| 1. | Firstly , we do video segmentation and key frame extraction
首先，进行视频分割和提取关键帧。 |
| 2. | And also , the number of key frames can be slightly lesser than what it would have been with pure vertex based animation
因此，需要关键帧的数量较少一些，与基于顶点的动画而言它干净些。 |
| 3. | An advertisement search system base on the key frames and streams of h . 264 / avc is developed in this dissertation
在镜头边界检测的基础上,设计并实现了一个基于h . 264 / avc码流的视频广告查找系统。 |
| 4. | The key frames are detected using the motion features , color features and texture features of skin in key frame images
关键帧图象皮肤检测方法从皮肤的运动特征、颜色特征和纹理特征三个方面进行综合考量。 |
| 5. | Through the segmenting video into shots , we can represent the visual content of every shot with key frames abstractly
通过合理的把视频分割成镜头( shot ) ，我们可以用关键帧( keyframe )作为镜头视觉内容的有效抽象。 |
| 6. | In the area of computer graphics , most of the computer animations are made by traditional , time - consuming " key frame " technique
在计算机图形学中，大多数动画的创作是采用传统的、花费大量劳动的“关键帧”技术。 |
| 7. | Experiment shows that this key frame extraction method is efficient , the video abstraction can preferable express the video content
试验表明，这种关键帧提取算法是有效的，其建立的视频摘要能较好的反映原视频的内容。 |
| 8. | The main work in this thesis is video temporal segmentation , each video sequence could be hierarchically segmented as : scenes , shots and key frames
本文主要研究了视频时域分割问题,将整个视频划分为若干级的层次结构:场景、镜头、关键帧等。 |
| 9. | Based on this method , we also design a key frame extraction algorithm , which can transform the problem of recognition in videos to the problem of recognition in key frame images
同时，我们设计了相应的关键帧提取算法，将视频的皮肤检测问题转换为关键帧图象的皮肤检测问题。 |
| 10. | In our model , videos are represented in a hierarchical structure with four layers from frame , shot , scene to story unit , and key frames , etc . are introduced to describe the features and contents of layer
该模型描绘了从帧、镜头、场景到故事单元的结构化层次，并引入关键帧等概念分别描述每个层次的视频特征。 |
