首页> 外文会议>International Conference on Knowledge-Based and Intelligent Information and Engineering Systems >Intelligent Texture Reconstruction of Missing Data in Video Sequences Using Neural Networks
【24h】

Intelligent Texture Reconstruction of Missing Data in Video Sequences Using Neural Networks

机译:基于神经网络视频序列中缺失数据的智能纹理重建

获取原文

摘要

The missing data appear in video sequences after removal of nondisabled objects or artifacts. We have proposed an intelligent method of texture reconstruction which novelty consists in a mode of texture estimations using separated neural networks, a boundaries interpolation into a missing data region by a fast wave algorithm, and a texture in painting considering spatio-temporal parameters of surrounding region. We suggest three strategies of wave algorithm for contour optimization into a missing data region. The proposed technique was tested for visual reconstruction of small missing regions such as subtitles, logotypes and large regions (less 8-12% of frame area). In the first case we have a simplified decision without stage of boundaries approximation, in the second case a background complexity and motions in scene determine significantly the reconstruction results.
机译:丢失数据在删除非残疾对象或工件后显示在视频序列中。我们已经提出了一种智能纹理重建方法,该方法是使用分离的神经网络的纹理估计模式,通过快速波算法将边界插入缺失的数据区域,以及考虑周围区域的时空参数的绘画中的纹理。我们建议三个波浪算法的策略,以将轮廓优化到缺失的数据区域中。该提出的技术被测试用于对小缺失区域的视觉重建,例如字幕,标识符和大区域(较少8-12%的框架区域)。在第一种情况下,我们在没有边界阶段的情况下具有简化的决定,在第二种情况下,场景中的背景复杂性和动作决定了重建结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号