Sciweavers

Share
CVPR
2009
IEEE

Granularity-tunable Gradients Partition (GGP) Descriptors for Human Detection

10 years 2 months ago
Granularity-tunable Gradients Partition (GGP) Descriptors for Human Detection
This paper proposes a novel descriptor, granularitytunable gradients partition (GGP), for human detection. The concept granularity is used to define the spatial and angular uncertainty of the line segments in the Hough space. Then this uncertainty is backprojected into the image space by orientation-space partitioning to achieve efficient implementation. By changing the granularity parameter, the level of uncertainty can be controlled quantitatively. Therefore a family of descriptors with versatile representation property can be generated. Specifically, the finely granular GGP descriptors can represent the specific geometry information of the object (the same as Edgelet); while the coarsely granular GGP descriptors can provide the statistical representation of the object (the same as histograms of oriented gradients, HOG). Moreover, the position, orientation, strength and distribution of the gradients are embedded into a unified descriptor to further improve the GGP’s...
Yazhou Liu (Harbin Institute of Technology), Shigu
Added 09 May 2009
Updated 10 Dec 2009
Type Conference
Year 2009
Where CVPR
Authors Yazhou Liu (Harbin Institute of Technology), Shiguang Shan (Chinese Academy of Sciences), Wenchao Zhang (Chinese Academy of Sciences), Xilin Chen (Chinese Academy of Sciences), Wen Gao (Chinese Academy of Sciences)
Comments (0)
books