Jurrian Doornbos

Mr. Jurrian Doornbos


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 February 2024 in IEEE Access
Verified
Journal Article
Open access
JDJurrian Doornbos
Jurrian Doornbos
KBKwabena E. Bennin
Kwabena E. Bennin
ÖBÖnder Babur
Önder Babur
João ValenteJoão Valente
João Valente
Unmanned aerial vehicles (UAVs) have emerged as versatile tools with significant potential in various fields, including, but not limited to civil engineering, ecology, networking and precision agriculture. Systematic literature reviews (SLRs) play a crucial role in assessing the quality of research methods and approaches, aiding researchers and practitioners in selecting and optimizing their projects. However, the quality assessment of UAV-related SLRs and the aggregation of UAV technologies across research fields remain limited. This study aims to address these gaps by conducting a tertiary literature review (TLR) that assesses the quality of SLRs, aggregates data across research fields, and provides guidelines for researchers and practitioners in the UAV community. Based on a review of 73 SLRs, it is evident that the quality of UAV-related SLRs is generally low, with a lack of quality assessment and inadequate reporting of detailed information on primary studies. Consequently, this study presents reporting items and example quality assessment ratings sourced from the SLRs to enhance the transparency and comparability of future UAV-related research. Additionally, it highlights common limitations faced by UAV applications, such as regulatory, technical, social, and research-related challenges, which require attention for progress in the field. Overall, this study aims to enhance the quality and knowledge sharing in the UAV research community by providing insights into the current state of UAV-related SLRs and offering practical guidance for researchers and practitioners through the provision of data-extraction templates and quality control questions for future UAV-related reviews and primary research. Key outcomes: • This tertiary review indicates a low quality of UAV-related SLRs. • Lack of quality assessment and inadequate reporting of detailed information on primary studies is identified as a prevalent issue. • Data-extraction templates and quality control questions ratings sourced from SLRs are offered for future UAV-related reviews and primary research to enhance transparency and comparability in future UAV-related research. • Common limitations faced by UAV applications are highlighted, including regulatory, technical, social, and research-related challenges.

1 February 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JDJurrian Doornbos
Jurrian Doornbos
ÖBÖnder Babur
Önder Babur
João ValenteJoão Valente
João Valente
High-resolution NDVI maps derived from UAV imagery are valuable in precision agriculture, supporting vineyard management decisions such as disease risk and vigor assessments. However, the expense and complexity of multispectral sensors limit their widespread use. In this study, we evaluate Generative Adversarial Network (GAN) approaches—trained on either multispectral-derived or true RGB data—to convert low-cost RGB imagery into NDVI maps. We benchmark these models against simpler, explainable RGB-based indices (RGBVI, vNDVI) using Botrytis bunch rot (BBR) risk and vigor mapping as application-centric tests. Our findings reveal that both multispectral- and RGB-trained GANs can generate NDVI maps suitable for BBR risk modelling, achieving R-squared values between 0.8 and 0.99 on unseen datasets. However, the RGBVI and vNDVI indices often match or exceed the GAN outputs, for vigor mapping. Moreover, model performance varies with sensor differences, vineyard structures, and environmental conditions, underscoring the importance of training data diversity and domain alignment. In highlighting these sensitivities, this application-centric evaluation demonstrates that while GANs can offer a viable NDVI alternative in some scenarios, their real-world utility is not guaranteed. In many cases, simpler RGB-based indices may provide equal or better results, suggesting that the choice of NDVI conversion method should be guided by both application requirements and the underlying characteristics of the subject matter.

10 October 2025 in Data in Brief
Verified
Journal Article
Open access
JDJurrian Doornbos
Jurrian Doornbos
ÖBÖnder Babur
Önder Babur
This dataset comprises a curated collection of UAV RGB and multispectral imagery sourced from multiple open-access platforms. It contains the largest set of UAV imagery covering at least four spectral bands (Green, Red, RedEdge, and Near-Infrared) and is available as either orthomosaic or raw sensor data. A systematic calibration process was employed to ensure radiometric consistency across the diverse sensor types (DJI Mavic 3 M, DJI Phantom 4 Multispectral, Parrot Sequoia, MicaSense RedEdge, and MicaSense Altum(PT)). This involved correcting raw digital numbers (DNs) for sensor-specific variables (e.g., black level, vignetting) and normalizing pixel values with internal sunlight sensors. The resultant imagery is provided as UINT8 5-channel multispectral TIFF files and RGB 3-channel JPG files for robust cross-study comparison. Comprehensive metadata, processing scripts, and calibration details are publicly available in the accompanying repository folder. This dataset offers a valuable resource for researchers and practitioners seeking consistent, high-quality UAV multispectral data to train or fine-tune foundational models in computer vision and remote sensing applications.

29 October 2025 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Verified
Journal Article
Open access
PDF file
JDJurrian Doornbos
Jurrian Doornbos
ÖBÖnder Babur
Önder Babur
While UAVs have revolutionized data collection for remote sensing, the practical application of Deep Learning remains severely limited by the scarcity of labelled training data, creating a stark contrast between laboratory successes and field performance. This research investigates whether transfer learning techniques can overcome this "small data problem" by enabling UAV-based deep learning models to generalize effectively across diverse environments without requiring prohibitive amounts of labelled examples. We present the use of an efficient self-supervised learning framework (FastSiam) tailored specifically for multispectral UAV imagery to overcome this generalization gap. Our approach enables effective feature learning without requiring extensive labelled data, bridging the gap between the potential of foundation models and the resource constraints of UAV remote sensing applications. We evaluate our method on a vineyard segmentation task across multiple geographic locations, demonstrating that models with FastSiam pretrained backbones significantly outperform their end-to-end trained counterparts, even with extremely limited labelled data. The most sophisticated architecture tested, Swin-T with a pretrained backbone, achieved an average F1 score of 0.80 across diverse test sites, showcasing robust generalization capabilities. Importantly, our results show that pretrained models benefit more from diversity in training samples than from sheer volume, suggesting new pathways for efficient model development in UAV applications. This work establishes that self-supervised pretraining serves as an effective regularizer for remote sensing tasks. Pretraining limits overfitting and improves generalization across varying environmental conditions, whilst requiring only modest computational resources, making advanced Deep Learning techniques more accessible for practical UAV applications.

18 March 2025
Verified
Conference Paper
Open access
JDJurrian Doornbos
Jurrian Doornbos
ÖBÖnder Babur
Önder Babur
Uncrewed aerial vehicles (UAVs) have been identified as an important tool supporting more detailed remote sensing applications compared to satellite-based platforms, from agriculture to forest monitoring and sensing mountains. The insights the UAV can offer, due to its flexibility, high precision and sensor variety, are far beyond the previous approaches to measure the health of forests, yield in field crops, and even rockfall risk. The flexibility however also poses a problem, flight conditions, sensor types, flight height and angles all affect the generalization of developed approaches using UAVs. These supervised approaches also rely on large amounts of human-labelled datasets. A pathway to reduce high-label requirements is to utilize unsupervised training with Vision Transformers (ViTs). Pretrained Vision Transformers on large datasets generalize well to unseen data, with only supervised few samples required to specify the application. However, these models are often trained on massive web-scraped RGB datasets. Furthermore, RGB-ViTs miss the infrared domain to handle crucial vegetation information. Finally, UAV imagery is exclusively from the aerial perspective, this is missing in existing pretraining datasets.We present an openly available, pre-trained Vision Transformer specifically for UAV multispectral imagery across various domains. Furthermore, various downstream applications such as canopy height modelling and semantic segmentation are evaluated and compared against RGB baselines. The main contribution is the openly available training dataset, and the pre-trained models, with recipes for finetuning a task-specific head.The dataset is built around multispectral image contributions from the ICAERUS Drone Data Analytics Library and an additional database search on Zenodo and Data in Brief (Table 1.). This is followed by a quality check after, including radiometric calibration, and spectral alignment. Furthermore, all data is quantized into 16-bit float and sliced into smaller 224x224 chips with four channels (Green, Red, Red Edge and NIR). A summary of included datasets is presented in Table 1. DINOv2-s and DINOv2-b were chosen for the architecture as there is much available documentation and provide a state-of-the-art vision foundation model. The training was done in minibatches of size 32, for 6 days on two V100 GPUs.Early experiments suggest that the pre-trained models outperform existing DINOv2-s and DINOv2-b pre-trained foundation models in both the clarity of the features, as well as tuned on UAV-specific tasks (canopy height modelling, and semantic segmentation).Table 1. Included datasets for pretraining, total size on disk is 399GB

6 November 2026 in ISPRS Open Journal of Photogrammetry and Remote Sensing
Verified
Journal Article
Open access
JDJurrian Doornbos
Jurrian Doornbos
ÖBÖnder Babur
Önder Babur