Description: A method to detect new objects in a scene by
comparing an input query image and a movie database captured beforehand is proposed.
Our method is based on both feature point matching and edge matching. First, we select the most matched movie from the movie
database based on the number of matched feature points. In addition,
we can get unmatched points in the query by excluding the matched points from all the extracted feature points in the query. Next, the most matched frame is selected from the most matched movie. It has the most
matched points with an input query image. Canny edge detector is applied
to both the query and the most matched frame in order to find unmatched edges. By merging the results of unmatched points and unmatched
edges, new objects will be detected. Our method can be applied to various scenes such as indoor and outdoor. In experimental results, we represent that our proposed method achieves change detection in various scenes.
File list (Check if you may need any files):
vcas_2009.pdf
Download