Defogging Target Detection based on YOLOv4 and Deblurganv2
DOI:
https://doi.org/10.54691/sjt.v4i6.880Keywords:
Generative Adversarial Nets; DeblurGANv2; Coordinate Attention; ShuffleNet V2; Defogging Target Detection.Abstract
Aiming at the problem of low detection accuracy of existing object detection in fog and haze weather, a defogging object detection method based on DeblurGANv2 and YOLOv4 is proposed. In this method, the image enhancement algorithm in the generation countermeasure network DeblurGanv2 is added to the preprocessing module of YOLOv4 to preprocess the foggy image and retain the high-quality texture and color information of the image, At the same time, the lightweight neural network ShuffleNet V2 is used to replace the CSPDarkNet53 network used for backbone feature extraction in YOLOv4 to improve the speed of model mark detection. The experimental results show that the proposed method can reduce the problems of large color difference and fog residue, and the map value in the rest data set reaches 86.56%, It has achieved good results in the actual defogging target test.
Downloads
References
Liu W, ANGUELOV D, ERHAN D, et al. Ssd: Single shot multibox detector[C]//European Conference on Computer Vision, Springer, 2016: 21-37. DOI: https://doi.org/10.1007/978-3-319-46448-0_2
REDMON J, FARHADI A. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:779-788. DOI: https://doi.org/10.1109/CVPR.2016.91
REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//CVPR 2017:Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway: IEEE, 2017: 7263 -7271. DOI: https://doi.org/10.1109/CVPR.2017.690
Redmon J, Farhadi A. Yolov3: An incremental improvement[C]//IEEE conference on Computer Vision and Pattern Recognition, 2018, arXiv: 1804.0276.
Bochkovskiy A, Wang C-Y, Liao H-Y M. Yolov4: Optimal speed and accuracy of object detection [J/OL]. arXiv:2004.10934[2020-4-23].
Lin T Y, Goyal P, Girshick R, et al. Focal loss for denseobject detection[C]/ /2017 IEEE International Conferenceon Computer Vision( ICCV) ,2017: 2999 - 3007. DOI: https://doi.org/10.1109/ICCV.2017.324
Lin T Y, Dollár P, Girshick R,et al. Feature pyramid net-works for object detection[C]/ /2017 IEEE Conference on Computer Vision and Pattern Recognition( CVPR) ,2017: 936- 944. DOI: https://doi.org/10.1109/CVPR.2017.106
GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014:580-587. DOI: https://doi.org/10.1109/CVPR.2014.81
LI C, GUO C, GUO J, et al. PDR-Net: Perception -inspired single image dehazing network with refinement [J]. IEEE Transactions on Multimedia(S1520-9210), 2019, 22(3): 704-716. DOI: https://doi.org/10.1109/TMM.2019.2933334
Ren S, He K , Girshick R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence(S0162-8828), 2017, 39(6):1137-1149. DOI: https://doi.org/10.1109/TPAMI.2016.2577031
Li B Y, Peng X L, Wang Z Y, et al. AOD-Net: all-in-one de-hazing network[C] //Proceedings of the IEEE International Conference on Computer Vision. Los Alamitos: IEEE Com-puter Society Press, 2017: 4780-4788. DOI: https://doi.org/10.1109/ICCV.2017.511
Li B Y, Ren W Q, Fu D P, et al. Benchmarking single image dehazing and beyond[J]. IEEE Transactions on Image Processing(S1057-7149), 2019, 28(1): 492-505. DOI: https://doi.org/10.1109/TIP.2018.2867951
Liu Y, Zhao G , Gong B , et al. Improved Techniques for Learning to Dehaze and Beyond: A Collective Study [J]. arXiv:1807.00202 2018.
Yang W H, Yuan Y, Ren W Q, et al. Advancing image under-standing in poor visibility environments: a collective bench-mark study[J]. IEEE Transactions on Image Processing(S1057-7149), 2020, 29: 5737-5752. DOI: https://doi.org/10.1109/TIP.2019.2938310
Ma N, Zhang X, Zheng H T, et al. Shufflenet v2: Practical guidelines for efficient cnn architecture design [C]//Pro- ceedings of the European conference on computer vision (ECCV). 2018: 116-131. DOI: https://doi.org/10.1007/978-3-030-01264-9_8
Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, et al. Deblurgan: Blind motion deblurring using conditional adversarial networks[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8183-8192. DOI: https://doi.org/10.1109/CVPR.2018.00854
Zhang X, Zhou X, Lin M, et al. Shufflenet: An extremely efficient convolutional neural network for mobile devices [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 6848-6856. DOI: https://doi.org/10.1109/CVPR.2018.00716
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
