کنفرانس مهندسی برق ایران

صفحه اصلی / سی و یکمین کنفرانس بین المللی مهندسی برق

Transformer-Based Unsupervised Image Registration using SSIM and Homography Loss for Steady Camera and Aerial Videos

نویسندگان :

Golnoosh Abdollahinejad¹ Matin Hashemi²

1- دانشگاه صنعتی شریف 2- دانشگاه صنعتی شریف

کلمات کلیدی :

Computer Vision،Image Registration،Transformer Network،Deep Learning

چکیده :

Image registration is an essential and initial block in the pipeline of computer vision tasks and systems. It is defined as the process of transforming a moving image into a target image with minimum difference when get aligned. Unlike previous work for general-purpose datasets, aerial images suffer from mechanical shakes which leads to deformed distortion that is similar to medical volumetric image registration task. Inspired by medical approaches, we use a Transformer-based network to have a semi-unlimited receptive field Swin block, to produce a general output for each pixel named flow matrix. Flow matrix is utilized instead of regressing parameters of transformation matrix with a fixed degree of freedom that can't handle the structural difference between images. This leads to introducing of a new loss function based on the Structural Similarity Index Measure (SSIM) and embedding Homography transformation as a regularization term. The combination of a generalized-designed network and loss function based on problem definition significantly enhanced results.

لیست مقالات

لیست مقالات بایگانی شده

ZYNQ Based Real-Time Data Logger with 256 kSPS Sampling using Ethernet Interface

Alireza Eteghad - Ataollah Panahgholi - Esmaeil Najafiaghdam

Design and Determing Two Separate Rotor Axial Flux Permanent Magnet Motor Load and Efficinecy

Siamak Omrani - Ahmad Darabi

Semi-supervised Deep Reinforcement Learning in Decentralized Multi-Agent Collision Avoidance and Path Planning in a Complex Environment

Marzie Parooei - Mehdi Tale Masouleh - Ahmad Kalhor

Fault tolerant control design for linear systems based on cubic observers

Mahsa Hasanshahi - Malihe Maghfoori Farsangi - Elham Amini Boroujeni

Synergy of Deep Learning and Artificial Potential Field Methods for Robot Path Planning in the Presence of Static and Dynamic Obstacles

Mohammad Amin Basiri - Shirin Chehelgami - Erfan Ashtari - Mehdi Tale Masouleh - Ahmad Kalhor

Microgrid Damping Improvement Using High-Pass Filter-Based Virtual Synchronous Generator

Shayan Zaimi - Ashkan Moradi Naserkhani - Sharara Rehimi - Amin Karimi - Rahmatollah Mirzaei - Hassan Bevrani

Stability Improvement in Weak Grid-Tied DFIG-based WECS Employing Adaptive Virtual Impedance Strategy Based on Machine Learning Considering the LVRT Constraint

Mohammad Hossein Shaabani - Behrooz Vahidi - Navid Dehghan

Stability Analysis for the Non-linear Model Predictive Control of a Flexible Joint Manipulator with Dynamics Uncertainties

Mohamadreza Satvati - Hossein Karimpour - Keivan Torabi - Mohammad Motaharifar

Message Overhead Control Using P-Epidemic Routing Method in Resource-Constrained Heterogeneous DTN

Mohammad Yousef Darmani - Shiva Karimi

بررسی اثر پیرشدگی بر میدان الکتریکی و جریان نشتی در مقره‌های پلیمری آلوده با شبیه‌سازی به روش اجزای محدود

محمد گودرزی - سید محمد شهرتاش - احمد غلامی

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