首页> 外文会议>International Conference on Control, Automation, Robotics Vision >Hand-held 3D Dense Map Construction System Based on Improved ICP Algorithm
【24h】

Hand-held 3D Dense Map Construction System Based on Improved ICP Algorithm

机译:基于改进ICP算法的手持3D密集地图施工系统

获取原文

摘要

In view of the problems of poor image quality and inaccurate positioning due to interference in interactive control systems, this paper proposes a non-local mean algorithm (NLM) based on adaptive median algorithm (ALM) based on the strategy of salt and pepper noise processing), and applied to non-contact interactive systems based on laser sensors. The main innovations of this paper: 1) In the image preprocessing algorithm, a noise reduction method that is effective for Gaussian noise, salt and pepper noise, and mixed noise of both of them is proposed; 2) The improved denoising algorithm is applied to lidar-based sensor's non-contact interactive system, which significantly improves the interactive performance. Experimental results show that the proposed algorithm has obvious denoising effect, accurate image positioning and good target tracking effect.
机译:鉴于图像质量差和由于交互式控制系统的干扰导致的图像质量不佳,基于盐和辣椒噪声处理策略提出了一种基于自适应中值算法(ALM)的非局部平均算法(NLM) ),并应用于基于激光传感器的非接触式交互系统。本文的主要创新:1)在图像预处理算法中,提出了一种对高斯噪声,盐和胡椒噪声有效的降噪方法,以及它们两者的混合噪声; 2)改进的去噪算法应用于基于LIDAR的传感器的非接触式交互式系统,这显着提高了交互式性能。实验结果表明,该算法具有明显的去噪效果,准确的图像定位和良好的目标跟踪效果。

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