University of Glasgow at Image CLEF 2009 Robot Vision Task.
Yue Jiang Feng, Martin J. Halvey, Joemon M. Jose · 2009
The submission from the Multimedia Information Retrieval Group at the University of Glasgow for the ImageCLEF 2009 Robot Vision Task combines point matching methodologies with rule based decision techniques. Instead of the whole image we use a large set of interesting points extracted from the image contents to represent each image. The points of interest are extracted using an edge corner detector. The RANAC method [3] was then applied to estimate the similarity between the test and training images based on the number of matched pairs of points. The location of robot is then annotated based on the training image that contains the highest number of matched point pairs with the test image. A set of decision rules with the respect to the trajectory behaviour of robot’s motion are defined to refine the final results. An illumination filter was also applied for two of the runs in order to reduce the illumination effect. Three runs were submitted using the different of combination of the above approaches.