Multi-target tracking is a challenge due to the variable number of targets and the frequent interaction between targets in complex dynamic environments. This paper presents a multi-target tracking algorithm based on bipartite graph matching. Unlike previous approaches, the method proposed considers the target tracking as a bipartite graph matching problem where the nodes of the bipartite graph correspond to the targets in two neighboring frames, and the edges correspond to the degree of the similarity measure between the targets in different frames. Finding correspondence between the targets is formulated as a maximal matching problem which can be solved by the dynamic Hungarian algorithm. Then, merging and splitting of the targets detection is proposed, the candidate occlusion region is predicted according to the overlapping between the bounding boxes of the interacting targets to handle the mutual occlusion problem. The extensive experimental results show that the algorithm proposed can achieve good performance on dynamic target interactions compared to state-of-the-art methods.
Unlike regular three-dimensional solids two of a nanotube dimensions are confined and quantized. Bulk samples consist of irregular networks of merging and splitting bundles of parallel tubes. On a local scale, nanotubes are at the same time one-dimensional crystals and two-dimensional quantum rings. They have attracted extensive studies on individual aspects in their electronic and optical properties . The current contribution aims at bridging the fundamental physical concepts behind carbon nanotubes to their unique spectroscopic signatures in optical absorption, luminescence, Raman and electron energy loss spectroscopy. The aim is not to compete with the local depth of a focused review, but to briefly convey the physical concept and related spectroscopic signatures of one-dimensionality. Indirect signatures are the manifold appearances of van Hove singularities in their optical transitions. Direct probes of one-dimensionality unveil the confined momentum space, which manifests in the distinction of localized and propagating excitations.
; pp 1-6. Kustár A, Forró L, Kalina I, Fazekas F, Honti S, Makra S, Friess M. 2013. FACE-R--a 3D database of 400 living individuals’ full head CT- and face scans and preliminary GMM analysis for craniofacial reconstruction. J Forensic Sci 58(6):1420-8. Kusumoputro B, Satria Y. 2003. Development of 3D face databases by using mergingandsplitting eigenspace models, WSEAS Transactions on Computers 2(1):203-9. Maal TJ, Plooij JM, Rangel FA, Mollemans W, Schutyser FA, Bergé SJ. 2008. The accuracy of matching three-dimensional photographs with skin surfaces derived from
iteration. When given parameters, this modification is achieved by mergingandsplitting, we can (refer to the Reference [ 33 ]). In order to deal with data clustering problems with different data distributions, it is necessary to select different similarity measures between sample points, so that different types of K -means improved models can be obtained. Kernel K -means model is similar to the idea of kernel function in support vector machine, mapping all samples to another vector space and clustering [ 31 ]. Fuzzy C -means model introduces the fuzzy factors