Visual Target Detection in Unstructured Environments — A Novel Technique for Robotic Navigation
We report a novel method of visual modeling and detecting 3D rigid objects randomly located in complex cluttered environments. Models are built (in reference scale) using visual saliencies (interest points) in template images presenting the object of interest from various viewpoints. By matching interest point detected in camera-captured images (relative scale is used there) to visual saliencies from the database, the target objects are detected and verified. If a stereovision system is available, the procedure is separately performed for both cameras. Subsequently, the corresponding matches from both images can be used to solve the fundamental correspondence problem. The paper briefly discusses methodology and presents exemplary experimental results in vision-based robotic aplications.
KeywordsTarget Object Reference Image Interest Point Visual Saliency Moment Invariant
Unable to display preview. Download preview PDF.
- Hu, M.K. (1962). Visual pattern recognition by moment invariants. IRE Transactions on Information Theory 8: 179–187.Google Scholar
- Islam, M.S. (2005). Relative scale method to recognize and locate objects for robotic applications. PhD thesis, Nanyang Technological University, SingaporeGoogle Scholar
- Jurie, F. and Schmid, C. (2004). Scale-invariant shape features for recognition of object categories. Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition 2: II.90–II.96.Google Scholar
- Wong, A.K.C., Rong, L., and Liang, X. (1998). Robotic vision: 3D object recognition and pose determination. Proceedings of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, 1202–1209.Google Scholar