Indranil Misra
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Indranil Misra has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Debajyoti Dhar
11 shared publications- Manthira Moorthi Subbiah
India Space Research Organization
6 shared publications Mukesh Kumar Rohil
Department of Computer Science and Information Systems, Birla Institute of Technology and Science, Pilani, India
6 shared publications- Mukesh Kumar Rohil
Department of Computer Science and Information Systems, Birla Institute of Technology and Science Pilani, Pilani Campus, Pilani, India
5 shared publications - Debajyoti Dhar
India Space Research Organization
3 shared publications S Manthira Moorthi
3 shared publications
Latest Publications
- 12 November 2026
- Published by Elsevier in Remote Sensing Applications: Society and Environment
- Vol. 44
Hybrid quantum-classical optimization framework for satellite image registration
- 12 November 2026
- Published by Elsevier in Remote Sensing Applications: Society and Environment
- Vol. 44
Hybrid quantum-classical optimization framework for satellite image registration
- Open Access
- 18 September 2026
- Published by Elsevier in SSRN Electronic Journal
Geospatial Foundation Models for Remote Sensing Image Processing: Architectures, Pre-training Strategies, and Modality Adaptation
The growth of Earth observation data has revealed a major limitation of task-specific Remote Sensing (RS) models: their limited ability to generalize across different sensors, geographic regions, and application domains. Geospatial Foundation Models (GFMs) address this limitation by using large-scale self-supervised pretraining to learn transferable feature representations from heterogeneous Earth observation data. In this paper, we provide a structured critical review of benchmarked model architectures and associated training strategies. Additionally, we characterize the evolution from Convolutional Neural Networks to Vision Transformer architectures, with particular emphasis on the advantages that attention-based architectures provide for modeling global context and scalable learning. The primary self-supervised paradigms of masked image modeling, contrastive learning, and distillation are presented with respect to their inductive biases and suitability for spatial, spectral, and temporal tasks. In addition, we compile recent developments in vision, vision-language, and generative foundation models and characterize their roles in multimodal fusion, open-vocabulary reasoning, and geospatial data generation. We synthesize reported evidence on model generalization, transferability, and efficiency across representative downstream remote sensing tasks. Furthermore, we discuss key challenges in data curation, cross-sensor alignment, interpretability, and scalable deployment to guide the future development of unified and physically grounded geospatial foundation models. This review provides a synthesis of the emerging foundation-model-driven paradigm in Earth observation.
- 18 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessGeospatial Foundation Models for Remote Sensing Image Processing: Architectures, Pre-training Strategies, and Modality Adaptation
The growth of Earth observation data has revealed a major limitation of task-specific Remote Sensing (RS) models: their limited ability to generalize across different sensors, geographic regions, and application domains. Geospatial Foundation Models (GFMs) address this limitation by using large-scale self-supervised pretraining to learn transferable feature representations from heterogeneous Earth observation data. In this paper, we provide a structured critical review of benchmarked model architectures and associated training strategies. Additionally, we characterize the evolution from Convolutional Neural Networks to Vision Transformer architectures, with particular emphasis on the advantages that attention-based architectures provide for modeling global context and scalable learning. The primary self-supervised paradigms of masked image modeling, contrastive learning, and distillation are presented with respect to their inductive biases and suitability for spatial, spectral, and temporal tasks. In addition, we compile recent developments in vision, vision-language, and generative foundation models and characterize their roles in multimodal fusion, open-vocabulary reasoning, and geospatial data generation. We synthesize reported evidence on model generalization, transferability, and efficiency across representative downstream remote sensing tasks. Furthermore, we discuss key challenges in data curation, cross-sensor alignment, interpretability, and scalable deployment to guide the future development of unified and physically grounded geospatial foundation models. This review provides a synthesis of the emerging foundation-model-driven paradigm in Earth observation.
- 3 March 2026
- Published by Elsevier in Advances In Space Research
- Vol. 77 (9) , 8884-8911
Feature-based image processing in remote sensing: future prospects and research directions
- 3 March 2026
- Published by Elsevier in Advances In Space Research
- Vol. 77 (9) , 8884-8911
Feature-based image processing in remote sensing: future prospects and research directions
- 23 February 2026
- Published by Elsevier in Remote Sensing Applications: Society and Environment
- Vol. 41
Quantum annealing for remote sensing data processing: A review of optimization based applications
- 23 February 2026
- Published by Elsevier in Remote Sensing Applications: Society and Environment
- Vol. 41
Quantum annealing for remote sensing data processing: A review of optimization based applications
- 13 March 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 276
Demystifying SAR with attention
- 13 March 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 276
Demystifying SAR with attention
- 14 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 6521-6534
Enhanced Multispectral Band-to-Band Registration Using Co-Occurrence Scale Space and Spatial Confined RANSAC Guided Segmented Affine Transformation
Band-to-Band Registration (BBR) is a pre-requisite image processing operation essential for specific remote sensing multispectral sensors. BBR aims to align spectral wavelength channels at sub-pixel level accuracy over each other. The paper presents a novel BBR technique utilizing Co-occurrence Scale Space (CSS) for feature point detection and Spatial Confined RANSAC (SC-RANSAC) for removing outlier matched control points. Additionally, the Segmented Affine Transformation (SAT) model reduces distortion and ensures consistent BBR. The methodology developed is evaluated with Nano-MX multispectral images onboard the Indian Nano Satellite (INS-2B) covering diverse landscapes. BBR performance using the proposed method is also verified visually at a 4X zoom level on satellite scenes dominated by cloud pixels. The band misregistration effect on the Normalized Difference Vegetation Index (NDVI) from INS-2B is analyzed and cross-validated with the closest acquisition Landsat-9 OLI NDVI map before and after BBR correction. The experimental evaluation shows that the proposed BBR approach outperforms the state-of-the-art image registration techniques.
- 14 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 6521-6534
Enhanced Multispectral Band-to-Band Registration Using Co-Occurrence Scale Space and Spatial Confined RANSAC Guided Segmented Affine Transformation
Band-to-Band Registration (BBR) is a pre-requisite image processing operation essential for specific remote sensing multispectral sensors. BBR aims to align spectral wavelength channels at sub-pixel level accuracy over each other. The paper presents a novel BBR technique utilizing Co-occurrence Scale Space (CSS) for feature point detection and Spatial Confined RANSAC (SC-RANSAC) for removing outlier matched control points. Additionally, the Segmented Affine Transformation (SAT) model reduces distortion and ensures consistent BBR. The methodology developed is evaluated with Nano-MX multispectral images onboard the Indian Nano Satellite (INS-2B) covering diverse landscapes. BBR performance using the proposed method is also verified visually at a 4X zoom level on satellite scenes dominated by cloud pixels. The band misregistration effect on the Normalized Difference Vegetation Index (NDVI) from INS-2B is analyzed and cross-validated with the closest acquisition Landsat-9 OLI NDVI map before and after BBR correction. The experimental evaluation shows that the proposed BBR approach outperforms the state-of-the-art image registration techniques.
- 12 March 2024
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 27 (2) , 1-15
A novel Venus’ visible image processing neoteric workflow for improved planetary surface feature analysis
- 12 March 2024
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 27 (2) , 1-15
A novel Venus’ visible image processing neoteric workflow for improved planetary surface feature analysis
- 25 October 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 238
Direct feature extraction and image co-registration of morphological structure from Bayer pattern raw planetary images
- 25 October 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 238
Direct feature extraction and image co-registration of morphological structure from Bayer pattern raw planetary images
- 14 October 2023
- Published by Elsevier in Infrared Physics & Technology
- Vol. 135
CLIM: Co-occurrence with Laplacian Intensity Modulation and Enhanced Color Space Transform for Infrared-Visible Image Fusion
- 14 October 2023
- Published by Elsevier in Infrared Physics & Technology
- Vol. 135
CLIM: Co-occurrence with Laplacian Intensity Modulation and Enhanced Color Space Transform for Infrared-Visible Image Fusion