TY  - JOUR
PY  - 2017//
TI  - Pedestrian count estimation using texture feature with spatial distribution
JO  - Advances in mechanical engineering
A1  - Hu, Hongyu
A1  - Gao, Zhenhai
A1  - Sun, Yiteng
SP  - e1687814016683599
EP  - e1687814016683599
VL  - 9
IS  - 1
N2  - We present a novel pedestrian count estimation approach based on global image descriptors formed from multi-scale texture features that considers spatial distribution. For regions of interest, local texture features are represented based on histograms of multi-scale block local binary pattern, which jointly constitute the feature vector of the whole image. Therefore, to achieve an effective estimation of pedestrian count, principal component analysis is used to reduce the dimension of the global representation features, and a fitting model between image global features and pedestrian count is constructed via support vector regression. The experimental result shows that the proposed method exhibits high accuracy on pedestrian count estimation and can be applied well in the real world.<p />  <p>Language: en</p>
LA  - en
SN  - 1687-8132
UR  - http://dx.doi.org/10.1177/1687814016683599
ID  - ref1
ER  -