eprintid: 17374
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/73/74
datestamp: 2023-12-19 03:23:46
lastmod: 2023-12-19 03:23:46
status_changed: 2023-12-19 03:07:57
type: conference_item
metadata_visibility: show
creators_name: Nguyen, N.-D.
creators_name: Bui, D.-H.
creators_name: Hussin, F.A.
creators_name: Tran, X.-T.
title: An Adaptive Hardware Architecture using Quantized HOG Features for Object Detection
ispublished: pub
keywords: Feature extraction; Graphic methods; Memory architecture; Object detection; Object recognition; Pipeline processing systems; Static random access storage, Hardware architecture; Histogram of oriented gradient features; Histogram of oriented gradients; Memory footprint; Objects detection; Performance; Quantized histograms; Support vectors machine; Supported vector machines, Support vector machines
note: cited By 2; Conference of 2022 IEEE International Conference on IC Design and Technology, ICICDT 2022 ; Conference Date: 21 September 2022 Through 23 September 2022; Conference Code:184070
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. © 2022 IEEE.
date: 2022
publisher: Institute of Electrical and Electronics Engineers Inc.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85142756779&doi=10.1109%2fICICDT56182.2022.9933068&partnerID=40&md5=8dbc6c28f9905b2df68cc139546542d7
id_number: 10.1109/ICICDT56182.2022.9933068
full_text_status: none
publication: Proceedings of 2022 IEEE International Conference on IC Design and Technology, ICICDT 2022
pagerange: 113-116
refereed: TRUE
isbn: 9781665459013
citation:   Nguyen, N.-D. and Bui, D.-H. and Hussin, F.A. and Tran, X.-T.  (2022) An Adaptive Hardware Architecture using Quantized HOG Features for Object Detection.  In: UNSPECIFIED.