Sciweavers

Share
ICCV
2007
IEEE

Real-time Accurate Object Detection using Multiple Resolutions

9 years 7 months ago
Real-time Accurate Object Detection using Multiple Resolutions
We propose a multi-resolution framework inspired by human visual search for general object detection. Different resolutions are represented using a coarse-to-fine feature hierarchy. During detection, the lower resolution features are initially used to reject the majority of negative windows at relatively low cost, leaving a relatively small number of windows to be processed in higher resolutions. This enables the use of computationally more expensive higher resolution features to achieve high detection accuracy. We applied this framework on Histograms of Oriented Gradient (HOG) features for object detection. Our multi-resolution detector produced better performance for pedestrian detection than state-of-the-art methods [7], and was faster during both training and testing. Testing our method on motorbikes and cars from the VOC database revealed similar improvements in both speed and accuracy, suggesting that our approach is suitable for realtime general object detection applications.
Wei Zhang 0002, Gregory J. Zelinsky, Dimitris Sama
Added 14 Oct 2009
Updated 14 Oct 2009
Type Conference
Year 2007
Where ICCV
Authors Wei Zhang 0002, Gregory J. Zelinsky, Dimitris Samaras
Comments (0)
books