eprintid: 4779
rev_number: 7
eprint_status: archive
userid: 4
dir: disk0/00/00/47/79
datestamp: 2022-09-04 15:07:14
lastmod: 2022-09-04 15:07:14
status_changed: 2022-09-04 15:07:14
type: conference_item
metadata_visibility: show
creators_name: Nguyen, Ngo Doanh
creators_name: Bui, Duy Hieu
creators_name: Hussin, Fawnizu Azmadi
creators_name: Tran, Xuan Tu
creators_id: doanh.nn.97@gmail.com
creators_id: hieubd@vnu.edu.vn
creators_id: fawnizu@utp.edu.my
creators_id: tutx@vnu.edu.vn
corp_creators: Vietnam National University, Hanoi
title: An Adaptive Hardware Architecture using Quantized HOG Features for Object Detection
ispublished: inpress
subjects: isi_scopus_conf
abstract: This article presents an adaptive hardware architecture for high-performance object detection using Histogram of Oriented Gradient (HOG) features in combination with Supported Vector Machines (SVM). This architecture can adapt
to various bit-width representations of HOG features by using the quantization technique. The HOG features can be represented from 8 bits to 4 bits to remove the bubble in the processing pipeline and reduce the memory footprint. As a result, the overall throughput is robustly increased as the number of bits decreases. Moreover, we propose a new cell-reused strategy to speed up the system throughput and reduce memory footprint. The proposed architecture has been implemented in TSMC 65nm technology with a maximum operating frequency of 500MHz and throughput of 3.98Gbps. The total hardware area cost is about 167KGEs and 212kb SRAMs.
date: 2022-09-21
date_type: published
full_text_status: public
pres_type: paper
event_title: 2022 International Conference on IC Design and Technology (ICICDT 2022)
event_location: Hanoi, Vietnam
event_dates: 21-23 September 2022
event_type: conference
refereed: TRUE
citation:   Nguyen, Ngo Doanh and Bui, Duy Hieu and Hussin, Fawnizu Azmadi and Tran, Xuan Tu  (2022) An Adaptive Hardware Architecture using Quantized HOG Features for Object Detection.  In: 2022 International Conference on IC Design and Technology (ICICDT 2022), 21-23 September 2022, Hanoi, Vietnam.    (In Press)  
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/4779/1/Final%20manuscript%20Doanh%201.pdf