| 摘要 |
A reframing application crops a sub part of a video source based on its content. The application includes a visual attention module generating a saliency map and exclusive reframing algorithm estimating a cropping window based on the saliency map. After cropping, only reframed part of each video image is still shown. A method for processing images of a video sequence includes a step (21) of determining parameters of the video sequence, parameters of a sub sequence decoded before the video sequence, and user settings, a step (22) of determining a part to be cropped according to the determined parameters, and a step (23) of cropping the determined part for display. The advantage of the invention is to provide an automatic solution for automatically tuning reframing parameters based on the content of the video. |
