FPGA-GPU architecture for kernel SVM pedestrian detection

  title={FPGA-GPU architecture for kernel SVM pedestrian detection},
  author={Sebastian Bauer and Sebastian K{\"o}hler and Konrad Doll and Ulrich Brunsmann},
  journal={2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops},
We present a real-time multi-sensor architecture for video-based pedestrian detection used within a road side unit for intersection assistance. The entire system is implemented on available PC hardware, combining a frame grabber board with embedded FPGA and a graphics card into a powerful processing network. Giving classification performance top priority, we use HOG descriptors with a Gaussian kernel support vector machine. In order to achieve real-time performance, we propose a hardware… CONTINUE READING
Highly Cited
This paper has 81 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 50 extracted citations

Fast FPGA-based architecture for pedestrian detection based on covariance matrices

2011 18th IEEE International Conference on Image Processing • 2011
View 5 Excerpts
Highly Influenced

Rejecting Motion Outliers for Efficient Crowd Anomaly Detection

IEEE Transactions on Information Forensics and Security • 2019
View 1 Excerpt

82 Citations

Citations per Year
Semantic Scholar estimates that this publication has 82 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 27 references

Challenges of Embedded Computer Vision in Automotive Safety Systems, pages 257–279

Y. Zhang, A. S. Dhua, S. J. Kiselewich, W. A. Bauson
Advances in Pattern Recognition. Springer, • 2009

FPGA implementation of a HOG - based pedestrian recognition sys

S. Schlotterbeck-Macht
MPC Workshop • 2009

Hardware architecture for high-accuracy real-time pedestrian detection with CoHOG features

2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops • 2009

Hardware implementation of HOG feature extraction for real-time pedestrian recognition

R.M.R. Kadota, Y. Nakamura
Technical report. In IEICE Smart Info-Media System, • 2009

Monocular Pedestrian Detection: Survey and Experiments

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2009

Multiple kernels for object detection

2009 IEEE 12th International Conference on Computer Vision • 2009

Parallel implementation of pedestrian tracking using multiple cues on GPGPU

2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops • 2009

Similar Papers

Loading similar papers…