微信服务号

微信订阅号

2025-4-1- 12
Home > Archive>Volume 30, Issue S1, 2019 >94-104
PDF HTML XML Export Cite reminder
Methods of Image Restoration and Object Detection in Low-Light Environment
Author:
Affiliation:

Fund Project:

National Natural Science Foundation of China (No.61370222); Natural Science Foundation of Heilongjiang Province (ZD2019F003)

  • Article
    • | |
  • Metrics
    • |
  • Reference [34]
    • |
  • Related [20]
    • | | |
  • Comments
    Abstract:

    The existing object detection methods for low-light image usually separate image restoration from object detection tasks. In addition, the quality and computing time of image restoration cannot meet the requirements of object detection task. To solve these problems, firstly, this study proposes an efficient image restoration convolutional neural network architecture, which aggregates feature information of multi-level contexts by combining feature maps of different scales, reduces information redundancy of convolutional layers, and improves the real-time performance of image restoration. In addition, a local-global attention block is designed to improve the ability of the recovery network to distinguish between noise and image content by calibrating the local information of each feature map and the relationship between feature channels. Secondly, this study designs a solution for collaborative processing of image restoration and target recognition tasks. The high-level semantic information of target recognition is used to guide the image recovery network learning, so as to highlight the feature information such as the structure and texture of the target, and make the recovery result more suitable for the target recognition task. Experimental results show that this method is superior to the existing methods in image restoration quality, computing time and object detection rate.

    Reference
    [1] Ren SQ, He KM, Girshick R, Sun J. Faster R-CNN:Towards real-time object detection with region proposal networks. In:Proc. of the Annual Conf. on Neural Information Processing Systems. 2015. 91-99.
    [2] He KM, Zhang XY, Ren SQ, Sun J. Deep residual learning for image recognition. In:Proc. of the 2016 IEEE Conf. on Computer Vision and Pattern Recognition. 2016. 770-778.
    [3] Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks. In:Proc. of the 2017 IEEE Conf. on Computer Vision and Pattern Recognition. 2017. 2261-2269.
    [4] He KM, Gkioxari G, Dollár P, Girshick R. Mask R-CNN. In:Proc. of the 2017 IEEE Int'l Conf. on Computer Vision. 2017. 2980-2988.
    [5] Zhao HS, Shi JP, Qi XJ, Wang XG, Jia JY. Pyramid scene parsing network. In:Proc. of the 2017 IEEE Conf. on Computer Vision and Pattern Recognition. 2017. 6230-6239.
    [6] Neuhold G, Ollmann T, BulòSR, Kontschieder P. The mapillary vistas dataset for semantic understanding of street scenes. In:Proc. of the Int'l Conf. on Computer Vision. 2017. 5000-5009.
    [7] Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B. The cityscapes dataset for semantic urban scene understanding. In:Proc. of the Conf. on Computer Vision and Pattern Recognition. 2016. 3213-3223.
    [8] Huang XY, Cheng XJ, Geng QC, Cao BB, Zhou DF, Wang P, Lin YQ, Yang RG. The ApolloScape dataset for autonomous driving. In:Proc. of the 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition Workshops. 2018. 954-960.
    [9] Lin TY, Maire M, Belongie S, Bourdev L, Girshick R, Hays J, Perona P, Ramanan D, Zitnick CL, Dollár P. Microsoft COCO:Common objects in context. In:Proc. of the European Conf. on Computer Vision (ECCV). 2014. 740-755.
    [10] Deng J, Dong W, Socher R, Li LJ, Li K, Li FF. ImageNet:A large-scale hierarchical image database. In:Proc. of the Conf. on Computer Vision and Pattern Recognition. 2009. 248-255.
    [11] Gu SH, Zhang L, Zuo WM, Feng XC. Weighted nuclear norm minimization with application to image denoising. In:Proc. of the 2014 IEEE Conf. on Computer Vision and Pattern Recognition. 2014. 2862-2869.
    [12] Dabov K, Foi A, Katkovnik V, Egiazarian K. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. on Image Processing, 2007,16(8):2080-2095.
    [13] Mairal J, Bach F, Ponce J, Sapiro G, Zisserman A. Non-local sparse models for image restoration. In:Proc. of the 2009 IEEE 12th Int'l Conf. on Computer Vision. 2009. 2272-2279.
    [14] Zhang K, Zuo WM, Chen YJ, Meng DY, Zhang L. Beyond a Gaussian denoiser:Residual learning of deep CNN for image denoising. IEEE Trans. on Image Processing, 2017,26(7):3142-3155.
    [15] Zhang K, Zuo WM, Zhang L. FFDNet:Toward a fast and flexible solution for CNN-based image denoising. IEEE Trans. on Image Processing, 2018,27(9):4608-4622.
    [16] Guo S, Yan ZF, Zhang K, Zuo WM, Zhang L. Toward convolutional blind denoising of real photographs. In:Proc. of the Conf. on Computer Vision and Pattern Recognition. 2019. 1712-1722.
    [17] Ronneberger O, Fischer P, Brox T. U-Net:Convolutional networks for biomedical image segmentation. In:Medical Image Computing and Computer-Assisted Intervention. 2015. 234-241.
    [18] Mao XJ, Shen CH, Yang YB. Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In:Proc. of the Annual Conf. on Neural Information Processing Systems. 2016. 2802-2810.
    [19] Tao X, Gao HY, Shen XY, Wang J, Jia JY. Scale-recurrent network for deep image deblurring. In:Proc. of the Conf. on Computer Vision and Pattern Recognition. 2018. 8174-8182.
    [20] Jain V, Seung HS. Natural image denoising with convolutional networks. In:Proc. of the Annual Conf. on Neural Information Processing Systems. 2008. 769-776.
    [21] Xie JY, Xu LL, Chen EH. Image denoising and inpainting with deep neural networks. In:Proc. of the Annual Conf. on Neural Information Processing Systems. 2012. 350-358.
    [22] Yan ZY, Li XM, Li M, Zuo WM, Shan SG. Shift-net:Image inpainting via deep feature rearrangement. In:Proc. of the European Conf. on Computer Vision (ECCV). 2018. 3-19.
    [23] Wu ZF, Shen CH, Anton van den Hengel. Real-time semantic image segmentation via spatial sparsity. Computing Research Repository (CoRR), 2017,abs/1712.00213.
    [24] Chollet F. Xception:Deep learning with depthwise separable convolutions. In:Proc. of the Conf. on Computer Vision and Pattern Recognition. 2017. 1800-1807.
    [25] Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In:Proc. of the Conf. on Computer Vision and Pattern Recognition. 2018. 7132-7141.
    [26] Woo S, Park J, Lee JY, Kweon IS. CBAM:Convolutional block attention module. In:Proc. of the European Conf. on Computer Vision (ECCV). 2018. 3-19.
    [27] Kong T, Sun FC, Huang WB, Liu HP. Deep feature pyramid reconfiguration for object detection. In:Proc. of the European Conf. on Computer Vision (ECCV). 2018. 172-188.
    [28] Liu D, Wen BH, Jiao JB, Liu XM, Wang ZY, Huang TS. Connecting image denoising and high-level vision tasks via deep learning. Computing Research Repository (CoRR), 2018,abs/1809.01826.
    [29] Chen C, Chen QF, Xu J, Koltun V. Learning to see in the dark. In:Proc. of the Conf. on Computer Vision and Pattern Recognition. 2018. 3291-3300.
    [30] Kingma DP, Ba JL. Adam:A method for stochastic optimization. In:Proc. of the Int'l Conf. on Learning Representations. 2015.
    [31] Zhang K, Zuo WM, Chen Yj, Meng DY, Zhang L. Beyond a Gaussian denoiser:Residual learning of deep CNN for image denoising. IEEE Trans. on Image Processing, 2017,26(7):3142-3155.
    [32] Chen QF, Xu J, Koltun V. Fast image processing with fully-convolutional networks. In:Proc. of the Int'l Conf. on Computer Vision. 2017. 2516-2525.
    [33] Redmon J, Farhadi A. YOLOv3:An incremental improvement. Computing Research Repository (CoRR), 2018,abs/1804.02767.
    [34] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In:Proc. of the Int'l Conf. on Learning Representations. 2015.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

任东东,李金宝.低光照环境下的图像恢复与目标识别方法.软件学报,2019,30(S1):94-104

Copy
Share
Article Metrics
  • Abstract:1864
  • PDF: 5553
  • HTML: 0
  • Cited by: 0
History
  • Received:September 15,2019
  • Online: January 02,2020
Links:Institute of Software, CASChina Computer FederationCASNSFC
You are the first2030800Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address：4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code：100190
Phone：010-62562563 Fax：010-62562533 Email：jos@iscas.ac.cn
Technical Support：Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063