| Abstract: |
We propose to use symmetry as a global feature for mobile robot applications in an indoor environment. Our mobile robot solely uses an omnidirectional vision sensor consisting of a digital colour video camera and a hyperbolic mirror. Thus, robust image feature extraction is required for good performance in each application. The detection of symmetry is an effective natural vision routine resulting in more global features than edges, corner, etc. Each image can be reduced to certain points of symmetric interest, which can be tracked in all azimuthal directions and used for multiple tasks like range estimation, object classification and probably egomotion. In this paper, we present a qualitative symmetry algorithm, the results of range estimation and object classification experiments using symmetry as a feature in panoramic images. |
