Dr. Friso G. Heslinga Profile

Dr. Friso G. Heslinga

at TNO

SPIE Involvement:

Author

Publications (10)

Proceedings Article | 7 June 2024 Presentation + Paper

Automatic satellite characterization using simulated ISAR data

Friso Heslinga, Miguel Caro Cuenca, Rob Knight, Faruk Uysal

Proceedings Volume 13035, 1303517 (2024) https://doi.org/10.1117/12.3013381

KEYWORDS: Image segmentation, Satellites, Data modeling, Deep learning, Image analysis, Image processing

Read Abstract +

Proceedings Article | 7 June 2024 Presentation + Paper

Combining simulated data, foundation models, and few real samples for training object detectors

Friso Heslinga, Thijs Eker, Ella Fokkinga, Jan Erik van Woerden, Frank Ruis, Richard J. den Hollander, Klamer Schutte

Proceedings Volume 13035, 1303509 (2024) https://doi.org/10.1117/12.3013375

KEYWORDS: Deep learning, Scene simulation, Computer simulations, Object detection, Detector development

Read Abstract +

Proceedings Article | 7 June 2024 Presentation + Paper

Improving object detector training on synthetic data by starting with a strong baseline methodology

Frank Ruis, Alma Liezenga, Friso Heslinga, Luca Ballan, Thijs Eker, Richard J. den Hollander, Martin van Leeuwen, Judith Dijk, Wyke Huizinga

Proceedings Volume 13035, 1303511 (2024) https://doi.org/10.1117/12.3013441

KEYWORDS: Data modeling, Object detection, Transformers, Education and training, Performance modeling, 3D modeling, Sensors, Visual process modeling, Linear filtering, Computer vision technology

Read Abstract +

Proceedings Article | 7 June 2024 Presentation + Paper

EO and radar fusion for fine-grained target classification with a strong few-shot learning baseline

Luca Ballan, Jorge G. Melo, Sebastiaan van den Broek, Jan Baan, Friso Heslinga, Wyke Huizinga, Judith Dijk, Arta Dilo

Proceedings Volume 13057, 130570K (2024) https://doi.org/10.1117/12.3013756

KEYWORDS: Data modeling, Machine learning, Image classification, Visualization, Radar, Sensors, Deep learning

Read Abstract +

Combining data from multiple sensors to improve the overall robustness and reliability of a classification system has become crucial in many applications, from military surveillance and decision support, to autonomous driving, robotics, and medical imaging. This so-called sensor fusion is especially interesting for fine-grained target classification, in which very specific sub-categories (e.g. ship types) need to be distinguished, a task that can be challenging with data from a single modality. Typical modalities are electro-optical (EO) image sensors, that can provide rich visual details of an object of interest, and radar, that can yield additional spatial information. Defined by the approach used to combine data from these sensors, several fusion techniques exist. For example, late fusion can merge class probabilities outputted by separate processing pipelines dedicated to each of the individual sensor data. In particular, deep learning (DL) has been widely leveraged for EO image analysis, but typically requires a lot of data to adapt to the nuances of a fine-grained classification task. Recent advances in DL on foundation models have shown a high potential when dealing with in-domain data scarcity, especially in combination with few-shot learning. This paper presents a framework to effectively combine EO and radar sensor data, and shows how this method outperforms stand-alone single sensor methods for fine-grained target classification. We adopt a strong few-shot image classification baseline based on foundation models, which robustly handles the lack of in-domain data and exploits rich visual features. In addition, we investigate a weighted and a Bayesian fusion approach to combine target class probabilities outputted by the image classification model and radar kinematic features. Experiments with data acquired in a measurement campaign at the port of Rotterdam show that our fusion method improves on the classification performance of individual modalities.

Proceedings Article | 17 October 2023 Presentation + Paper

Leveraging temporal context in deep learning methodology for small object detection

Friso Heslinga, Frank Ruis, Luca Ballan, Martin van Leeuwen, Beatrice Masini, Jan Erik van Woerden, Richard J. den Hollander, Martin Berndsen, Jan Baan, Judith Dijk, Wyke Huizinga

Proceedings Volume 12742, 127420H (2023) https://doi.org/10.1117/12.2675589

KEYWORDS: Object detection, Video, Deep learning, Infrared cameras, Image segmentation

Read Abstract +

Proceedings Article | 17 October 2023 Presentation + Paper

The effect of simulation variety on a deep learning-based military vehicle detector

Thijs Eker, Friso Heslinga, Luca Ballan, Richard J. den Hollander, Klamer Schutte

Proceedings Volume 12742, 127420O (2023) https://doi.org/10.1117/12.2679808

KEYWORDS: 3D modeling, High dynamic range imaging, Object detection, Deep learning

Read Abstract +

SPIE Journal Paper | 28 May 2022 Open Access

Knowledge distillation with ensembles of convolutional neural networks for medical image segmentation

Julia M. Noothout, Nikolas Lessmann, Matthijs Van Eede, Louis van Harten, Ecem Sogancioglu, Friso Heslinga, Mitko Veta, Bram van Ginneken, Ivana Išgum

JMI, Vol. 9, Issue 05, 052407, (May 2022) https://doi.org/10.1117/12.10.1117/1.JMI.9.5.052407

KEYWORDS: Network architectures, Image segmentation, Brain, Medical imaging, Magnetic resonance imaging, Convolutional neural networks, Neuroimaging, Performance modeling, Heart, Computed tomography

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 16 March 2020 Presentation + Paper

Direct classification of type 2 diabetes from retinal fundus images in a population-based sample from the Maastricht study

Friso Heslinga, Josien P. Pluim, A.J.H.M. Houben, Miranda Schram, Ronald M. Henry, Coen D. Stehouwer, Marleen van Greevenbroek, Tos T.J.M. Berendschot, Mitko Veta

Proceedings Volume 11314, 113141N (2020) https://doi.org/10.1117/12.2549574

KEYWORDS: Image classification, Eye, Image analysis, Retinal scanning, Image processing

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Value based decision support to prioritize development of innovative technologies for image-guided vascular surgery in the hybrid operating theater

Friso Heslinga, Hendrik Koffijberg, Robert Geelkerken, Robbert Meerwaldt, Thijs ter Mors, Carine J. Doggen, Marjan Hummel

Proceedings Volume 11315, 1131525 (2020) https://doi.org/10.1117/12.2549486

KEYWORDS: Surgery, Medicine, Angiography, Image-guided intervention, Ionizing radiation, Radiation effects, Iodine, Aneurysms, Standards development, New and emerging technologies

Read Abstract +

Proceedings Article | 15 March 2019 Presentation + Paper

Approximation of a pipeline of unsupervised retina image analysis methods with a CNN

Friso Heslinga, Josien P. Pluim, Behdad Dashtbozorg, Tos T. J. Berendschot, A. J. H. M. Houben, Ronald M. A. Henry, Mitko Veta

Proceedings Volume 10949, 109491N (2019) https://doi.org/10.1117/12.2512393

KEYWORDS: Retina, Image analysis, Image processing, Neural networks, Visualization, Eye, Feature extraction, Convolutional neural networks

Read Abstract +

Showing 5 of 10 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years