Abstract Details


Name: Aishmeen Kaur
Affiliation: Department of Physical Sciences, Indian Institute of Science Education and Research Mohali
Conference ID: TVS202510169
Title: Tracking Solar transients using Optical flow method
Authors and Co-Authors: Pritam Das, Pallavi Rajeev , Aishmeen Kaur, Dr. Dipankar Banerjee
Abstract Type: Contributory Presentation
Abstract: This project explores the use of optical flow techniques to detect and track solar transients, especially Coronal Mass Ejections (CMEs). Optical flow is a popular computer vision method that estimates how objects move across successive frames. Here, it is applied to time-series images of the solar corona to show dynamic features that develop over time. The motivation for this work comes from the growing need for automated and accurate detection of solar eruptive events. CMEs are significant drivers of space weather disturbances. They need to be identified quickly for reliable forecasting. Manual detection methods are often time-consuming and prone to human bias. This has led to a demand for algorithmic solutions that can process large amounts of solar data efficiently. In this project, solar images from instruments like LASCO (onboard SOHO) and STEREO were preprocessed to improve the visibility of important coronal features. After that, Farneback’s optical flow algorithms were used to calculate velocity fields. These fields show the apparent motion of plasma structures in the corona and indicate transient phenomena. The final stage of the project involved visualizing the flow maps and assessing their effectiveness in identifying CMEs. We will then compare the results to traditional threshold-based detection methods to evaluate their strengths and weaknesses in various situations. We are also working on training the algorithm to make real-time CME detections.