DocumentCode :
624654
Title :
An enhanced Histogram of Oriented Gradient for pedestrian detection
Author :
Daimeng Wei ; Yong Zhao ; Ruzhong Cheng ; Guoliang Li
Author_Institution :
Shenzhen Grad. Sch., Sch. of Comput. & Inf. Eng., Peking Univ., Shenzhen, China
fYear :
2013
fDate :
9-11 June 2013
Firstpage :
459
Lastpage :
463
Abstract :
Significant researches have been carried out for pedestrian detection in images. The outstanding Histogram-of-Oriented-Gradients (HOG) feature proposed by Dalal and Triggs is the state-of-art for this task, and it is applied with a linear support vector machine (SVM) in a sliding-window framework. The novel method we proposed in this paper is based on this approach in which we add an enhanced feature to contain more feature information. Besides the same gradient information extraction process as HOG´s, the enhanced feature extraction contains two steps: firstly, a new way is found to downscale the gradient image to its quarter size without losing much gradient information; secondly, `Circle HOG´ features are extracted from those downscaled images. Then we combine the new enhanced features and the original HOG features together as an Enhanced HOG (EHOG) features. Our method is evaluated with a Histogram Intersection Kernel SVM (HIKSVM) on the public “INRIA” pedestrian detection benchmark dataset. The results show that proposed method consistently improves the detection rate by 4.5% in detection accuracy, compared with the original HOG.
Keywords :
feature extraction; gradient methods; image enhancement; object detection; pedestrians; support vector machines; EHOG; HIKSVM; circle HOG feature extraction; detection accuracy; detection rate; enhanced HOG; enhanced feature extraction; enhanced histogram of oriented gradient; feature information; gradient image downscale; gradient information extraction process; histogram intersection kernel SVM; linear support vector machine; public INRIA pedestrian detection benchmark dataset; sliding-window framework; Computers; Educational institutions; Feature extraction; Histograms; Interpolation; Kernel; Support vector machines;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Control and Information Processing (ICICIP), 2013 Fourth International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4673-6248-1
Type :
conf
DOI :
10.1109/ICICIP.2013.6568118
Filename :
6568118
Link To Document :
بازگشت