A review on pedestrian detection techniques based on Histogram of Oriented gradient feature

Author

Chi Qin Lai ; Soo Siang Teoh

Author_Institution

Sch. of Electr. & Electron. Eng., Univ. Sains Malaysia, Nibong Tebal, Malaysia

fYear

2014

Firstpage

1

Lastpage

6

Abstract

Locally normalized Histogram of Oriented Gradient (HOG) algorithm originally proposed by Dalal & Triggs presents excellent results for pedestrian detection. However, as the demand of accuracy and speed in real-time application increase, the detection speed and robustness of this method is becoming insufficient. Over the years, improvements have been proposed by different researchers in order to meet the requirement of the robustness and processing speed. This includes the improvement in the ways HOG feature is extracted, combination of HOG feature with other image features and using part based detection method. This paper reviews the current advancement in HOG features for human detection.

Keywords

feature extraction; gradient methods; object detection; pedestrians; traffic engineering computing; HOG algorithm; HOG feature extraction; histogram of oriented gradient feature; human detection; image features; locally normalized histogram of oriented gradient algorithm; part based detection method; pedestrian detection techniques; real-time application; Accuracy; Feature extraction; Graphics processing units; Histograms; Robustness; Support vector machine classification; Advanced Driver Assistance System; HOG Feature; Human Detection; Object Classification; Pedestrian Detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Research and Development (SCOReD), 2014 IEEE Student Conference on

Print_ISBN

978-1-4799-6427-7

Type

conf

DOI

10.1109/SCORED.2014.7072948

Filename

7072948