Fast triangular binning kernel approximations for weighted gradient histogram creation
2014 (English)In: 2014 IEEE International Conference on Electronics, Computing and Communication Technologies (IEEE CONECCT), 2014, 6740351- p.Conference paper (Refereed)
The implementation of weighted gradient histograms are studied. Such histograms are commonly used in computer vision methods, and their creation can make up a significant portion of the computational cost. Further, due to potentially severe aliasing, non-uniform binning kernels are desirable. We show that previously presented fast methods for uniform binning kernels can be extended to non-uniform binning, and that the triangular kernel can be well approximated for common weighting strategies. The approximation is implemented with sums and products of projections of the gradient samples on specially chosen vectors. Consequently, only a few standard arithmetic operations are required, and therefore, the suggested implementation has a significantly lower computational cost when compared with an implementation in which the gradient argument and magnitude are explicitly evaluated. Finally, the frequency components of the different kernels are studied to quantify the fundamental gain achieved by using triangular kernels instead of uniform kernels.
Place, publisher, year, edition, pages
2014. 6740351- p.
Arithmetic operations, Computational costs, Fast methods, Frequency components, Gradient histograms, Kernel approximation, Non-uniform, Weighting strategies, Communication systems, Computer vision, Statistical methods
IdentifiersURN: urn:nbn:se:kth:diva-136275DOI: 10.1109/CONECCT.2014.6740351ISI: 000349779700066ScopusID: 2-s2.0-84900674987ISBN: 978-1-4799-2318-2OAI: oai:DiVA.org:kth-136275DiVA: diva2:675685
2014 IEEE International Conference on Electronics, Computing and Communication Technologies, IEEE CONECCT 2014; Bangalore; India; 6 January 2014 through 7 January 2014
QC 201402252013-12-042013-12-042015-03-27Bibliographically approved