, pp. 188-201.

10.1016/j.aei.2017.03.003
9

Koren, N. (2006), “The Imatest program: Comparing cameras with different amounts of sharpening”, Digital Photography II, Vol. 6069, 60690L.

10.1117/12.650848
10

Lee, C., Kim, D., Kim, D. (2025), “Performance verification of deep-learning based tunnel crack detection using no-reference image quality assessment”, Journal of Korean Tunnelling and Underground Space Association, Vol. 27, No. 4, pp. 287-304.

10.9711/KTAJ.2025.27.4.287
11

Liu, Y., Yeoh, J.K.W., Chua, D.K.H. (2020), “Deep learning-based enhancement of motion blurred UAV concrete crack images”, Journal of Computing in Civil Engineering, Vol. 34, No. 5, 04020028.

10.1061/(ASCE)CP.1943-5487.0000907
12

Masaoka, K. (2018), “Accuracy and precision of edge-based modulation transfer function measurement for sampled imaging systems”, IEEE Access, Vol. 6, pp. 41079-41086.

10.1109/ACCESS.2018.2856742
13

Mittal, A., Moorthy, A.K., Bovik, A.C. (2012), “No-reference image quality assessment in the spatial domain”, IEEE Transactions on Image Processing, Vol. 21, No. 12, pp. 4695-4708.

10.1109/TIP.2012.2214050
14

Mittal, A., Soundararajan, R., Bovik, A.C. (2013), “Making a completely blind image quality analyzer”, IEEE Signal Processing Letters, Vol. 20, No. 3, pp. 209-212.

10.1109/LSP.2012.2227726
15

Narvekar, N.D., Karam, L.J. (2011), “A no-reference image blur metric based on the cumulative probability of blur detection (CPBD)”, IEEE Transactions on Image Processing, Vol. 20, No. 9, pp. 2678-2683.

10.1109/TIP.2011.2131660
16

Pennada, S., Perry, M., McAlorum, J., Dow, H., Dobie, G. (2023), “Threshold-based Brisque-assisted deep learning for enhancing crack detection in concrete structures”, Journal of Imaging, Vol. 9, No. 10, 218.

10.3390/jimaging910021837888325PMC10607118
17

Venkatanath, N., Praneeth, D., Maruthi, C.B., Sumohana, S.C., Swarup, S.M. (2015), “Blind image quality evaluation using perception based features”, Proceedings of the Twenty First National Conference on Communications, Mumbai, India, pp. 1-6.

10.1109/NCC.2015.7084843
18

Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P. (2004), “Image quality assessment: From error visibility to structural similarity”, IEEE Transactions on Image Processing, Vol. 13, No. 4, pp. 600-612.

10.1109/TIP.2003.819861
19

Wu, Q., Li, H., Meng, F., Ngan, K.N., Zhu, S. (2015), “No reference image quality assessment metric via multi-domain structural information and piecewise regression”, Journal of Visual Communication and Image Representation, Vol. 32, pp. 205-216.

10.1016/j.jvcir.2015.08.009
20

Zhang, W., Ma, K., Yan, J., Deng, D., Wang, Z. (2020), “Blind image quality assessment using a deep bilinear convolutional neural network”, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 30, No. 1, pp. 36-47.

10.1109/TCSVT.2018.2886771
21

Zhu, H., Li, L., Wu, J., Dong, W., Shi, G. (2020), “MetaIQA: Deep meta-learning for no-reference image quality assessment”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, pp. 14143-14152.

10.1109/CVPR42600.2020.01415
Information
  • Publisher :Korean Tunneling and Underground Space Association
  • Publisher(Ko) :한국터널지하공간학회
  • Journal Title :Journal of Korean Tunnelling and Underground Space Association
  • Journal Title(Ko) :한국터널지하공간학회 논문집
  • Volume : 27
  • No :5
  • Pages :489-504
  • Received Date : 2025-09-08
  • Revised Date : 2025-09-23
  • Accepted Date : 2025-09-24
  • DOI :https://doi.org/10.9711/KTAJ.2025.27.5.489
Journal Informaiton Journal of Korean Tunnelling and Underground Space Association Journal of Korean Tunnelling and Underground Space Association
Online Submission & Review System
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close