利用空間與時間一致性去增強縫刻的影片縮放

Exploring Spatial and Temporal Coherence to Strengthen Seam Carving in Video Retargeting

黃紀偉(Chi-Wei Huang)

指導教授 ： 劉興民

國立中正大學/工學院/資訊工程學系/碩士(2015年)

摘要

隨著銀幕顯示器逐漸的多樣化，要展示尺寸固定的圖片或影片，往往受限於不同顯示器的大小。在近幾年來，內容感知的縮放方法日益增加，而縫刻是一種新穎且有效的方法，但是此方法可能破壞物體的結構性並造成扭曲現象。

我們在影片放大的部分使用等比例放大後，再採用縫刻來縮減到目標大小。因此在本篇論文，會著重於縮減部分，在空間的一致性上，強調輪廓和主體內容的保護，並且結合縫刻和非等比例運算子來達到美觀的效果。最後將此方法延伸至影片，因為每個影格之間都有時間的連續性，若直接套用原方法會造成影片跳動的問題。我們把影片分成靜態相機跟動態相機兩種類型，利用時間的一致性來減少跳動問題的產生，並且根據實驗結果驗證，我們的方法可以提升影片縮放後的品質。

關鍵字

內容感知重新定位 ； 影片重新定位 ； 縫刻 ； 空間一致性 ； 時間一致性

並列摘要

Number of various display screens and mobile devices has increased significantly. Unfortunately, showing a fixed size picture or video is often limited by the aspect ratio of different displays. In recent years, many content-aware retargeting techniques have been proposed. Among them, Seam carving is a novel and efficient method, but it may distort the object’s structure.
For enlarging an image, we tend to make it larger and undistorted by first magnifying the image, and shrink it to the target size using Seam carving. Thus, in this thesis, we focus on shrinking. For spatial coherence, we emphasize the object shape and protect significant content. We also combine Seam carving and Scaling operator, trying to avoid the bad results due to content distortion. Moreover, we extend our method to video retargeting, which formerly caused the jittery artifacts without exploring temporal information. We classify the videos into those taken by the static camera setup and the others by the moving camera setup. Then we explore temporal coherence to decrease the jittery artifacts. Finally, the experimental results demonstrate our approach can raise the quality in video retargeting.

並列關鍵字

Temporal coherence ； Spatial coherence ； Content aware retargeting ； Video retargeting ； Seam carving

參考文獻

[1] Yanwen Guo, Feng Liu, Jian Shi, Zhi-Hua Zhou, and Michael Gleicher, “Image retargeting using mesh parametrization,” in IEEE Transactions on Multimedia, vol. 11, pp. 856-867, 2009.

[3] Shai Avidan and Ariel Shamir, “Seam carving for content-aware image resizing,” in ACM Transactions on Graphics (TOG), vol. 26(3), 2007.

[5] Michael Frankovich and Alexander Wong, “Enhanced seam carving via integration of energy gradient functionals,” in IEEE Signal Processing Letters, vol. 18, pp. 375-378, 20011.

[6] Michael Rubinstein, Ariel Shamir, and Shai Avidan, “Multi-operator media retargeting,” in ACM Transactions on Graphics (TOG), vol. 28(3), 2009.

[7] Thomas Deselaers, Philippe Dreuw, and Hermann Ney , “Pan, Zom, San – time-coherent, trained automatic video cropping,” in Computer Vision and Patterm Recognition (CVPR), pp. 1-8, 2008.