Enhanced Point Descriptors
We are focused on how to describe a common image point distinctively, make its descriptor concise and invariant to general image transformations. We use neighborhood pixel characteristics, including HSV color space, Gaussian-weighted gradient magnitudes and orientations, sampled in specific window around interest point to enhance the description. The enhanced point descriptor (EPD) is a covariance matrix of the above-mentioned image characteristics. Experimental results show that, the performance of EPD, in the distinctiveness and invariance aspects, is as good as now popular local descriptors (SIFT and SURF), while the time cost of descriptor construction and matching is far less than them. Moreover, in comparison with SIFT and SURF, the EPD combines more image characteristics, which makes it be able to describe common image points, but not limited to the image extreme points. These advantages make the EPD finding new applications in the field of dense stereo matching.
Haitao Lang Lanyifei Lei Yongtian Wang
Beijing University of Chemical Technology Beijing, 100029, China Beijing Institute of Technology Beijing, 100029, China
国际会议
上海
英文
677-681
2010-10-20（万方平台首次上网日期，不代表论文的发表时间）