簡易檢索 / 詳目顯示

回結果列表
研究生： 林峻億
Chun-Yi Lin
論文名稱： 利用圖像梯度之基於低光源圖像的顯著圖檢測及主觀圖像增強
Subjective image enhancement and saliency map detection based on low-light images with image gradients
指導教授： 阮聖彰
Shanq-Jang Ruan
口試委員: 阮聖彰
Shanq-Jang Ruan
吳晉賢
Chin-Hsien Wu
林淵翔
Yuan-Hsiang Lin
蔡坤霖
Kun-Lin Tsai
學位類別： 碩士
Master
系所名稱： 電資學院 - 電子工程系
Department of Electronic and Computer Engineering
論文出版年： 2023
畢業學年度： 111
語文別： 英文
論文頁數： 98
中文關鍵詞： 卷積神經網路優化 、低光源圖像增強 、顯著圖檢測
外文關鍵詞： Convolutional neural network optimization, Low-light image enhancement, Saliency map detection
相關次數： 點閱：162  下載：5 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 近年來，深度學習在各個領域被廣泛應用。卷積神經網絡（Convolution Neural Network, CNN）是一個相當知名的深度學習演算法，且被廣泛地運用在物件識別、 人臉識別和車輛識別等處。然而，傳統的物體識別方法可能不適合於低光環境下 的圖像識別，因為黑暗區域的資訊損失以及意外的噪音導致惡化。因此，開發低 光源圖像增強技術及顯著圖檢測已成為物體檢測的主要研究重點。本文提出了一 種基於梯度的顯著圖檢測方法以及優化的 ResNet 架構，更有效的檢測多個或大 型物體。此外，所提出的方法以物體為中心增強圖像，並強調前景和背景之間的 差異。相較於先前的論文，本文在參數方面實現了 1.28 倍的改進，並比原始 ResNet 架構實現了 1.32 倍的更快推論速度。

    Recently, deep learning has been widely employed across various domains. The Convolution Neural Network (CNN), a popular deep learning algorithm, has been successfully utilized in object recognition tasks, such as face recognition and vehicle recognition. However, conventional methods for object recognition may not be appropriate for low-light image recognition due to information loss in the dark regions and unexpected noise that can impair object quality. Therefore, the development of techniques for low-light image enhancement and saliency map detection has become a major research focus for object detection. This paper proposed a gradient-based saliency map detection method with an improved ResNet architecture that outperforms previous works in detecting multiple or large objects. Additionally, the proposed method enhances images with the object as the center and emphasizes foreground-background differences. Compared with previous works, this paper achieves 1.28× improvements in the parameters and 1.32× faster inference speed than the original ResNet architecture.

    摘要 IV ABSTRACT V ACKNOWLEDGEMENTS VI TABLE OF CONTENTS VIII LIST OF FIGURES XI LIST OF TABLES XIII CHAPTER 1 1 INTRODUCTION 1 1.1 Background of the saliency map detection 1 1.2 Background of the low-light image enhancement 3 1.3 Challenges of previous works 5 1.4 Contribution of this thesis 7 1.5 Organization 8 CHAPTER 2 9 BACKGROUNDS 9 2.1 Convolutional neural networks 9 2.2 Image gradient 20 2.3 Structural re-parameterization technique 23 CHAPTER 3 28 RELATED WORKS 28 3.1 Low-light image enhancement 28 3.2 Saliency map detection on images 32 3.3 Saliency map detection on videos 36 CHAPTER 4 40 SALIENCY MAP DETECTION BASED ON GRADIENT 40 4.1 Architecture overview 40 4.2 Saliency map detection architecture 42 4.3 Saliency map detection 46 CHAPTER 5 53 EXPERIMENT RESULTS 53 5.1 Environment/Dataset setup 53 5.2 Results of saliency map detection on low-light images 56 5.3 Results of low-light images enhancement 67 5.4 The re-parameterization architecture performance 70 CHAPTER 6 77 CONCLUSIONS 77 REFERENCES 79

    [1] S.-L. Chang, L.-S. Chen, Y.-C. Chung, and S.-W. Chen. "Automatic license plate recognition." IEEE Transactions on Intelligent Transportation Systems, 5(1):42-53, 2004.
    [2] D. Gray and H. Tao. "Viewpoint invariant pedestrian recognition with an ensemble of localized features." European Conference on Computer Vision, Springer, Berlin, Heidelberg, 2008.
    [3] D. G. Lowe. "Object recognition from local scale-invariant features." Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, IEEE, 1999.
    [4] J. Ren, X. Gong, L. Yu, W. Zhou, and M. Y. Yang. "Exploiting global priors for RGB-D saliency detection." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 25-32, 2015.
    [5] H. Peng, B. Li, W. Xiong, W. Hu, and R. Ji. "RGBD salient object detection: A benchmark and algorithms." In Computer Vision–ECCV 2014, Springer International Publishing, pp. 92-109, 2014.
    [6] L. Itti, C. Koch, and E. Niebur. "A model of saliency-based visual attention for rapid scene analysis." IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(11):1254-1259, 1998.
    [7] V. Gopalakrishnan, Y. Hu, and D. Rajan. "Salient Region Detection by Modeling Distributions of Color and Orientation." IEEE Transactions on Multimedia, 11(5):892-905, 2009.
    [8] J. Kim, D. Han, Y. W. Tai, and J. Kim. "Salient region detection via high-dimensional color transform." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 883-890, 2014.
    [9] G. H. Liu and J. Y. Yang. "Exploiting color volume and color difference for salient region detection." IEEE Transactions on Image Processing, 28(1):6-16, 2018.
    [10] O. K. Sikha, S. S. Kumar, and K. P. Soman. "Salient region detection and object segmentation in color images using dynamic mode decomposition." Journal of Computational Science, 25:351-366, 2018.
    [11] J. Lou, H. Wang, L. Chen, F. Xu, Q. Xia, W. Zhu, and M. Ren. "Exploiting color name space for salient object detection." Multimedia Tools and Applications, 79:10873-10897, 2020.
    [12] S. M. Pizer. "Contrast-limited adaptive histogram equalization: Speed and effectiveness stephen m. pizer, r. eugene johnston, james p. ericksen, bonnie c. yankaskas, keith e. muller medical image display research group." In Proceedings of the First Conference on Visualization in Biomedical Computing, Atlanta, Georgia, vol. 337, p. 1, May 1990.
    [13] W. Ren, S. Liu, L. Ma, Q. Xu, X. Xu, X. Cao, et al. "Low-light image enhancement via a deep hybrid network." IEEE Transactions on Image Processing, 28(9): 4364-4375.
    [14] A. Polesel, G. Ramponi, V. J. Mathews. "Image enhancement via adaptive unsharp masking." IEEE Transactions on Image Processing, 9(3), 505-510, 2000.
    [15] C. Chen, Q. Chen, J. Xu, V. Koltun. "Learning to see in the dark." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3291-3300, 2018.
    [16] A. Ignatov, N. Kobyshev, R. Timofte, K. Vanhoey, L. Van Gool. "Wespe: weakly supervised photo enhancer for digital cameras." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 691-700, 2018.
    [17] R. Rothe, R. Timofte, L. Van Gool. "Dex: Deep expectation of apparent age from a single image." In Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 10-15, 2015.
    [18] X. Guo, Y. Li, H. Ling. "LIME: Low-light image enhancement via illumination map estimation." IEEE Transactions on Image Processing, 26(2), 982-993, 2016.
    [19] C. Guo, C. Li, J. Guo, C. C. Loy, J. Hou, S. Kwong, R. Cong. "Zero-reference deep curve estimation for low-light image enhancement." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1780-1789, 2020.
    [20] X. Ding, X. Zhang, N. Ma, J. Han, G. Ding, J. Sun. "Repvgg: Making vgg-style convnets great again." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13,733–13,742, 2021.
    [21] H. Ibrahim, N. S. P. Kong. "Brightness preserving dynamic histogram equalization for image contrast enhancement." IEEE Transactions on Consumer Electronics, 53(4), 1752–1758, 2007.
    [22] X. Fu, D. Zeng, Y. Huang, X.-P. Zhang, X. Ding. "A weighted variational model for simultaneous reflectance and illumination estimation." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2782–2790, 2016.
    [23] X. Ren, M. Li, W.-H. Cheng, J. Liu. "Joint enhancement and denoising method via sequential decomposition." In 2018 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1–5, 2018.
    [24] M. Li, J. Liu, W. Yang, X. Sun, Z. Guo. "Structure-revealing lowlight image enhancement via robust retinex model." IEEE Transactions on Image Processing, 27(6), 2828–2841, 2018.
    [25] M. Mukaida, S. Kojima, N. Suetake. "Low-light image enhancement based on soft-closing-based illumination estimation and noise mitigation using correlation among RGB components." Optical Review, 29(5), 396–407, 2022.
    [26] Y. Zhang, J. Zhang, X. Guo. "Kindling the darkness: A practical low-light image enhancer." In Proceedings of the 27th ACM International Conference on Multimedia, 2019, pp. 1632–1640.
    [27] Y. Jiang, X. Gong, D. Liu, Y. Cheng, C. Fang, X. Shen, J. Yang, P. Zhou, Z. Wang. "Enlightengan: Deep light enhancement without paired supervision." IEEE Transactions on Image Processing, 30, 2340-2349, 2021.
    [28] Q. Li, B. Jiang, X. Bo, C. Yang, X. Wu. "Effective low-light image enhancement with multiscale and context learning network." Multimedia Tools and Applications, 1-16, 2022.
    [29] P. Chondro, S.-J. Ruan. "Perceptually hue-oriented power-saving scheme with overexposure corrector for AMOLED displays." Journal of Display Technology, 12(8), 791-800, 2016.
    [30] P. Chondro, C.-H. Chang, S.-J. Ruan, C.-A. Shen. "Advanced multimedia power-saving method using a dynamic pixel dimmer on AMOLED displays." IEEE Transactions on Circuits and Systems for Video Technology, 28(9), 2200-2209, 2018.
    [31] Y.-Y. Chou, M.A. Haq, S.-J. Ruan, P. Chondro. "Power constrained exposure correction network for mobile devices." Journal of Ambient Intelligence and Humanized Computing, 1-13, 2022.
    [32] P. Hao, M. Yang, N. Zheng. "Subjective low-light image enhancement based on a foreground saliency map model." Multimedia Tools and Applications, 81(4), 4961-4978, 2022.
    [33] N. Bruce, J. Tsotsos. "Attention based on information maximization." Journal of Vision, 7(9), 950–950, 2007.
    [34] N. Murray, M. Vanrell, X. Otazu, C.A. Parraga. "Saliency estimation using a non-parametric low-level vision model." In Proceedings of 2011 IEEE Computer Vision and Pattern Recognition (CVPR), pp. 433–440, 2011.
    [35] Z.-u. Rahman, D.J. Jobson, G.A. Woodell. "Multi-scale retinex for color image enhancement." In Proceedings of 3rd IEEE International Conference on Image Processing, Vol. 3, 1996.
    [36] X. Shen, Y. Wu. "A unified approach to salient object detection via low rank matrix recovery." In 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012.
    [37] H.R. Tavakoli, J. Laaksonen. "Bottom-up fixation prediction using unsupervised hierarchical models." In Proceedings of Asian conference on computer vision, pp. 287–302, 2016.
    [38] J.-X. Zhao, J.-J. Liu, D.-P. Fan, Y. Cao, J. Yang, M.-M. Cheng. "EGNet: Edge guidance network for salient object detection." In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.
    [39] M. Zhang, W. Ren, Y. Piao, Z. Rong, H. Lu. "Select, supplement and focus for RGB-D saliency detection." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.
    [40] P.-C. Tsai, P. Chondro, S.-J. Ruan. "Depth-guided pixel dimming with saliency-oriented power-saving transformation for stereoscope AMOLED displays." IEEE Transactions on Circuits and Systems for Video Technology, 30(9), 3095-3105, 2019.
    [41] C. Chen, S. Li, Y. Wang, H. Qin, A. Hao. "Video saliency detection via spatial-temporal fusion and low-rank coherency diffusion." IEEE Transactions on Image Processing, 26(7), 3156–3170, 2017.
    [42] H. Jiang, J. Wang, Z. Yuan, Y. Wu, N. Zheng, S. Li. "Salient object detection: A discriminative regional feature integration approach." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2083–2090, 2013.
    [43] L. Wang, H. Lu, Y. Wang, M. Feng, D. Wang, B. Yin, X. Ruan. "Learning to detect salient objects with image-level supervision." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 136–145, 2017.
    [44] Y. Li, S. Li, C. Chen, A. Hao, H. Qin. "A plug-and-play scheme to adapt image saliency deep model for video data." IEEE Transactions on Circuits and Systems for Video Technology, 31(6), 2315–2327, 2020.
    [45] C. Chen, H. Wang, Y. Fang, C. Peng. "A novel long-term iterative mining scheme for video salient object detection." IEEE Transactions on Circuits and Systems for Video Technology, 32(11), 7662–7676, 2022.
    [46] C. Chen, J. Song, C. Peng, G. Wang, Y. Fang. "A novel video salient object detection method via semisupervised motion quality perception." IEEE Transactions on Circuits and Systems for Video Technology, 32(5), 2732–2745, 2021.
    [47] C. Chen, M. Song, W. Song, L. Guo, M. Jian. "A comprehensive survey on video saliency detection with auditory information: the audio-visual consistency perceptual is the key!" IEEE Transactions on Circuits and Systems for Video Technology, 2022.
    [48] M. Jiang, S. Huang, J. Duan, Q. Zhao. "Salicon: Saliency in context." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015.
    [49] Loh, Y. P., & Chan, C. S. "Getting to know low-light images with the exclusively dark dataset." Computer Vision and Image Understanding 178 (2019): 30-42.
    [50] R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra. "Grad-CAM: Visual explanations from deep networks via gradient-based localization." In Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626, 2017.
    [51] X. Jia, C. Zhu, M. Li, W. Tang, W. Zhou. "LLVIP: A visible-infrared paired dataset for low-light vision." In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3496–3504, 2021.
    [52] W. Chen, W. Wang, W. Yang, J. Liu. "Deep retinex decomposition for low-light enhancement." arXiv preprint arXiv:1808.04560, 2018.
    [53] J. Cai, S. Gu, L. Zhang. "Learning a deep single image contrast enhancer from multi-exposure images." IEEE Transactions on Image Processing, 27(4), 2049-2062, 2018.
    [54] J. Ma, X. Fan, J. Ni, X. Zhu, C. Xiong. "Multi-scale retinex with color restoration image enhancement based on Gaussian filtering and guided filtering." International Journal of Modern Physics B, 31(16-19), 1744077, 2017.
    [55] C. Wei, W. Wang, W. Yang, J. Liu. "Deep retinex decomposition for low-light enhancement." arXiv preprint arXiv:1808.04560, 2018.
    [56] F. Lv, F. Lu, J. Wu, C. Lim. "Mbllen: Low-light image/video enhancement using CNNs." In BMVC, vol. 220, no. 1, 2018, p. 4.
    [57] Lin, C. Y., Haq, M. A., Chen, J. H., Ruan, S. J., & Naroska, E. "Efficient Saliency Map Detection for Low-Light Images Based on Image Gradient." IEEE Transactions on Circuits and Systems for Video Technology (2023).

    QR CODE