Research and Performance Analysis on Pedestrian Detection Based on Optimized Hog and SVM

Yan Xi Zhang; Kai Ping Feng

doi:10.4028/www.scientific.net/AMM.511-512.247

Paper Titles

Study on the Multi-Optical Theodolites Positioning Method Based on Function Restriction
p.227

Suppressing of Nonlinear Phase Noise in Dispersion Managed Quasi-Linear Transmission Systems
p.234

Weight Size Determined Variable Step Size LMS Method for Identifying under Damped Systems
p.238

A Fuzzy Curve Detection Method Based on Lateral Acceleration
p.242

Research and Performance Analysis on Pedestrian Detection Based on Optimized Hog and SVM
p.247

A New Method for Calculating the Volume of Debris Flow Using GIS and RS Technology
p.253

Design of Thermocouple Verification Data Records Table Based on Labview
p.259

Development of a Transducer for Dental Implant Stability Measurement
p.265

Temperature Influence on Real-Time Ultrasonic Detection of Multi-Planetary Gear Transmission
p.270

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 511-512Research and Performance Analysis on Pedestrian...

Research and Performance Analysis on Pedestrian Detection Based on Optimized Hog and SVM

Abstract:

Pedestrian detection based on images is one key technology of intelligent vehicles, and it is also widely applied in intelligent robots, intelligent surveillance. This paper mainly focuses on implementing a pedestrian detection system, which is classified by linear SVM with optimized Hog (Histograms of Oriented Gradients) as the extracted features. Then some experiments were done to find out that how the changing resolution of training set, times of bootstrapping iterations and different size and steps of the sliding windows affect the overall performance of detecting systems.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 511-512)

Pages:

247-250

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.511-512.247

Citation:

Cite this paper

Online since:

February 2014

Authors:

Yan Xi Zhang*, Kai Ping Feng

Keywords:

HOG, Pedestrian Detection, Sliding Window, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] David Geronimo, Antonio M. Lopez, Angel D. Sappa and et al. Survey of Pedestrian Detection f or Advanced Driver Assistance Systems. IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 32, no. 7 (Jan. 2010), pp.1239-1258.

DOI: 10.1109/tpami.2009.122

Google Scholar

[2] Hui-Xing JIA, Yu-Jin ZHANG. A Survey of Computer Vision Based Pedestrian Detection for Driver Assistance Systems. ACTA AUTOMATICA SINICA. Vol. 33, no. 1 (2007), P84-90.

DOI: 10.1360/aas-007-0084

Google Scholar

[3] Jian-hong WANG, Pin-zheng ZHANG, Li-min LUO. Improved fast pedestrian detection method. Computer Engineering and Applications. Vol. 45, No. 28 (2009), P160-163.

Google Scholar

[4] N. Dalal and B. Triggs, Histograms of Oriented Gradients for Human Detection, Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp.886-893. (2005).

DOI: 10.1109/cvpr.2005.177

Google Scholar