Multiresolution Vision in Autonomous Systems
The performance of many autonomous systems based on artificial vision depends mainly on the speed of response and the field of view of the vision systems. The many tasks to be carried out, such as object detection, recognition, tracking, etc., the complexity of reliable algorithms and tasks to be done in real time, and the huge data volumes involved with stereo vision systems, imply processing times and resources that, in some cases, are incompatible with or unsuitable for acceptable system operation. Multiresolution systems are one alternative to cover wide fields of view without involving high data volumes and, therefore, considerably reduce the constraints imposed by off-the-shelf uniresolution vision systems.
Our work is related to adaptive space-variant sensors, able to supply any number of resolution levels with reconfigurable resolution profiles around regions or objects of interest, and to the specific algorithms and hierarchical data structures related to processing multiresolution data involved in tasks of image segmentation, object detection, etc. required for operation in dynamic environments.
KeywordsRetinal Image Compute Cell Active Vision Camera Parameter Stereo Vision System
Unable to display preview. Download preview PDF.
- 1.Marr D (1982) Vision, MIT Press.Google Scholar
- 2.Swain MJ, Stricker M (1993) (eds.) Promising Directions in Active Vision. Int. Journal of Computer Vision 11:109–126.Google Scholar
- 3.Aloimonos JY, Weiss I, Bandyopadhyay A (1987) Active Vision. Int. Journal of Computer Vision 8:333–356.Google Scholar
- 4.Bajcsy R (1998) Active Perception. IEEE Proceedings, 76:996–1006.Google Scholar
- 13.Kathman A, Johnson E (1992) Binary Optics: new diffractive elements for the designer tool kit. Photonic Spectra 9:125–132.Google Scholar
- 14.Camacho P, Arrebola F, Sandoval F (1998) Multiresolution Sensors with Adaptive Structure. 24th IEEE Intnl. Conf. Industrial Electronics, IECON’98, 2:1230–1235.Google Scholar
- 15.Rojer AS, Schwartz EL (1990) Design considerations for space-variant visual sensor with complex-logartihmic geometry. 10th Intnl. Conf. on Pattern Recognition 2:278–285.Google Scholar
- 16.Scott P, Bandera C (1990) Hierarchical Multiresolution Data Structures and Algorithms for Foveal Vision Systems. IEEE Intnl. Conf on System, Man and Cybernetics, 832–834.Google Scholar
- 22.Arrebola F, Urdiales C, Camacho P, Sandoval F (1998) Vision System Based on Shifted Fovea Multiresolution Retinotopologies. 24th IEEE Intnl. Conf. Industrial Electronics IECON’98, 3:1357–1361.Google Scholar
- 28.Arrebola F (1998), Sistema Multirresolucin Basado en Imgenes Multirresolucin de Fvea Desplazable, (in Spanish) Ph. D. thesis, Malaga University.Google Scholar
- 30.Coslado F, Camacho P, Gonzlez M, Sandoval F (2001) Hardware Implementation of a Node Linking Segmentation Algorithm, Proc. XVI Conf. on Design of Circuits and Integrated Systems, DCIS2001, 654–659.Google Scholar