【2010-10-22】 Visual Media Retargeting

Poster:Post date:2010-10-12

Title: Visual Media Retargeting
Prof. Yu-Shuen Wang
Time: 14:20, Oct 22 (Fri), 2010
Place: Room 103, CSIE Building

Research on automatic resizing of images and videos is becoming ever more important with the proliferation of display units, such as television, notebooks, PDAs and cell phones, which all come in different aspect ratios and resolutions. To achieve full presentation of images and videos, we introduce a content aware technique which considers the interior pixels while resizing images and videos. Specifically, we represent an image/frame with a grid mesh and then warp the mesh based on the saliency measure. Unlike the previous methods, which strove to preserve the prominent objects untouched, our method allows them to be scaled uniformly, enabling the distortion propagation in multiple directions. In addition to the resizing of static images, we extend our resizing technique to videos. The most important issue on this extension is the temporal coherence since the interior contents keep changing when the video is played. Due to the camera and object motions, simply preserving consistent resizing of temporally adjacent pixels cannot achieve temporal coherence and thus, resulting in flickering or waving artifacts. To solve this problem, we detect the object motions based on optical flows. We then introduce the temporal constraints to preserve corresponding objects in neighboring frames to have the same resizing. All the criteria are formulated into energy terms and we solve for the resized images and
videos by minimizing the objective function.

As attached.
Attached File:
Last modification time:2010-10-18 PM 4:43

cron web_use_log