Robust Light Objects Recognition Based on Computer Vision

Abstract

This paper proposes a recognition method for light objects in a video for real-time application and the movement of the surrounding objects. The method extracts the objects by considering known geometric arrangements and blinking frequency, while the latter is also used to remove the image noise. Therefore, locations of the light objects can be found rapidly, and the on-off blinking states of these objects can be recognized accordingly if the frame rate of the video is sufficient. Besides, it can be used in the image recognition unit of a light communication system.