Examinando por Materia "Classification (of information)"

Mostrando 1 - 5 de 5
  • No hay miniatura disponible
    Publicación
    Barriers and success factors in lean construction implementation-survey in pilot context
    (Lean Construction, 2015-07-31) Cano, Sandra; Botero- B, Luis-F; Delgado, Jonathan; RUBIANO, OSCAR; Universidad EAFIT. Departamento de Ingeniería Civil; Gestión de la Construcción
    The study identifies a set of barriers and critical success factors (CSF) involved in the implementation of Lean Construction (LC) through three phases: Literature's Collection, with analysis and obtained information processing
  • No hay miniatura disponible
    Ítem
    Gunshot identification system by integration of open source consumer electronics
    (SPIE-INT SOC OPTICAL ENGINEERING, 2014-01-01) López R., J.M.; Marulanda B., J.I.; López R., J.M.; Marulanda B., J.I.; Universidad EAFIT. Departamento de Ciencias; Electromagnetismo Aplicado (Gema)
    This work presents a prototype of low-cost gunshots identification system that uses consumer electronics in order to ensure the existence of gunshots and then classify it according to a previously established database. The implementation of this tool in the urban areas is to set records that support the forensics, hence improving law enforcement also on developing countries. An analysis of its effectiveness is presented in comparison with theoretical results obtained with numerical simulations. © 2014 SPIE.
  • No hay miniatura disponible
    Ítem
    Gunshot identification system by integration of open source consumer electronics
    (SPIE-INT SOC OPTICAL ENGINEERING, 2014-01-01) López R., J.M.; Marulanda B., J.I.; Universidad EAFIT. Departamento de Ciencias Básicas; Óptica Aplicada
    This work presents a prototype of low-cost gunshots identification system that uses consumer electronics in order to ensure the existence of gunshots and then classify it according to a previously established database. The implementation of this tool in the urban areas is to set records that support the forensics, hence improving law enforcement also on developing countries. An analysis of its effectiveness is presented in comparison with theoretical results obtained with numerical simulations. © 2014 SPIE.
  • No hay miniatura disponible
    Ítem
    Spatial layout and surface reconstruction from omnidirectional images
    (Institute of Electrical and Electronics Engineers Inc., 2016-01-01) Posada, L.F.; Velasquez-Lopez, A.
    This paper presents a spatial layout recovery approach from single omnidirectional images. Vertical structures in the scene are extracted via classification from heterogeneous features computed at the superpixel level. Vertical surfaces are further classified according to their main orientation by fusing oriented line features, floor-wall boundary features and histogram of oriented gradients (HOG) with a Random Forest classifier. Oriented line features are used to build an orientation map that considers the main vanishing points. The floor-wall boundary feature attempts to reconstruct the scene shape as if it were observed from a bird's-eye view. Finally, the HOG descriptors are aggregated per superpixel and summarize the gradient distribution at homogeneous appearance regions. Compared to existing methods in the literature which rely only on corners or lines, our method gains statistical support from multiple cues aggregated per superpixel which provide more robustness against noise, occlusion, and clutter. © 2016 IEEE.
  • No hay miniatura disponible
    Ítem
    Spatial layout and surface reconstruction from omnidirectional images
    (Institute of Electrical and Electronics Engineers Inc., 2016-01-01) Posada, L.F.; Velasquez-Lopez, A.; Posada, L.F.; Velasquez-Lopez, A.; Universidad EAFIT. Departamento de Ciencias; Ciencias Biológicas y Bioprocesos (CIBIOP)
    This paper presents a spatial layout recovery approach from single omnidirectional images. Vertical structures in the scene are extracted via classification from heterogeneous features computed at the superpixel level. Vertical surfaces are further classified according to their main orientation by fusing oriented line features, floor-wall boundary features and histogram of oriented gradients (HOG) with a Random Forest classifier. Oriented line features are used to build an orientation map that considers the main vanishing points. The floor-wall boundary feature attempts to reconstruct the scene shape as if it were observed from a bird's-eye view. Finally, the HOG descriptors are aggregated per superpixel and summarize the gradient distribution at homogeneous appearance regions. Compared to existing methods in the literature which rely only on corners or lines, our method gains statistical support from multiple cues aggregated per superpixel which provide more robustness against noise, occlusion, and clutter. © 2016 IEEE.