건설현장 내 객체검출 정확도 향상을 위한 저조도 영상 강화 기법에 관한 연구
A Study on Low-Light Image Enhancement Technique for Improvement of Object Detection Accuracy in Construction Site
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
AI영상 기반 건설현장 안전관리 모니터링 시스템 개발 및 적용하는 추세에 다양한 환경변화에 따른 위험객체 탐지 딥러닝 모델 개발에 많은 연구적 관심이 쏟아지고 있다. 여러 환경 변화요인 중 저조도 조건에서 객체 검출 모델의 정확도는 현저히 감소하며, 저조도 환경을 고려한 학습을 수행하더라도 일관적인객체 탐지 정확도를 확보할 수 없다. 이에 따라 저조도 영상을 강화하는 영상 전처리 기술의 필요성이 대두된다. 따라서, 본 논문은 취득된 건설 현장 영상 데이터를 활용하여 다양한 딥러닝 기반 저조도 영상 강화 모델(GLADNet, KinD, LLFlow, Zero-DCE)을 학습하고, 모델별 저조도 영상 강화 성능을 비교 검증실험을 진행하였다. 저조도 강화된 영상을 시각적으로 검증하였고, 영상품질 평가 지수(PSNR, SSIM, Delta-E)를 도입하여 정량적으로 분석하였다. 실험 결과, GLADNet의 저조도 영상 강화 성능이 정량·정성적 평가에서 우수한 결과를 보여줬으며, 저조도 영상 강화 모델로 적합한 것으로 분석되었다. 향후 딥러닝 기반 객체 검출 모델에 저조도 영상 강화 기법이 전처리 단계로 적용한다면, 저조도 환경에서 일관된 객체 검출 성능을 확보할 것으로 예상된다.
Abstract
There is so much research effort for developing and implementing deep learning-based surveillance systems to manage health and safety issues in construction sites. Especially, the development of deep learning-based object detection in various environmental changes has been progressing because those affect decreasing searching performance of the model. Among the various environmental variables, the accuracy of the object detection model is significantly dropped under low illuminance, and consistent object detection accuracy cannot be secured even the model is trained using low-light images. Accordingly, there is a need of low-light enhancement to keep the performance under low illuminance. Therefore, this paper conducts a comparative study of various deep learning-based low-light image enhancement models (GLADNet, KinD, LLFlow, Zero-DCE) using the acquired construction site image data. The low-light enhanced image was visually verified, and it was quantitatively analyzed by adopting image quality evaluation metrics such as PSNR, SSIM, Delta-E. As a result of the experiment, the low-light image enhancement performance of GLADNet showed excellent results in quantitative and qualitative evaluation, and it was analyzed to be suitable as a low-light image enhancement model. If the low-light image enhancement technique is applied as an image preprocessing to the deep learning-based object detection model in the future, it is expected to secure consistent object detection performance in a low-light environment.
참고문헌 (9)
- Frieden, B. R., "Picture processing and digital filtering", pp.177~248 (2005)
- Guo, C., "Zero-reference deep curve estimation for low-light image enhancement", Proceedings of the IEEE, 2020, 1780~1789
- Na, J. H., "A study on the performance improvement technique for Instance segmentation of objects in the construction site", Proceedings of the KAIS Korea Academia-Industrial cooperation Society Conference, pp.983~986 (2022)
- Na, J. H., "Building-up and Feasibility Study of Image Dataset of Field Construction Equipments for AI Training", KSCE Journal of Civil and Environmental Engineering Research, 43(1), pp.99~107 (2023)
- Robertson, A. R., "Historical development of CIE recommended color difference equations", Color Research & Application, 15(3), pp.167~170 (1990)
- Wang, W., "Gladnet: Low-light enhancement network with global awareness", 2018 13th IEEE international conference on automatic face & gesture recognition (FG 2018), pp.751~755 (2018), IEEE
- Wang, Y., "Low-light image enhancement with normalizing flow", Proceedings of the AAAI Conference on Artificial Intelligence, 36(3), pp.2604~2612 (2022)
- Wang, Z., "Image quality assessment : from error visibility to structural similarity", IEEE transactions on image processing, 13(4), pp.600~612 (2004)
- Zhang, Y., "Kin -dling the darkness: A practical low-light image enhancer", Proceedings of the 27th ACM international conference on multimedia, pp.1632~1640 (2019)