A Calculation Method of Degree of Data Indication Regions in First-Person View Videos for Improvement Transportation
Takayuki Abe, Sho Takahashi, Toru Hagiwara · 2019
In this paper, we propose a calculation method of degree for detecting regions of various data indication in first-person view videos. In recent years, contents of augmented reality (AR) have been implemented due to advances in computer hardware and interface. By indicating the data on road user's view, intelligent transport systems (ITS) is enhanced. However, since the user's view includes a lot of visually important information which the user should perceive, for indicating the data on the user's view, it is necessary to detect regions that do not include the information. In our method, degree as criteria is obtained based on seam carving and saliency map model. By utilizing the degree, it is possible to adaptively detect the regions of the data indication from different viewpoints. Experimental results show the effectiveness of our method.