ORB_an efficient alternative to SIFT or SURF

【文件属性】：
文件名称：ORB_an efficient alternative to SIFT or SURF
文件大小：2.25MB
文件格式：PDF
更新时间：2016-11-16 04:38:44
ORB SIFT SURF Feature matching is at the base of many computer vision problems, such as object recognition or structure from motion. Current methods rely on costly descriptors for de­tection and matching. In this paper, we propose a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise. We demonstrate through experiments how ORB is at two orders of magni­tude faster than SIFT, while peiforming as well in many situations. The efficiency is tested on several real-world ap­plications, including object detection and patch-tracking on a smart phone.