Motion detection is the first important step in large applications of computer vision. Motion detection extracts moving objects from the background. There are many methods to do that. However, in most methods, if the input video has noise and light change, moving objects will not be extracted accurately. In this paper, we propose the method for motion detection which extracts moving objects from the background based on the image intensity ratio concept that is not affected by light change; therefore, the sensitivity with light change is overcome. The image intensity ratio is computed by the average intensity of current frame and the intensity of every pixel in that frame. The intensity ratio of a pixel is nearly unchanged between two frames. We apply the Lucas-Kanade optical flow method based on that image intensity ratio. Our proposed algorithm has good noise tolerance and is not affected by light change. For demonstrating the superiority of the proposed method, we have compared the results with the other recent methods available in literature.
CITATION STYLE
Quoc, P. B., & Binh, N. T. (2015). Motion detection based on image intensity ratio. In Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST (Vol. 144, pp. 350–359). Springer Verlag. https://doi.org/10.1007/978-3-319-15392-6_33
Mendeley helps you to discover research relevant for your work.