• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Image Processing Algorithms and Techniques II >Restoration of distorted depth maps calculated from stereo sequences
【24h】

Restoration of distorted depth maps calculated from stereo sequences

机译：恢复从立体序列计算出的变形深度图

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Abstract: Passive depth map determination has become an important part of vision processing. Applications include autonomous navigation, robotic assembly, and aerial cartography. With the reliance of such systems on visual characteristics only, a need to overcome image degradations, such as from motion and out of focus blurring and random image-capture noise, is clearly necessary. These image degradations can limit the accuracy and reliability of depth and displacement information extracted from such sequences. In this paper a model based Kalman estimator is developed for spatial-temporal filtering of noise and other degradations in velocity and depth maps derived from image sequence or cinema. As an illustration of the proposed procedures, edge information from image sequences of rigid objects is used in the processing of the velocity maps by selecting from a series of models for directional adaptive filtering. Adaptive filtering then allows for noise reduction while preserving sharpness in the velocity maps. Results from several synthetic and real image sequences are given.!
机译：摘要：被动深度图的确定已经成为视觉处理的重要组成部分。应用程序包括自主导航，机器人组装和航图。由于仅依靠这些系统的视觉特性，显然有必要克服图像质量下降的问题，例如运动和散焦模糊以及随机图像捕获噪声引起的图像质量下降。这些图像质量下降可能会限制从此类序列中提取的深度和位移信息的准确性和可靠性。在本文中，开发了一种基于模型的卡尔曼估计器，用于噪声的时空滤波以及从图像序列或电影院获得的速度和深度图中的其他降级。作为所提出程序的说明，通过从一系列用于方向自适应滤波的模型中进行选择，将来自刚性物体图像序列的边缘信息用于速度图的处理。然后，自适应滤波可以减少噪声，同时保持速度图中的清晰度。给出了几个合成和真实图像序列的结果。

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