Utilization image of monocular camera to build navigation system and path mapping using SURF approach

摘要

Navigation system of some camera devices such as robot could be done by measure the rotation of device's wheels and device's velocity. But in several cases, like device for rescue and surveillance, sometimes the device need to deal with an uneven surface that makes device's wheels slipped, impacting in navigation measurement. Fortunately, almost all of devices nowadays equipped with at least one camera to monitor the environment. So, this research purpose to utilization image of the camera vision that's been captured to build a navigation system. We will show that a simple monocular camera could build an alternative navigation system for several uses, while the system also navigates and tracks camera's paths to draw the path mapping. Firstly, we tried to detect the camera motion and its direction by using optical flow model. To improve this model, we use feature transform, which is SURF. Secondly, after we know the direction from feature transform, we got the formula to know the real direction and use it for drawing the path that camera took for tracking. We tested our application directly in our video stream camera and compare the system coordinate with the real world coordinate in centimeters unit.