QQ客服 官方微博 反馈留言

浏览/检索结果: 共1条，第1-1条 帮助 已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序题名升序题名降序发表日期升序发表日期降序提交时间升序提交时间降序 Scene matching based on directional keylines and polar transform (EI CONFERENCE) 会议论文 2010 IEEE 10th International Conference on Signal Processing, ICSP2010, October 24, 2010 - October 28, 2010, Beijing, China Zhang Y.; Qu H.; Wang Y. 收藏  |  浏览/下载：19/0  |  提交时间：2013/03/25 Scene matching under complex background is a priority and difficulty in the field of computer vision  it has the characteristics of rotation and scaling invariance  commonly used in matching real-time collected images and photos for navigation. Scene matching techniques are faced with complex natural scenes  anti-light and anti-slight-distortion  the image distortion exist  applicable for complex scene matching. The project has a new idea: combining the keylines with the vectors description based on polar image translation  such as light  and utilize the rotation-scale-invariance vectors to describe the extracted keylines  change of gray levels  this method includes three steps: keylines extraction  perspective  description and matching. Preliminary experiments show that this keylines-based scene matching algorithm is applicable for image matching under complex background. 2010 IEEE.  scaling and other differences  which cause matching difficult. This paper aims to find a scene matching algorithm