• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Image Processing >FAST 2D-TO-3D MATCHING WITH CAMERA POSE VOTING FOR 3D OBJECT IDENTIFICATION
【24h】

FAST 2D-TO-3D MATCHING WITH CAMERA POSE VOTING FOR 3D OBJECT IDENTIFICATION

机译：与相机姿势投票的快速2D-3D匹配3D对象识别

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we propose a fast non-iterative camera pose voting method for 3D object identification. The proposed method improves the accuracy and speed upon the conventional local feature based 2D-to-3D matching between a 2D image and a 3D model reconstructed by the structure-from-motion (SfM) pipeline. Instead of performing iterative RANSAC based method for geometric verification, the proposed method computes a hypothesis of camera pose from each feature correspondence between the query image and the 3D model. The camera pose is computed using scale, orientation and coordinate of the local features, calibrated by the camera matrix of the database image used to construct the 3D model. Then the most likely hypothesis is found by carrying out a two-stage clustering on the estimated camera poses in the parameter space. Experiment results on the 3D machine datasets show that our method improves the identification accuracy from 82.8% to 84.9% when FPR is 1%, compared with conventional RANSAC based method. In addition, the processing speed for the geometric verification is improved up to 25 times compared to the conventional method.
机译：在本文中，我们提出了一种快速的非迭代摄像机姿势投票方法，用于3D对象识别。所提出的方法在2D图像和由结构 - 来自运动（SFM）管道重建的2D图像和3D模型之间的2D-3D匹配之间的传统局部特征的准确度和速度提高了精度和速度。该提出的方法而不是执行基于几何验证的基于Ransac的基于Ransac方法，而不是执行用于几何验证的方法，而是从查询图像和3D模型之间的每个特征对应关系计算相机姿势的假设。使用本地特征的比例，方向和坐标计算相机姿势，由用于构造3D模型的数据库映像的相机矩阵校准。然后通过在参数空间中的估计相机姿势上执行两阶段聚类来发现最可能的假设。与常规RANSAC的方法相比，3D机器数据集上的实验结果表明，当FPR为1％时，我们的方法将识别准确性提高了82.8％至84.9％。另外，与传统方法相比，几何验证的处理速度高达25次。

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