Color-based tracking is prone to failure in situations where visually similar targets are moving in a close proximity or occlude each other. To deal with the ambiguities in the visual information, we devised a color-independent visual model based on the target's local motion. This model is calculated from the optical flow induced by the target in consecutive images. A combined color/local-motion-based tracker is constructed that resolves situations when the target is occluded by, or moves in front of, a visually similar object.
COBISS.SI-ID: 7086164
The computational complexity of the meshless local Petrov-Galerkin method (MLPG) has been analyzed and compared with FDM and FEM. Theoretically, MLPG is the most complex of the three methods. Experimental results show that MLPG, with appropriately selected integration order and dimensions of support and quadrature domains, achieves similar accuracy as FEM. The parallel complexity and speed-up of MLPG scales well on larger systems. The normalized computational complexity makes FEM the best choice. MLPG remains competitive if human assistance is needed for meshing.
COBISS.SI-ID: 21895463
The main problems in computer-vision-based tracking of a large number of interacting targets are unpredictable behavior, collisions, occlusions, ambiguities involved in detecting and recognizing moving targets. Our approach integrates state-of-the-art tracking methods based on particle filtering, dynamic Voronoi diagram generation and physical model for collision disambiguation, and closed-world paradigm. The method is used for tracking players in team sports.
COBISS.SI-ID: 6401620
BEsTRF (Best Estimated T-RF) provides a standalone environment for analyzing primers-enzymes-gene section combinations used in terminal-restriction fragment length polymorphism (T-RFLP) for its optimal resolution. User-defined sequence databases of several hundred thousand DNA sequences can be explored. Sequence quality, primer mismatches, insertions and deletions can be controlled and. The configuration for a novel T-RFLP population profiling using rpoB gene (DNA-directed RNA polymerase, beta subunit) on forward fluorescently labeled primer are presented.
COBISS.SI-ID: 2450312
In this paper we apply a recent approach, called flexibility, to solving two-stage flexible-choice problems. The aim of a decision maker is to find a solution in the present that is as easy as possible to adapt to solutions in the future. We present computational complexity results and algorithms for two versions of the two-stage flexible-choice problem. We prove NP-hardness and non-approximability, and describe an exact and approximations polynomial-time algorithms for different versions of the problem.
COBISS.SI-ID: 7087444