Automatic Selection and Detection of Visual Landmarks Using Multiple Segmentations
Detection of visual landmarks is an important problem in the development of automated, vision-based agents working on unstructured environments. In this paper, we present an unsupervised approach to select and to detect landmarks in images coming from a video stream. Our approach integrates three main visual mechanisms: attention, area segmentation, and landmark characterization. In particular, we demonstrate that an incorrect segmentation of a landmark produces severe problems in the next steps of the analysis, and that by using multiple segmentation algorithms we can greatly increase the robustness of the system. We test our approach with encouraging results in two image sets taken in real world scenarios. We obtained a significant 52% increase in recognition when using the multiple segmentation approach with respect to using single segmentation algorithms.
KeywordsSegmentation Algorithm Scale Invariant Feature Transform Salient Region Visual Landmark Landmark Detection
Unable to display preview. Download preview PDF.
- 2.Duncan, J.: Integrated mechanisms of selective attention. Current Opinion in Biology 7, 255–261 (1997)Google Scholar
- 3.Harris, S.: A combined corner and edge detector, pp. 147–151 (1988)Google Scholar
- 5.Karlsson, N., Goncalves, L., Munich, M., Pirjanian, P.: The vslam algorithm for navigation in natural environments. Korean Robotics Society Review 2(1), 51–67 (2005)Google Scholar
- 8.Munoz, X.: Image segmentation integrating colour, texture and boundary information. PhD thesis, Universitat de Girona (2002)Google Scholar
- 10.Soto, A.: A Probabilistic Approach for the Adaptive Integration of Multiple Visual Cues Using an Agent Framework. PhD thesis, Robotics Institute, Carnegie Mellon University (2002)Google Scholar
- 14.Walther, D.R., Edgington, D., Koch, C.: Detection and tracking of objects in underwater video, pp. 544–549 (2004)Google Scholar