Sciweavers

204 search results - page 36 / 41
» Trainable Pedestrian Detection
Sort
View
CVPR
2009
IEEE
1413views Computer Vision» more  CVPR 2009»
16 years 7 months ago
Learning Semantic Scene Models by Object Classification and Trajectory Clustering
The visual surveillance task is to monitor the activity of objects in a scene. In far-field settings (i.e., wide outdoor areas), the majority of visible activities are objects movi...
Hanqing Lu, Stan Z. Li, Tianzhu Zhang
ICCV
2009
IEEE
16 years 4 months ago
Patch based Within-Object Classification
Advances in object detection have made it possible to collect large databases of certain objects. In this paper we exploit these datasets for within-object classification. For e...
Jania Aghajanian, Jonathan Warrell, Simon J.D. Pri...
ICCV
2005
IEEE
16 years 1 months ago
Local Features for Object Class Recognition
In this paper we compare the performance of local detectors and descriptors in the context of object class recognition. Recently, many detectors / descriptors have been evaluated ...
Krystian Mikolajczyk, Bastian Leibe, Bernt Schiele
ECCV
2008
Springer
16 years 1 months ago
Scene Segmentation for Behaviour Correlation
Abstract. This paper presents a novel framework for detecting abnormal pedestrian and vehicle behaviour by modelling cross-correlation among different co-occurring objects both loc...
Jian Li, Shaogang Gong, Tao Xiang
ICPR
2008
IEEE
16 years 1 months ago
Scale-invariant medial features based on gradient vector flow fields
We propose a novel set of medial feature interest points based on gradient vector flow (GVF) fields [18]. We exploit the long ranging GVF fields for symmetry estimation by calcula...
Cristóbal Curio, David Engel