首页> 外国专利> GPU SURF Complexity Reduction Method of SURF algorithm based on Frame Difference in the Mobile GPU environment

GPU SURF Complexity Reduction Method of SURF algorithm based on Frame Difference in the Mobile GPU environment

机译:移动GPU环境下基于帧差的SURF算法的GPU SURF复杂度降低方法

摘要

The present invention relates to a method for reducing computation of a SURF algorithm using difference images in a mobile GPU environment; Obtaining a current frame of the image from the camera; A second step of generating difference image data by calculating a difference between a current frame and a previous frame to store coordinate values of a region having no change or a small change such as a changed region of the previous frame and a current frame and a background; A third step of generating an integral image by receiving coordinate values stored in the difference image; And a fourth step of calculating a Hessian detector using the integral image and storing orientation information and descriptor information of the feature point. According to the present invention, when the SURF algorithm of moving image input is performed, the calculation is reduced by using the difference image between the previous frame and the current frame of the moving image, thereby improving the image processing speed.
机译:本发明涉及一种在移动GPU环境中使用差异图像来减少SURF算法的计算的方法。从摄像机获取图像的当前帧;通过计算当前帧与前一帧之间的差以存储诸如前一帧与当前帧以及背景的变化区域之类的不变或小的变化的区域的坐标值来生成差异图像数据的第二步骤;第三步,通过接收存储在差异图像中的坐标值来产生积分图像;第四步骤,使用积分图像计算Hessian检测器,并存储特征点的方位信息和描述符信息。根据本发明,当执行运动图像输入的SURF算法时,通过使用运动图像的前一帧和当前帧之间的差异图像来减少计算,从而提高了图像处理速度。

著录项

  • 公开/公告号KR101853468B1

    专利类型

  • 公开/公告日2018-04-30

    原文格式PDF

  • 申请/专利权人 인하대학교 산학협력단;

    申请/专利号KR20160131185

  • 发明设计人 이채은;조형래;

    申请日2016-10-11

  • 分类号G06T7/20;G06T5/50;G06T9;

  • 国家 KR

  • 入库时间 2022-08-21 12:37:55

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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