基于YOLOv3的建筑工地目标检测研究
Research on Construction Site Target Detection Based on YOLOv3

DOI: 10.12677/CSA.2021.1111283, PP. 2788-2794

Keywords: 目标检测，建筑工地场景，YOLOv3，Noise2noise
Object Detection, Construction Site Scene, YOLOv3, Noise2noise

Full-Text   Cite this paper   Add to My Lib

Abstract:

随着智慧工地的产生和发展，建筑工地施工现场各类监测技术的要求日益提高，为了更好地监测施工现场各类行为是否符合规范需要提高目标检测算法的精确度。本文为了更准确地检测建筑工地场景下的真实图像，采用MOCS数据集验证目标检测效果。首先用无监督的深度学习去噪网络Noise2noise进行去噪，其次将去噪后的图像送入深度学习网络YOLOv3进行目标检测。经过去噪后的图像目标检测的效果有一定的提升。
With the emergence and development of smart construction sites, the requirements of various monitoring technologies on construction sites are increasing day by day. In order to better monitor the compliance of various behaviors on construction sites, the accuracy of target detection algorithms needs to be improved. In order to more accurately detect the real image in the construction site scene, this paper uses MOCS data set to verify the target detection effect. Firstly, Noise2noise, an unsupervised deep learning denoising network, is used for denoising. Secondly, the denoised images are sent to YOLOv3, a deep learning network for target detection. After denoising, the effect of image target detection is improved to some extent.

References

[1]	李瑞平, 杜瑞. 智慧工地管理平台在建筑工程中的应用探究[J]. 智能建筑与智慧城市, 2021(10): 60-61.
[2]	Ren, S., He, K., Girshick, R., et al. (2015) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Net-works. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149. https://doi.org/10.1109/TPAMI.2016.2577031
[3]	Redmon, J., Divvala, S., Girshick, R., et al. (2016) You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 779-788. https://doi.org/10.1109/CVPR.2016.91
[4]	Redmon, J. and Farhadi, A. (2016) YOLO9000: Better, Faster, Stronger. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 6517-6525. https://doi.org/10.1109/CVPR.2017.690
[5]	Redmon, J. and Farhadi, A. (2018) YOLOv3: An In-cremental Improvement.
[6]	Lehtinen, J., Munkberg, J., Hasselgren, J., et al. (2018) Noise2Noise: Learning Image Restoration without Clean Data. Proceedings of the 35th International Conference on Machine Learning, Stockholm, PMLR 80 2018.
[7]	刘迪, 贾金露, 赵玉卿, 钱育蓉. 基于深度学习的图像去噪方法研究综述[J]. 计算机工程与应用, 2021, 57(7): 1-13.
[8]	An, X.H., Zhou, L., Liu, Z.G., Wang, C.Z., Li, P.F. and Li, Z.W. (2021) Dataset and Benchmark for Detecting Moving Objects in Construction Sites. Automation in Construction, 122, Article ID: 103482. https://doi.org/10.1016/j.autcon.2020.103482

Full-Text