ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper 2.5D Body Estimation via Refined Forest with Field-based Objective
Cited 0 time in scopus Download 4 time Share share facebook twitter linkedin kakaostory
Authors
Jaehwan Kim, HoWon Kim
Issue Date
2017-11
Citation
International Conference on Machine Vision (ICMV) 2017, pp.1-5
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1117/12.2310059
Project Code
17CS1100, Development of Mobile Measure-based 3D Modeling and Realistic-Experience Technology for the Mobile 3D Content Service, Kim Ho Won
Abstract
In this paper, we present a 2.5D?닓 body region classification method based on the global refinement of random forest. The refinement of random forest provides the reduction of the size of training model with preserving prediction accuracy. We also incorporate the field-inspired objective to the random forest in consideration of the pairwise spatial relationships between neighboring data points. Numerical and visual experiments with artificial 3D data confirm the usefulness of the proposed method.
KSP Keywords
3D data, Classification method, Prediction accuracy, Random forest, Region classification, Spatial relationships, Visual experiments, training model