Estimation of the Depth Information from Single View Image Sequence with Camera Translation

摘要

The general problems of recovering 3D from 2D imagery require the depth information for each picture element from focus. The manual creation of those 3D models is time consuming and cost expensive. The goal in this paper is to estimate the depth information of every region from single view image sequence with camera translation. This paper is based on the property that the motion of every point within image which taken from camera translation depends on depth information. Full-search motion estimation based on block matching algorithm is exploited at first step with image that compensated for camera rotation and zooming. We have introduced a framework that estimates the depth of objects by analysis of single view motion picture and also calculates the average of frame depth and relative depth of region to the average depth. Simulation results show that the depth of region belongs to a near object or a distant object is in accord with relative depth that man recognizes.