Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
4 results
Search Results
Item YOLOv5 Model-based Ship Detection in High Resolution SAR Images(Institute of Electrical and Electronics Engineers Inc., 2023) Sapna, S.; Sandhya, S.; Shetty, R.D.; Pais, S.M.; Bhattacharjee, S.Detection of ships in Synthetic Aperture Radar (SAR) images play a crucial role in maritime surveillance, most importantly under complex sea conditions. SAR permits observation in any weather conditions, at all hours of the day and night. At present, the ship detection from SAR images is a notable area of research since it is very difficult to detect the ships in the SAR images using traditional object or target detection algorithms. In this work, a You Only Look Once version 5 (YOLOv5) based ship detection model from SAR images with faster training speed and higher accuracy is implemented and tested. This model achieved a mean average precision (mAP) of 96.2% with a training time of 8.63 hours. This work also provides a comparative analysis with the existing methods for detection of ships in SAR images. The comparison shows that the YOLOv5 based model performs better in terms of both mean average precision and training time when compared to the existing models. © 2023 IEEE.Item Prediction of High-Resolution Atmospheric CO2 Concentration from OCO-2 using Machine Learning(Association for Computing Machinery, 2023) Pais, S.M.; Bhattacharjee, S.; Anand Kumar, A.K.Carbon Dioxide (CO2) is a greenhouse gas (GHG) emitted by human anthropogenic activities. The satellite measurement of atmospheric column-averaged CO2 concentration (XCO2) provides an excellent opportunity to understand the global carbon cycle for a large comprehensive temporal range. Orbiting Carbon Observatory-2 (OCO-2) satellite provides highly accurate data with a spatial resolution of approximately 3 km2. However, OCO-2 measures one location on the Earth's surface almost fortnightly. Also, the clouds and aerosols cause missing data. In this work, the OCO-2 measurements, along with Open-Source Data Inventory for Anthropogenic CO2 (ODIAC) emission estimate, are considered. A spatial upscaling, followed by different machine learning methods are used to predict high-resolution, continuous mapping of XCO2. The prediction models are evaluated using the Mean Absolute Error (MAE) and the Root Mean Square Error (RMSE) for Germany, considering a temporal range of November 2018 to December 2019. The least error is attained by monthly model, achieving a MAE and RMSE of 0.707 ppm and 1.187 ppm, respectively, using the extremely randomized trees (ERT) method. The predictions are externally validated using Total Carbon Column Observing Network (TCCON) ground-based measurements as well. © 2023 ACM.Item Disaster Classification Using Multimodality Techniques by Integrating Images and Text(Springer Science and Business Media Deutschland GmbH, 2025) Medapati, B.M.R.; Pais, S.M.; Bhattacharjee, S.In today’s digital era, the abundance of information shared through social media platforms in times of disaster has emerged as a crucial asset for enhancing disaster response operations. This research initiative was specifically dedicated to enhance disaster categorization by integrating image and tweet text data. The devised model comprises two distinct modules aimed at optimizing the classification process. The primary module focuses on extracting insights from text and images independently using VGG-16 for images, and Bidirectional Long Short-Term Memory and Convolutional Neural Network for texts, subsequently executing the classification task. Conversely, the secondary module is designed to learn the interconnectedness between textual content and images using Contrastive Learning Image Pretraining (CLIP). After this late fusion is used to combine the outcomes of these modules and later softmax classification is used for the classification of the incident into one of seven humanitarian categories thereby enhancing the precision and efficacy of disaster classification. The developed model gives an accuracy of 75% with no data and image augmentations and the result was improved to 93% with different combinations of augmentations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.Item Predicting High-Resolution Soil Moisture Using MODIS Bands: A Fusion-Regression Approach(Institute of Electrical and Electronics Engineers Inc., 2025) Sudhakara, B.; Pais, S.M.; Bhattacharjee, S.Soil moisture (SM) is a crucial biophysical parameter that plays a significant role in predicting food security. Monitoring SM is essential as it provides valuable insights into agricultural productivity and the impacts of climate change. Remote sensing platforms retrieve SM data from various satellites, enabling global monitoring. However, the coarse resolution of these datasets limits their ability to capture fine-scale variations in SM. To address this challenge, this study aims to generate a high-resolution SM product using data from the Soil Moisture Active Passive (SMAP) mission. The SMAP data is fused with MODIS spectral bands to create a multi-source dataset, which is then used as input for different regression models to achieve downscaling of SM. Experimental results demonstrate that the Extremely Randomized Trees (ERT) model achieves the minimum error, with RMSE 0.0113 m3/m3, MAE 0.0172 m3/m3, and R2 0.9725. The study focuses on Karnataka, covering the temporal window from 2015 to 2022. © 2025 IEEE.