臺灣博碩士論文加值系統

環境光源情況是影響影像式智慧系統效能的因素之一。為了處理視訊中過度曝光和曝光不足的情況，本文提出一套基於視覺關注模型與資料融合之視訊品質提升法則。本文所提出之法則由五個部分所組成：前處理、視覺關注模型、多層級曝光校正及資料融合與後處理。
前處理程序初步地調整影像內容，便於視覺線索的計算。在前處理程序後，利用視覺關注模型提取各項特徵資訊，求得視覺關注圖。多層級曝光校正演算法根據視覺關注圖，產生多個調整影像內容之結果。透過選取校正後影像局部內容較佳之處進行影像融合，以達成影像品質之提升。考量影像內容的連續性，本文提出一個時間域之曝光值濾波器，降低閃爍現象的影響。
為了評估本系統之效能，本文採用主觀與客觀的評估方式。實驗結果表明，相較於現有的其它方法，本文提出的技術能夠提高影像的細節，並且保持整體的視覺品質良好。

In this thesis, we proposed a video quality enhancement scheme based on visual attention model to deal with low- and high-exposure videos. The proposed scheme is composed of five parts: pre-processing, visual attention model, multilevel exposure correction, data fusion, and post-processing. To make the proposed scheme easily measure visual cues of each frame, the pre-processing procedure is used to coarsely modify each input frame. After pre-processing, visual attention model is used to extract visual features of each frame and then we conducted multi-level exposure correction for each frame according to the visual attention model. For each frame, we fuse these versions generated by multi-level exposure correction to obtain the final resulting frame. To reduce the impact of flicker on visual quality, a post-processing procedure is developed to enhance the video quality.
The experiment results demonstrate that the proposed scheme can deal with videos with low and high exposures. The results also show that the proposed scheme outperforms some existing methods in terms of visual quality.

第一章 緒論1
1.1研究動機1
第二章 相關文獻之研究3
2.1影像增強演算法3
2.1.1直方圖等化3
2.1.2曝光校正演算法4
2.1.3 Retinex演算法5
2.1.4基於暗通道之影像品質提升法5
2.1.5以感知為基礎之對比度提升法6
2.1.6動態範圍影像6
2.1.7 Rank transform 演算法8
2.2影像評估9
2.2.1主觀品質評估9
2.2.2客觀品質評估9
第三章 系統架構10
3.1前處理 12
3.2視覺關注模型13
3.2.1移動特徵偵測14
3.2.2顏色特徵偵測16
3.2.3強度特徵偵測18
3.2.4紋理特徵偵測19
3.2.5人臉偵測21
3.2.6特徵資訊融合22
3.3多層級曝光校正24
3.4資料融合28
3.5後處理 32
3.6系統加速33
第四章 實驗分析與結果36
4.1實驗執行環境與評估方式36
4.2前處理之分析38
4.3多層級曝校正與資料融合之分析43
4.4後處理之分析與播放品質之評估49
4.5畫幀品質與視訊品質之評估57
4.6系統加速之分析86
第五章 結論與未來研究方向89
5.1結論89
5.2未來研究方向90
參考文獻91

[1] L. Z. Rubenstein and K. R. Josephson, “The epidemiology of falls and syncope,” Clinics in Geriatric Medicine, pp. 141-158, 2002.
[2] 蔡益堅、葉純志、藍祚運、張文瓊、曾德運，1999 年與 2005年台灣地區老人跌倒狀況之比較，國家衛生研究院電子報，2007。
[3] Z. Rahman, D. J. Jobson, and G. A. Woodell, “Retinex processing for automatic image enhancement,” Journal of Electronic Imaging, vol. 13, no. 1, pp. 100−110, 2004.
[4] H. C. Lien, “Retinex-based intelligent image enhancement technologies,” Master Thesis, National Taiwan University, 2008.
[5] HDR, http://en.wikipedia.org/wiki/High_dynamic_range_imaging
[6] C. Shi, K. Yu, J. Li and S. Li, “Automatic image quality improvement for videoconferencing,” in Proc. IEEE Int’l Conf. on Acoustics, Speech, and Signal Processing, vol. 3, pp.701-704, 2004.
[7] X. Jiang, H. Yao, S. Zhang, X. Lu , and W. Zeng, “Night video enhancement using improved dark channel prior,” in Proc. IEEE Int’l Conf. on Image Processing, pp.553-557, 2013.
[8] M. Aditi and S. Irani, “Contrast enhancement of images using human contrast sensitivity,” Computer Vision and Pattern Recognition, pp. 377-382, 2005.
[9] K. C. Yang, C. C. Guest, and P. K. Das, “Human visual attention map for compressed video,” in Proc. IEEE Int’l Symposium on Multimedia, pp. 525-532, Dec. 2006.
[10] X. Yang, W. Lin, Z. Lu, X. Lin, S. Rahardja, E. Ong, and S. Yao, “Rate control for videophone using local perceptual cues,” IEEE Trans. Circuits and Systems for Video Technology, vol. 15, no. 4, pp. 496-507, 2005.
[11] L. Itti, C. Koch, and E. Niebur, “A model of saliency-based visual attention for rapid scene analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp. 1254-1259, 1998.
[12] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, vol. 1, no. 1 , pp. 511–518, 2001.
[13] G. S. Lin, M. K. Chang, and Y. J. Chang, “Gender recognition based on multi-model information fusion,” in Proc. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, China 2011.
[14] J. C. Hong, G. S. Lin , T. H. Hsiao, Y. P. Liao, K. C. Liu, and W. N. Lie, “Quality enhancement based on retinex and pseudo-HDR synthesis algorithms for endoscopic images,” in Proc. IEEE Int’l Conf. on Visual Communications and Image Processing, pp. 1-5, 2013.
[15] M. Ramkumar and B. Karthikeyan, “A survey on image enhancement methods,” International Journal of Engineering and Technology, vol.5, no. 2, pp. 960-962, 2013.
[16] D. Y. Huang, C. J. Lin, and S. H. Dai, “Face recognition using the diagonal relative gradient method in a low illumination environment,” Journal of Information Hiding and Multimedia Signal Processing, vol. 5, no. 2, pp. 310-323, 2014.
[17] W. N. Lie, C. Y. Chen, and W. C. Chen, “2D to 3D video conversion with key-frame depth propagation and trilateral filtering,” IET Electronics Letters, vol. 47, no. 5, pp. 319-321, 2011.
[18] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Third edition, Prentice Hall, 2008.