Basic Search / Detailed Display

Author: 李哲宇
Che-Yu Lee
Thesis Title: 基於自適應最小權重優先法之多視角影像色彩校正
A Novel Color Correction Algorithm for Multiview Images Using Adaptive Minimum Weight-First Approach
Advisor: 黃元欣
Yuan-Shin Hwang
鍾國亮
Kuo-Liang Chung
Committee: 顏嗣鈞
李同益
蔡文祥
Degree: 碩士
Master
Department: 電資學院 - 資訊工程系
Department of Computer Science and Information Engineering
Thesis Publication Year: 2023
Graduation Academic Year: 112
Language: 英文
Pages: 34
Keywords (in Chinese): 色彩校正最小權重優先多視角影像定量和定性品質
Keywords (in other languages): Color correction, minimum weight-first, multiview images, quantitative and qualitative quality
Reference times: Clicks: 27Downloads: 0
Share:
School Collection Retrieve National Library Collection Retrieve Error Report
  • 多視角影像的色彩校正是一項基本但具有挑戰性的任務,旨在生成顏
    色一致的組合影像,並在三維影像重建中獲得更好的渲染效果具有重要應
    用。在本論文中,我們提出了一種新穎且有效的多視角影像色彩校正演算
    法。我們首先利用修改過的顏色差距度量 (MCD),計算每對圖像 Vi 和 Vj
    的重疊區域的殘差,並將其作為邊 (Vi, Vj) 的權重,其中 Vi 和 Vj 也被視
    為兩個節點。接下來,我們提出了一種最小權重優先的方法來選擇第一個
    進行顏色校正的目標影像 It。然後,我們提出了一種將直方圖均衡化和雙
    邊插值法結合的方法,對 It 進行色彩校正。在此之後,更新 It 與其重疊
    影像之間的權重。上述基於最小權重優先法的目標影像選擇、色彩校正和
    權重更新的過程將重複進行,直到所有多視角影像的色彩校正完成。根據
    大規模測試多視角影像資料集,綜合實驗結果證明了我們的演算法在定量
    和定性品質方面相對於最先進色彩校正方法的優勢。


    Color correction for multiview images is a fundamental but challenging task to generate a color consistent composite image, and has important
    applications in rendering better 3D geometric reconstruction. In this paper,
    we propose a novel effective color correction algorithm for multiview images. Using our modified color distance (MCD) metric, we first estimate
    the residual of the overlapped region of each image pair, Vi and Vj, as the
    weight of the edge (Vi, Vj) where Vi and Vj are also viewed as two nodes.
    Next, a minimum weight-first approach is proposed to select the first target
    image It to be performed for color correction. Then, we propose a fusion
    based method, which integrates the histogram equalization and the joint bilateral interpolation, to correct color for It. After that, the weights between
    It and its overlapped images are updated. The above minimum weightfirst based target image selection, color correction, and weight updation
    process are repeated until the color correction for all multiview images is
    completed. Based on large-scale testing multiview image datasets, comprehensive experimental results demonstrated the quantitative and qualitative quality merits of our algorithm relative to state-of-the-art methods.

    Abstract in Chinese . . . . . . . . . . . . . . . . . . . . . . . . . . i Abstract in English . . . . . . . . . . . . . . . . . . . . . . . . . . ii Acknowledgements . . . . . . . . . . . . . . . . . . . . . . . . . . iii Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iv List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vii List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ix List of Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . x 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1 Related works . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1.1 Global color correction methods . . . . . . . . . . 2 1.1.2 Local color correction methods . . . . . . . . . . 5 1.1.3 Hybrid color correction methods . . . . . . . . . . 6 1.2 Contributions . . . . . . . . . . . . . . . . . . . . . . . . 6 2 The proposed adaptive minimum weight-first (AMWF) method to schedule the color correction order . . . . . . . . . . . . . . . 9 2.1 Construct a weighted graph for the input multiview images 9 2.2 The proposed AMWF-based method to schedule the color correction order . . . . . . . . . . . . . . . . . . . . . . . 10 3 The proposed fusion-based color correction algorithm for the selected target image . . . . . . . . . . . . . . . . . . . . . . . . . 13 3.1 The proposed fusion based color correction method for one overlapping area . . . . . . . . . . . . . . . . . . . . . . . 15 3.1.1 Derive the HE based color correction term for the target pixel I1′(t) . . . . . . . . . . . . . . . . . . 15 3.1.2 Derive the JBI based color correction term for the target pixel I1′(t) . . . . . . . . . . . . . . . . . . 16 3.1.3 Fuse the HE based and JBI based color correction terms to correct color for the target pixel I1′(t) . . . 17 3.2 The proposed fusion based color correction method for multiple overlapping areas . . . . . . . . . . . . . . . . . . . 18 4 Experimental result . . . . . . . . . . . . . . . . . . . . . . . . 22 4.1 Dataset Description and Parameter Setting . . . . . . . . . 22 4.1.1 Dataset description . . . . . . . . . . . . . . . . . 24 4.1.2 Parameter setting . . . . . . . . . . . . . . . . . . 25 4.2 Quantitative quality comparison . . . . . . . . . . . . . . 25 4.2.1 Color Distance . . . . . . . . . . . . . . . . . . . 25 4.2.2 Modified Color Distance . . . . . . . . . . . . . . 26 4.2.3 Measure of Enhancement . . . . . . . . . . . . . . 26 4.3 Qualitative quality comparison . . . . . . . . . . . . . . . 27 5 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33

    [1] J. Cui, M. Liu, Z. Zhang, S. Yang, and J. Ning, “Robust uav thermal infrared remote sensing images stitching via overlap-prior-based global similarity prior model,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 14, pp. 270–282, 2020.
    [2] Q. Xu, J. Chen, L. Luo, W. Gong, and Y. Wang, “Uav image stitching based on mesh-guided deformation and ground constraint,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 14, pp. 4465–4475, 2021.
    [3] Y. Yuan, F. Fang, and G. Zhang, “Superpixel-based seamless image stitching for uav images,” IEEE Trans. Geosci. Remote Sens., vol. 59, no. 2, pp. 1565–1576, 2021.
    [4] Z. Peng, Y. Ma, Y. Zhang, H. Li, F. Fan, and X. Mei, “Seamless uav hyperspectral image stitching using optimal seamline detection via graph cuts,” IEEE Trans. Geosci. Remote Sens., 2023.
    [5] M. Brown and D. G. Lowe, “Automatic panoramic image stitching using invariant features,” Int. J. Comput. Vis., vol. 74, p. 59–73, 2007.
    [6] A. K. U. Fecker, M. Barkowsky, “Histogram-based prefiltering for luminance and chrominance compensation of multiview video,” IEEE Trans. Circuits Syst. Video Technol., vol. 18, no. 9, pp. 1258–1267, 2008.
    [7] C. Ding and Z. Ma, “Multi-camera color correction via hybrid histogram matching,” IEEE Trans. Circuits Syst. Video Technol., vol. 31, no. 9, pp. 3327–3337, 2021.
    [8] Y. Xiong and K. Pulli, “Color matching for high-quality panoramic images on mobile phones,” IEEE Trans. Consum. Electron., vol. 56, no. 4, pp. 2592–2600, 2010.
    [9] J. Park, Y.-W. Tai, S. N. Sinha, and I. So Kweon, “Efficient and robust color consistency for community photo collections,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 430–438, 2016.
    [10] M. Xia, J. Yao, and Z. Gao, “A closed-form solution for multi-view color correction with gradient preservation,” ISPRS J. Photogramm. Remote Sens., vol. 157, pp. 188–200, 2019.
    [11] T. Shen, J. Wang, T. Fang, S. Zhu, and L. Quan, “Color correction for image-based modeling in the large,” in Computer Vision–ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part IV 13, pp. 392–407, Springer, 2017.
    [12] J. Yang, L. Liu, J. Xu, Y. Wang, and F. Deng, “Efficient global color correction for large-scale multipleview images in three-dimensional reconstruction,” ISPRS J. Photogramm. Remote Sens., vol. 173, pp. 209–220, 2021.
    [13] Y. Li, L. Li, J. Yao, M. Xia, and H. Wang, “Contrast-aware color consistency correction for multiple images,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 15, pp. 4941–4955, 2022.
    [14] Y. Li, Y. Li, J. Yao, Y. Gong, and L. Li, “Global color consistency correction for large-scale images in 3-D reconstruction,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 15, pp. 3074–3088, 2022.
    [15] M. Xia, J. Yao, R. Xie, M. Zhang, and J. Xiao, “Color Consistency Correction Based on Remapping Optimization for Image Stitching,” Proc. IEEE Int. Conf. Comput. Vis. Workshops, pp. 2977–2984, 2017.
    [16] Y. Li, H. Yin, J. Yao, H. Wang, and L. Li, “A unified probabilistic framework of robust and efficient color consistency correction for multiple images,” ISPRS J. Photogramm. Remote Sens., vol. 190, pp. 0924–2716, 2022.
    [17] H. Huang, Y. Tang, Z. Tan, J. Zhuang, C. Hou, W. Chen, and J. Ren, “Object-Based attention mechanism for color calibration of UAV remote sensing images in precision agriculture,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–13, 2022.
    [18] J. Liu, G. Wu, J. Luan, Z. Jiang, R. Liu, and X. Fan, “HoLoCo: Holistic and local contrastive learning network for multi-exposure image fusion,” Inf. Fusion, vol. 95, pp. 237–249, 2023.
    [19] F. Fang, T. Wang, Y. Fang, and G. Zhang, “Fast color blending for seamless image stitching,” IEEE Geosci. Remote Sens. Lett., vol. 16, no. 7, pp. 1115–1119, 2019.
    [20] K. L. Chung and D. Y. Row, “An adaptive joint bilateral interpolation-based color blending method for stitched uav images,” Remote Sens., vol. 14, no. 21, p. 5440, 2022.
    [21] L. Yu, Y. Zhang, M. Sun, X. Zhou, and C. Liu, “An auto-adapting global-to-local color balancing method for optical imagery mosaic,” ISPRS J. Photogramm. Remote Sens., vol. 132, pp. 1–19, 2017.
    [22] R. Cresson and N. Saint-Geours, “Natural color satellite image mosaicking using quadratic programming in decorrelated color space,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 8, pp. 4151–
    4162, 2015.
    [23] L. Li, M. Xia, C. Liu, L. Li, H. Wang, and J. Yao, “Jointly optimizing global and local color consistency for multiple image mosaicking,” ISPRS J. Photogramm. Remote Sens., vol. 107, pp. 45–56, 2020.

    QR CODE