0% Complete
صفحه اصلی
/
سی و یکمین کنفرانس بین المللی مهندسی برق
On spatiotemporal-aware deep neural networks for real-time video fire detection: empowering image-based models with temporal and spatial features of video
نویسندگان :
Mahdi Shamisavi
1
Sahar Eslami
2
Amir Jahanshahi
3
Morteza Rajabzadeh
4
1- دانشگاه صنعتی امیرکبیر
2- دانشگاه صنعتی امیرکبیر
3- دانشگاه صنعتی امیرکبیر
4- دانشگاه صنعتی قوچان
کلمات کلیدی :
Fire،Deep Neural Networks،Motion،Color،Resnet50
چکیده :
Fire is one of the natural events that has various risks for humans and the environment. Therefore, reliable and early detection of fire could greatly help save lives and prevent disasters. Image-based fire detection methods can be very quick and reliable, unlike, conventional chemical-based fire detectors. Convolutional Neural networks (CNN) have shown relatively impressive accuracy in the field of fire detection in recent years. However, extracting temporal features from images by CNN Networks proves to be the main challenge. In order to introduce temporal features inside CNN, we used motion and color features to improve the accuracy of the CNN . We propose a modified Resnet50 architecture by adding temporal features with the help of a classical image processing algorithm. Our implementation and results show that our improved Resnet50 architecture outperforms original Resnet50 on test images. Our results demonstrate that the performance of Deep Neural Networks (DNNs) can be improved by employing additional temporal features. We use motion and color features to improve the DNNs model (spatiotemporal-aware) to classify fire images more accurately than basic original DNNs without additional temporal features (spatiotemporal-unaware).
لیست مقالات
لیست مقالات بایگانی شده
طراحی کنترلکننده استروباسکوپ زمان واقعی مبتنی بر هوش مصنوعی برای سیستم های دورانی
مهدی مظفری - سعید جعفری نسب - حامد پورکاوه - سعید شمقدری
Autoencoders for Input Reduction in Interval Type-2 Hyperbolic Fuzzy System Identification and Control: Experimental Results
Behnaz Mohammadi - Nazanin Ildarabadi - Mohammad-R Akbarzadeh-T
Floquet model of spatiotemporally modulated graphene-based structures
Mahsa Valizadeh - Leila Yousefi - MirFaez Miri
ZnO-based Acoustofluidics: Droplet-based Particle Manipulation
Sara Abbasi - Behdad Barahimi - Sara Darbari - Mohammad Kazem Moravvej-Farshi - Mohammad Zabetian
تحلیل ارتباطات موثر و عملکردی سیگنالهای فیزیولوژیکی راننده جهت بهبود تشخیص حواس پرتی
نیلوفر وثوق - زهرا بهمنی دهکردی - امین محمدیان
Entanglement Witness Derived By Using Kolmogorov-Arnold Networks
Fatemeh Lajevardi - Azam Mani - Ali Fahim
Optimal Path Planning and Control of a Hexarotor with Mass Uncertainty in the Presence of Dynamic Obstacles and Wind Using Sliding Mode and Adaptive PSO Algorithm
Nima Sina - Peyman Amiri - Mohammad Danesh
بررسی روابط توان دوم برای اعداد باینری با تمرکز بر طراحی و پیاده سازی مدار برای ورودی 4 بیت مثبت و منفی در پروسه استاندارد 0.18 µm CMOS
احمد احمدزاده - امیر فتحی - بهبود مشعوفی
Entanglement-Assisted Classical-Quantum Multiple Access Wiretap Channel: One-shot Achievable Rate Region
Hadi Aghaee - Bahareh Akhbari
Second-Order Mode Analysis of Spoof Surface Plasmon Waveguide
Mohammad Ali Khosrovani_Moghaddam - Amir Ahmad Shishegar
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.8.0