A Novel Descriptor for Pedestrian Detection in Video Sequences
سال انتشار: 1389
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 176
فایل این مقاله در 8 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:
JR_ITRC-2-2_001
تاریخ نمایه سازی: 23 فروردین 1401
چکیده مقاله:
This paper presents a novel Texture-Edge Descriptor, TED, for background modeling and pedestrian detection in video sequences which models texture and edge information of each image block simultaneously. Each block is modeled as a group of adaptive TED histograms that are calculated for pixels of the block over a rectangular neighborhood. TED is an ۸-bit binary code which is independent of the neighborhood size. Experimental results over real-world sequences from PETS database clearly show that TED outperforms LBP.
کلیدواژه ها:
نویسندگان
Narges Armanfard
Dept. of Electrical and Computer Eng. Tarbiat Modarres University Tehran, Iran
Majid Komeili
Dept. of Electrical and Computer Eng. Tarbiat Modarres University Tehran, Iran
Ehsanollah Kabir
Dept. of Electrical and Computer Eng. Tarbiat Modarres University Tehran, Iran