کنفرانس مهندسی برق ایران

صفحه اصلی / بیست و نهمین کنفرانس مهندسی برق ایران

Transfer Learning Based Method for Human Activity Recognition

نویسندگان :

Saeedeh Zebhi¹ Smt Almodarresi² Vahid Abootalebi³

1- Yazd university 2- Yazd university 3- Yazd university

کلمات کلیدی :

gait history image, gradient, human activity recognition, transfer learning

چکیده :

A gait history image (GHI) is a spatial template that accumulates regions of motion into a single image in which moving pixels are brighter than others. A new descriptor named Time-sliced averaged gradient boundary magnitude (TAGBM) is also designed to show the time variations of motion. In the proposed method, each video is split into N and M groups of consecutive frames, and the GHI and TAGBM are computed for each group, resulting spatial and temporal templates. Transfer learning with the fine-tuning technique has been used for classifying these templates. This proposed method achieves the recognition accuracies of 96.5% and 92.7% for KTH and UCF Sport action datasets, respectively. Also it is compared with state-of-the-art approaches and the results demonstrate that the proposed method has the best efficiency.

لیست مقالات

لیست مقالات بایگانی شده

IRS-aided NOMA in a Cell Free Massive MIMO System

Anahid Rafieifar - Hosein Ahmadinejad - Abolfazl Falahati

تشخیص و تفکیک برخط خطای مدار باز کلید در اینورترهای تک فاز PWM

مهدی اره پناهی - علی اکبر سلیمی

حل مسئله مجموعه مستقل d-فاصله با رویکرد CombOpt Zero

فاطمه نیکبخت نصرآبادی - حسین فلسفین - مهران صفایانی

A boosting based approach to handle imbalanced data

Sahar Hassanzadeh Mostafaei - Jafar Tanha - Negin Samadi - Soodabeh Imanzadeh - Nazila Razzaghi-Asl

کنترل حرارت مبتنی بر روش LQG در پیل سوختی غشاء پلیمری

احمدرضا ولی - محمدعلی علیرضاپوری - محمدمهدی برزگری

طراحی و شبیه سازی مبدل کاهنده دو مرحله ای با کنترل کننده زمان روشن-خاموش تطبیقی

نوید گودرزی - حسین پاک نیت - نوید یثربی

Primary Frequency Support in Clustered Unit Commitment with Battery Energy Storage and High Renewable Penetration

Abbas Abdollahi-Veshvaee - Turaj Amraee

The Comparison of MXene and Graphene-Based Antennas for 5G/6G Communications

Javad Shokri Seyyedi - Gholamreza Moradi - Reza Sarraf Shirazi - Sepehr Sahab - Abolfazl Ebrahimpour

A New Coupled Inductor based Non-Isolated Dual Input Soft-Switching High Step-up DC-DC Converter

Amirreza Razavi Majarshin - Ebrahim Babaei - Mehran Sabahi

Conserving Power Consumption in Elastic Optical Networks using Deep Learning

Fatemeh Dehrouyeh - Sina Tavakolian - Lotfollah Beygi

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2