Pedestrian detection by PCA-based mixed HOG-LBP features

Authors:
Ren-wu Sun;Ting Rui;Jin-lin Zhang;You Zhou
Affiliations:
PLA University of Science and Technology Nan Jing, China;PLA University of Science and Technology Nan Jing, China;PLA University of Science and Technology Nan Jing, China;Jiangsu Institute of Economic and Trade Technology Nan Jing, China
Venue:
Proceedings of the 4th International Conference on Internet Multimedia Computing and Service
Year:
2012

Citing 5
Cited 0

A Simple Decomposition Method for Support Vector Machines

Machine Learning
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Learning discriminative multi-scale and multi-position LBP features for face detection based on Ada-LDA

ROBIO'09 Proceedings of the 2009 international conference on Robotics and biomimetics
Robust Head-Shoulder Detection by PCA-Based Multilevel HOG-LBP Detector for People Counting

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Speeding up HOG and LBP features for pedestrian detection by multiresolution techniques

ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

As the basic method of feature extraction, HOG and LBP are paid much attention in the field of pedestrian detection. But the HOG features are too narrow and complex, so we simplify the HOG from the two perspectives. After that, PCA is used to reduce the dimensions of simplified HOG features and LBP features and then combine the two features after the dimensionality reduction to extract the mixed HOG-LBP features, and then used for pedestrian detection. Compared with conventional HOG, The experimental results show that PCA-HOG-LBP features reduce the dimensions and complexity of operator; improve the speed and accuracy detection of algorithm.