Efficient Human Detection Based on Parallelimplementation of Gradient and Texture FeatureExtraction Methods
محل انتشار: هفتمین کنفرانس ماشین بینایی و پردازش تصویر ایران
سال انتشار: 1390
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 1,267
فایل این مقاله در 5 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICMVIP07_031
تاریخ نمایه سازی: 28 مرداد 1391
چکیده مقاله:
Pedestrian Detection is of interest in many computervision applications such as intelligent transportation systems andhuman-robot interaction; among the existing methods, thecombination of shape feature (i.e. Histogram of OrientedGradients (HOG)) and texture features (i.e. Local Binary Pattern(LBP)) has shown promising results in detection accuracy, but itis limited due to computation cost. In this paper, we introduce anew pedestrian detection algorithm with fast computation ofthese features on GPU. We propose a robust and rapidpedestrian detector by combining the HOG with LBP, as thefeature set and corresponding Support Vector Machine (SVM)classifiers. Also, we use the integral image method and anefficient parallel implementation to reduce detection time. Wecan achieve a more than 10x speed up, and 7% increase indetection rate.
کلیدواژه ها:
نویسندگان
Masoud Farhadi
Department of Electrical EngineeringAmirkabir University of Technology (Tehran polytechnic)Tehran, Iran
Seyed Ahmad Motamedi
Department of Electrical EngineeringAmirkabir University of Technology (Tehran polytechnic)Tehran, Iran
Saeed Sharifian
Department of Electrical EngineeringAmirkabir University of Technology (Tehran polytechnic)Tehran, Iran