Hayat Rajani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hayat Rajani has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Rafael Garcia
University of Girona
6 shared publications Nuno Gracias
Computer Vision and Robotics Research Institute, University of Girona, Spain
3 shared publications- Nuno Gracias
Computer Vision and Robotics Research Group (ViCOROB), University of Girona, 17003 Girona, Spain
3 shared publications - Can Lei
Northwestern Polytechnical University
2 shared publications - Gabriela Ghimpeteanu
Coronis Computing SL, 17003 Girona, Spain
2 shared publications - Huigang Wang
Northwestern Polytechnical University
2 shared publications
Latest Publications
- Open Access
- 10 August 2026
- Published by Copernicus GmbH in EGUsphere
- Vol. 2026, 1-32
BenthiCat: An opti-acoustic dataset for advancing benthic classification and habitat mapping
Benthic habitat mapping is fundamental for understanding marine ecosystems, guiding conservation efforts, and supporting sustainable resource management. Yet, the scarcity of large, annotated datasets limits the development and benchmarking of machine learning models in this domain. This paper introduces a thorough multi-modal dataset, comprising about a million side-scan sonar (SSS) tiles collected along the coast of Catalonia (Spain), complemented by bathymetric maps and a set of co-registered optical images from targeted surveys using an autonomous underwater vehicle (AUV). Approximately 36000 of the SSS tiles have been manually annotated with segmentation masks to enable supervised fine-tuning of classification models. All the raw sensor data, together with mosaics, are also released to support further exploration and algorithm development. To address challenges in multi-sensor data fusion for AUVs, we spatially associate optical images with corresponding SSS tiles, facilitating self-supervised, cross-modal representation learning. Accompanying open-source preprocessing and annotation tools are provided to enhance accessibility and encourage research. This resource aims to establish a standardized benchmark for underwater habitat mapping, promoting advancements in autonomous seafloor classification and multi-sensor integration.
- 10 August 2026
- Published by Copernicus GmbH in EGUsphere
- Vol. 2026, 1-32
Open AccessBenthiCat: An opti-acoustic dataset for advancing benthic classification and habitat mapping
Benthic habitat mapping is fundamental for understanding marine ecosystems, guiding conservation efforts, and supporting sustainable resource management. Yet, the scarcity of large, annotated datasets limits the development and benchmarking of machine learning models in this domain. This paper introduces a thorough multi-modal dataset, comprising about a million side-scan sonar (SSS) tiles collected along the coast of Catalonia (Spain), complemented by bathymetric maps and a set of co-registered optical images from targeted surveys using an autonomous underwater vehicle (AUV). Approximately 36000 of the SSS tiles have been manually annotated with segmentation masks to enable supervised fine-tuning of classification models. All the raw sensor data, together with mosaics, are also released to support further exploration and algorithm development. To address challenges in multi-sensor data fusion for AUVs, we spatially associate optical images with corresponding SSS tiles, facilitating self-supervised, cross-modal representation learning. Accompanying open-source preprocessing and annotation tools are provided to enhance accessibility and encourage research. This resource aims to establish a standardized benchmark for underwater habitat mapping, promoting advancements in autonomous seafloor classification and multi-sensor integration.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64, 4209814
Coarse-to-Fine Nonrigid Registration for Side-Scan Sonar Mosaicking
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64, 4209814
Coarse-to-Fine Nonrigid Registration for Side-Scan Sonar Mosaicking
- Open Access
Hyperspectral Imaging for Identifying Foreign Objects on Pork Belly
Ensuring food safety and quality is critical in the food-processing industry, where the detection of contaminants remains a persistent challenge. This study assesses the feasibility of hyperspectral imaging (HSI) for detecting foreign objects on pork belly meat. A Specim FX17 hyperspectral camera was used to capture data across various bands in the near-infrared spectrum (900–1700 nm), enabling identification of contaminants that are often missed by traditional visual inspection methods. The proposed solution combines a segmentation approach based on a lightweight Vision Transformer with specific pre- and post-processing strategies to distinguish contaminants from meat, fat, and conveyor belt, while emphasizing on a low false-positive rate. On a test set of 55 images with contaminants, the method retained most true positives; on 183 clean images, the full pipeline eliminated all false positives. Across 208 additional images acquired under production-line temperature variation (10–55 °C), only one image exhibited small false positives, and on a challenging 95-image set with fat-like spectra the pipeline produced zero false positives. These results demonstrate high detection accuracy and training efficiency while addressing issues such as noise, temperature drift, and spectral similarity. The findings support the feasibility of real-time HSI for automated quality control.
Open AccessHyperspectral Imaging for Identifying Foreign Objects on Pork Belly
Ensuring food safety and quality is critical in the food-processing industry, where the detection of contaminants remains a persistent challenge. This study assesses the feasibility of hyperspectral imaging (HSI) for detecting foreign objects on pork belly meat. A Specim FX17 hyperspectral camera was used to capture data across various bands in the near-infrared spectrum (900–1700 nm), enabling identification of contaminants that are often missed by traditional visual inspection methods. The proposed solution combines a segmentation approach based on a lightweight Vision Transformer with specific pre- and post-processing strategies to distinguish contaminants from meat, fat, and conveyor belt, while emphasizing on a low false-positive rate. On a test set of 55 images with contaminants, the method retained most true positives; on 183 clean images, the full pipeline eliminated all false positives. Across 208 additional images acquired under production-line temperature variation (10–55 °C), only one image exhibited small false positives, and on a challenging 95-image set with fat-like spectra the pipeline produced zero false positives. These results demonstrate high detection accuracy and training efficiency while addressing issues such as noise, temperature drift, and spectral similarity. The findings support the feasibility of real-time HSI for automated quality control.
- Open Access
Hyperspectral Imaging for Identifying Foreign Objects on Pork Belly
Ensuring food safety and quality is critical in the food processing industry, where the detection of contaminants remains a persistent challenge. This study presents an automated solution for detecting foreign objects on pork belly meat using hyperspectral imaging (HSI). A hyperspectral camera was used to capture data across various bands in the near-infrared (NIR) spectrum (900-1700 nm), enabling accurate identification of contaminants that are often undetectable through traditional visual inspection methods. The proposed solution combines pre-processing techniques with a segmentation approach based on a lightweight Vision Transformer (ViT) to distinguish contaminants from meat, fat, and conveyor belt materials. The adopted strategy demonstrates high detection accuracy and training efficiency, while also addressing key industrial challenges such as inherent noise, temperature variations, and spectral similarity between contaminants and pork belly. Experimental results validate the effectiveness of hyperspectral imaging in enhancing food safety, highlighting its potential for broad real-time applications in automated quality control processes.
Open AccessHyperspectral Imaging for Identifying Foreign Objects on Pork Belly
Ensuring food safety and quality is critical in the food processing industry, where the detection of contaminants remains a persistent challenge. This study presents an automated solution for detecting foreign objects on pork belly meat using hyperspectral imaging (HSI). A hyperspectral camera was used to capture data across various bands in the near-infrared (NIR) spectrum (900-1700 nm), enabling accurate identification of contaminants that are often undetectable through traditional visual inspection methods. The proposed solution combines pre-processing techniques with a segmentation approach based on a lightweight Vision Transformer (ViT) to distinguish contaminants from meat, fat, and conveyor belt materials. The adopted strategy demonstrates high detection accuracy and training efficiency, while also addressing key industrial challenges such as inherent noise, temperature variations, and spectral similarity between contaminants and pork belly. Experimental results validate the effectiveness of hyperspectral imaging in enhancing food safety, highlighting its potential for broad real-time applications in automated quality control processes.
- Open Access
- 25 February 2025
- Published by MDPI AG in Journal of Manufacturing and Materials Processing
- Vol. 9 (3) , 74
Real-Time Stringing Detection for Additive Manufacturing
Additive Manufacturing (AM), commonly known as 3D printing, has gained significant traction across various industries due to its versatility and customization potential. However, the process remains time-consuming, with print durations ranging from hours to days depending on the complexity and size of the object. In many cases, errors occur due to object misalignment, material stringing due to nozzle overflow, and filament blockages, which can lead to complete print failures. Such errors often go undetected for extended periods, resulting in substantial losses of time and material. This study explores the implementation of traditional computer vision, image processing, and machine learning techniques to enable real-time error detection, specifically focusing on stringing-related anomalies. To address data scarcity in training machine learning models, we also release a new dataset and improve upon the results achieved by the Obico server model, one of the most prominent tools for stringing detection. Our contributions aim to enhance process reliability, reduce material wastage, and optimize time efficiency in AM workflows.
- 25 February 2025
- Published by MDPI AG in Journal of Manufacturing and Materials Processing
- Vol. 9 (3) , 74
Open AccessReal-Time Stringing Detection for Additive Manufacturing
Additive Manufacturing (AM), commonly known as 3D printing, has gained significant traction across various industries due to its versatility and customization potential. However, the process remains time-consuming, with print durations ranging from hours to days depending on the complexity and size of the object. In many cases, errors occur due to object misalignment, material stringing due to nozzle overflow, and filament blockages, which can lead to complete print failures. Such errors often go undetected for extended periods, resulting in substantial losses of time and material. This study explores the implementation of traditional computer vision, image processing, and machine learning techniques to enable real-time error detection, specifically focusing on stringing-related anomalies. To address data scarcity in training machine learning models, we also release a new dataset and improve upon the results achieved by the Obico server model, one of the most prominent tools for stringing detection. Our contributions aim to enhance process reliability, reduce material wastage, and optimize time efficiency in AM workflows.
- Open Access
- 31 August 2023
- Published by Elsevier in Ocean Engineering
- Vol. 286
A convolutional vision transformer for semantic segmentation of side-scan sonar data
- 31 August 2023
- Published by Elsevier in Ocean Engineering
- Vol. 286
Open AccessA convolutional vision transformer for semantic segmentation of side-scan sonar data
- Open Access
A Convolutional Vision Transformer for Semantic Segmentation of Side-Scan Sonar Data
Distinguishing among different marine benthic habitat characteristics is of key importance in a wide set of seabed operations ranging from installations of oil rigs to laying networks of cables and monitoring the impact of humans on marine ecosystems. The Side-Scan Sonar (SSS) is a widely used imaging sensor in this regard. It produces high-resolution seafloor maps by logging the intensities of sound waves reflected back from the seafloor. In this work, we leverage these acoustic intensity maps to produce pixel-wise categorization of different seafloor types. We propose a novel architecture adapted from the Vision Transformer (ViT) in an encoder-decoder framework. Further, in doing so, the applicability of ViTs is evaluated on smaller datasets. To overcome the lack of CNN-like inductive biases, thereby making ViTs more conducive to applications in low data regimes, we propose a novel feature extraction module to replace the Multi-layer Perceptron (MLP) block within transformer layers and a novel module to extract multiscale patch embeddings. A lightweight decoder is also proposed to complement this design in order to further boost multiscale feature extraction. With the modified architecture, we achieve state-of-the-art results and also meet real-time computational requirements. We make our code available at ~\url{https://github.com/hayatrajani/s3seg-vit
Open AccessA Convolutional Vision Transformer for Semantic Segmentation of Side-Scan Sonar Data
Distinguishing among different marine benthic habitat characteristics is of key importance in a wide set of seabed operations ranging from installations of oil rigs to laying networks of cables and monitoring the impact of humans on marine ecosystems. The Side-Scan Sonar (SSS) is a widely used imaging sensor in this regard. It produces high-resolution seafloor maps by logging the intensities of sound waves reflected back from the seafloor. In this work, we leverage these acoustic intensity maps to produce pixel-wise categorization of different seafloor types. We propose a novel architecture adapted from the Vision Transformer (ViT) in an encoder-decoder framework. Further, in doing so, the applicability of ViTs is evaluated on smaller datasets. To overcome the lack of CNN-like inductive biases, thereby making ViTs more conducive to applications in low data regimes, we propose a novel feature extraction module to replace the Multi-layer Perceptron (MLP) block within transformer layers and a novel module to extract multiscale patch embeddings. A lightweight decoder is also proposed to complement this design in order to further boost multiscale feature extraction. With the modified architecture, we achieve state-of-the-art results and also meet real-time computational requirements. We make our code available at ~\url{https://github.com/hayatrajani/s3seg-vit