Accurate 3D measuring systems thrive in the past few years. Most of them are based on laser scanners because\nthese laser scanners are able to acquire 3D information directly and precisely in real time. However, comparing to\nthe conventional cameras, these kinds of equipment are usually expensive and they are not commonly available to\ncustomers. Moreover, laser scanners interfere easily with each other sensors of the same type. On the other hand,\ncomputer vision-based 3D measuring techniques use stereo matching to acquire the cameras� relative position and\nthen estimate the 3D location of points on the image. Because this kind of systems needs additional estimation of\nthe 3D information, systems with real time capability often relies on heavy parallelism that prevents implementation\non mobile devices.\nInspired by the structure from motion systems, we propose a system that reconstructs sparse feature points to a 3D\npoint cloud using a mono video sequence so as to achieve higher computation efficiency. The system keeps tracking\nall detected feature points and calculates both the amount of these feature points and their moving distances. We\nonly use the key frames to estimate the current position of the camera in order to reduce the computation load and\nthe noise interference on the system. Furthermore, for the sake of avoiding duplicate 3D points, the system\nreconstructs the 2D point only when the point shifts out of the boundary of a camera. In our experiments, we show\nthat our system is able to be implemented on tablets and can achieve state-of-the-art accuracy with a denser point\ncloud with high speed.
Loading....