Muhammad Kamran

Mohammad Moein Sheikholeslami, Muhammad Kamran, Andreas Wichmann et al.

The growing demand for high-resolution maps across various applications has underscored the necessity of accurately segmenting building vectors from overhead imagery. However, current deep neural networks often produce raster data outputs, leading to the need for extensive post-processing that compromises the fidelity, regularity, and simplicity of building representations. In response, this paper introduces a novel deep convolutional neural network named OriCornerNet, which directly extracts delineated building polygons from input images. Specifically, our approach involves a deep model that predicts building footprint masks, corners, and orientation vectors that indicate directions toward adjacent corners. These predictions are then used to reconstruct an initial polygon, followed by iterative refinement using a graph convolutional network that leverages semantic and geometric features. Our method inherently generates simplified polygons by initializing the refinement process with predicted corners. Also, including geometric information from oriented corners contributes to producing more regular and accurate results. Performance evaluations conducted on SpaceNet Vegas and CrowdAI-small datasets demonstrate the competitive efficacy of our approach compared to the state-of-the-art in building segmentation from overhead imagery.

Usman Nazir, Disha Gomathinayagam, Muhammad Kamran et al.

Pakistan experienced an unusually severe flood season between June and December 2025, with cascading impacts on population, infrastructure, and agriculture. Existing operational flood products (e.g., UNOSAT) provide valuable episode-level snapshots but rarely deliver spatially and temporally continuous inundation maps at near-real-time latency within the country. We present a multi-sensor, ensemble-based remote-sensing framework for continuous flood nowcasting in Pakistan that integrates Sentinel-1 SAR, Harmonized Landsat-Sentinel (HLS L30 and S30), MODIS, and VIIRS observations on a harmonized grid in Google Earth Engine. The framework employs a tiered nowcasting ensemble that prioritizes higher-resolution sensors (Sentinel-1 and HLS) and falls back to MODIS and VIIRS when necessary, preserving daily continuity of flood extent at each sensor's native resolution. Applied to the 2025 monsoon period, the system generates near-real-time, spatially consistent inundation maps across Pakistan. As a nowcasting case study, we track the super-flood of 26 August-7 September 2025 day by day, demonstrating the framework's ability to capture the evolving flood footprint in near real time and extend beyond the temporal limits of episodic mapping products. Validation against GloFAS discharge anomalies and precipitation datasets (CHIRPS v3.0, MSWEP) shows strong agreement with observed hydrometeorological conditions. By integrating nowcast outputs with exposure layers (WorldPop, ESA WorldCover, Giga-HOTOSM), the framework enables rapid estimation of affected populations, cropland, and critical infrastructure, supporting timely disaster response and resilience planning in South Asia.

Muhammad Kamran, Mohammad Moein Sheikholeslami, Andreas Wichmann et al.

In recent years, the number of remote satellites orbiting the Earth has grown significantly, streaming vast amounts of high-resolution visual data to support diverse applications across civil, public, and military domains. Among these applications, the generation and updating of spatial maps of the built environment have become critical due to the extensive coverage and detailed imagery provided by satellites. However, reconstructing spatial maps from satellite imagery is a complex computer vision task, requiring the creation of high-level object representations, such as primitives, to accurately capture the built environment. While the past decade has witnessed remarkable advancements in object detection and representation using visual data, primitives-based object representation remains a persistent challenge in computer vision. Consequently, high-quality spatial maps often rely on labor-intensive and manual processes. This paper introduces a novel deep learning methodology leveraging Graph Convolutional Networks (GCNs) to address these challenges in building footprint reconstruction. The proposed approach enhances performance by incorporating geometric regularity into building boundaries, integrating multi-scale and multi-resolution features, and embedding Attraction Field Maps into the network. These innovations provide a scalable and precise solution for automated building footprint extraction from a single satellite image, paving the way for impactful applications in urban planning, disaster management, and large-scale spatial analysis. Our model, Decoupled-PolyGCN, outperforms existing methods by 6% in AP and 10% in AR, demonstrating its ability to deliver accurate and regularized building footprints across diverse and challenging scenarios.

Kang Zhao, Muhammad Kamran, Gunho Sohn

In recent years, an ever-increasing number of remote satellites are orbiting the Earth which streams vast amount of visual data to support a wide range of civil, public and military applications. One of the key information obtained from satellite imagery is to produce and update spatial maps of built environment due to its wide coverage with high resolution data. However, reconstructing spatial maps from satellite imagery is not a trivial vision task as it requires reconstructing a scene or object with high-level representation such as primitives. For the last decade, significant advancement in object detection and representation using visual data has been achieved, but the primitive-based object representation still remains as a challenging vision task. Thus, a high-quality spatial map is mainly produced through complex labour-intensive processes. In this paper, we propose a novel deep neural network, which enables to jointly detect building instance and regularize noisy building boundary shapes from a single satellite imagery. The proposed deep learning method consists of a two-stage object detection network to produce region of interest (RoI) features and a building boundary extraction network using graph models to learn geometric information of the polygon shapes. Extensive experiments show that our model can accomplish multi-tasks of object localization, recognition, semantic labelling and geometric shape extraction simultaneously. In terms of building extraction accuracy, computation efficiency and boundary regularization performance, our model outperforms the state-of-the-art baseline models.

Muhammad Kamran, Muddassar Farooq

Recently, a significant amount of interest has been developed in motivating physicians to use e-health technology (especially Electronic Medical Records (EMR) systems). An important utility of such EMR systems is: a next generation of Clinical Decision Support Systems (CDSS) will extract knowledge from these electronic medical records to enable physicians to do accurate and effective diagnosis. It is anticipated that in future such medical records will be shared through cloud among different physicians to improve the quality of health care. Therefore, right protection of medical records is important to protect their ownership once they are shared with third parties. Watermarking is a proven well known technique to achieve this objective. The challenges associated with watermarking of EMR systems are: (1) some fields in EMR are more relevant in the diagnosis process; as a result, small variations in them could change the diagnosis, and (2) a misdiagnosis might not only result in a life threatening scenario but also might lead to significant costs of the treatment for the patients. The major contribution of this paper is an information-preserving watermarking scheme to address the above-mentioned challenges. We model the watermarking process as a constrained optimization problem. We demonstrate, through experiments, that our scheme not only preserves the diagnosis accuracy but is also resilient to well known attacks for corrupting the watermark. Last but not least, we also compare our scheme with a well known threshold-based scheme to evaluate relative merits of a classifier. Our pilot studies reveal that -- using proposed information-preserving scheme -- the overall classification accuracy is never degraded by more than 1%. In comparison, the diagnosis accuracy, using the threshold-based technique, is degraded by more than 18% in a worst case scenario.

Muhammad Kamran, Muddassar Farooq

Watermarking and fingerprinting of relational databases are quite proficient for ownership protection, tamper proofing, and proving data integrity. In past few years several such techniques have been proposed. A survey of almost all the work done, till date, in these fields has been presented in this paper. The techniques have been classified on the basis of how and where they embed the watermark. The analysis and comparison of these techniques on different merits has also been provided. In the end, this paper points out the direction of future research in these fields.