Low complexity content-aware video retargeting for mobile devices

Nam, Hyeong-Min; Byun, Keun-Yung; Choi, Kang-Sun; Ko, Sung-Jea

doi:10.1109/tce.2010.5439143

Cited by 10 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is the motion distortion problem [2], [18]. Retargeting is done only for preserving the original important visual objects of each frame and removing unimportant regions of each frame of videos, so there is a content-aware retargeting method [1][2], [4], [11]. Video retargeting includes some issues such as motion distortion, shape and structure preservation [2].…”

Section: Video Retargeting Using Image Warpingmentioning

confidence: 99%

“…In video retargeting, it is a need to consider frame by frame flow of the video, so there is flow problem means frame retargeting is done only for one frame, then it needs to do retargeting same work for each frame [11]. If retargeting is considered per second frames then each frame flows in some motion, so there is distortion in frame warping is due to the motion of the frame [2], [18].…”

Section: Motion Distortionmentioning

confidence: 99%

See 1 more Smart Citation

Issues and Challenges in Content-Based Media Retargeting

Fule

Theng

2014

2014 Fourth International Conference on Communication Systems and Network Technologies

View full text Add to dashboard Cite

Smartphones are rapidly increasing in this technological world, in that visual media is the most important thing in mobile arena and due to visual graphical world everyone wants high graphical visual media. Now a day demands of videos and images are very high, some devices support HD images and HD videos and some does not. It is due to the low resolution support of the device like some small screened phones which comes with low screen supporting only one or two aspect ratios. So media retargeting is the technique to resize visual media like images or videos and fit it to different resolution displays and aspect ratios while by keeping important regions as it is in that visual media. There are media retargeting like image retargeting and video retargeting to resize the media and fit to appropriate display without changing any content of media it is content-aware retargeting. By removing visual salient objects from media and resizing by image warping can be suitable for streaming online videos.

show abstract

Section: Video Retargeting Using Image Warpingmentioning

confidence: 99%

Section: Motion Distortionmentioning

confidence: 99%

Issues and Challenges in Content-Based Media Retargeting

Fule

Theng

2014

2014 Fourth International Conference on Communication Systems and Network Technologies

View full text Add to dashboard Cite

show abstract

“…However, the methods cannot guarantee that the cutting of meaningful content can be avoided. In the seam carving methods [7], [16], [17], [18], [19], [20], [21], a onepixel width continuous or discontinuous surface seam with minimal significance in the space-time volume is iteratively carved or inserted to reduce or enlarge the input video to the desired aspect ratio. This technique allows for high flexibility in pixel removal, and thus, can be applied to some interesting applications, such as object removal.…”

Section: Related Workmentioning

confidence: 99%

Content-Aware Video Retargeting Using Object-Preserving Warping

Lin

Yeh

et al. 2013

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Abstract-A novel content-aware warping approach is introduced for video retargeting. The key to this technique is adapting videos to fit displays with various aspect ratios and sizes while preserving both visually salient content and temporal coherence. Most previous studies solve this spatiotemporal problem by consistently resizing content in frames. This strategy significantly improves the retargeting results, but does not fully consider object preservation, sometimes causing apparent distortions on visually salient objects. We propose an object-preserving warping scheme with object-based significance estimation to reduce this unpleasant distortion. In the proposed scheme, visually salient objects in 3D space-time space are forced to undergo as-rigid-as-possible warping, while lowsignificance contents are warped as close as possible to linear rescaling. These strategies enable our method to consistently preserve both the spatial shapes and temporal motions of visually salient objects and avoid overdeformations on low-significance objects, yielding a pleasing motion-aware video retargeting. Qualitative and quantitative analyses, including a user study and experiments on complex videos containing diverse cameras and dynamic motions, show a clear superiority of our method over related video retargeting methods.

show abstract

“…However, this method could distort or remove important objects on images with complex backgrounds. Several methods [2][3][4][5][6][7] have been proposed to address this problem.…”

mentioning

confidence: 99%