English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/133963

Segmentation-aware deformable part models

AutorTrulls, Eduard; Tsogkas, Stavros; Kokkinos, Iasonas; Sanfeliu, Alberto; Moreno-Noguer, Francesc
Fecha de publicación2014
EditorInstitute of Electrical and Electronics Engineers
CitaciónIEEE Computer Society Conference on Computer Vision and Pattern Recognition: 168-175 (2014)
ResumenIn this work we propose a technique to combine bottom-up segmentation, coming in the form of SLIC superpixels, with sliding window detectors, such as Deformable Part Models (DPMs). The merit of our approach lies in >cleaning up> the low-level HOG features by exploiting the spatial support of SLIC superpixels, this can be understood as using segmentation to split the feature variation into object-specific and background changes. Rather than committing to a single segmentation we use a large pool of SLIC superpixels and combine them in a scale-, position- and object-dependent manner to build soft segmentation masks. The segmentation masks can be computed fast enough to repeat this process over every candidate window, during training and detection, for both the root and part filters of DPMs. We use these masks to construct enhanced, background-invariant features to train DPMs. We test our approach on the PASCAL VOC 2007, outperforming the standard DPM in 17 out of 20 classes, yielding an average increase of 1.7% AP. Additionally, we demonstrate the robustness of this approach, extending it to dense SIFT descriptors for large displacement optical flow.
DescripciónTrabajo presentado a la IEEE Conference on Computer Vision and Pattern Recognition (CVPR), celebrada del 23 al 28 de junio de 2014 en Columbus, Ohio (US).
Versión del editorhttp://dx.doi.org/10.1109/CVPR.2014.29
Identificadoresdoi: 10.1109/CVPR.2014.29
issn: 1063-6919
Aparece en las colecciones: (IRII) Artículos
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
Segmentation-aware.pdf6,41 MBUnknownVisualizar/Abrir
Mostrar el registro completo

Artículos relacionados:

NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.