Zoubir Barraz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zoubir Barraz has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
Ibtihal Ait Abdelmoula
6 shared publicationsImane Sebari
6 shared publicationsNassim Lamrini
6 shared publicationsKenza Ait El Kadi
3 shared publicationsAbdelkoudouss Izem
CEO IMAGE MAPPING SARL
1 shared publicationAbdelmalek El Mehdi
Smartict LAB National Schools Of Applied Sciences,Oujda,Morocco
1 shared publication
Latest Publications
- Open Access
- 9 May 2025
- Published by Elsevier in Energy and AI
- Vol. 21
A holistic multimodal approach for real-time anomaly detection and classification in large-scale photovoltaic plants
- 9 May 2025
- Published by Elsevier in Energy and AI
- Vol. 21
Open AccessA holistic multimodal approach for real-time anomaly detection and classification in large-scale photovoltaic plants
- Open Access
- 14 March 2025
- Published by MDPI AG in Technologies
- Vol. 13 (3) , 117
Towards a Holistic Approach for UAV-Based Large-Scale Photovoltaic Inspection: A Review on Deep Learning and Image Processing Techniques
This paper provides an in-depth literature review on image processing techniques, focusing on deep learning approaches for anomaly detection and classification in photovoltaics. It examines key components of UAV-based PV inspection, including data acquisition protocols, panel segmentation and geolocation, anomaly classification, and optimizations for model generalization. Furthermore, challenges related to domain adaptation, dataset limitations, and multimodal fusion of RGB and thermal data are also discussed. Finally, research gaps and opportunities are analyzed to create a holistic, scalable, and real-time inspection workflow for large-scale installation. This review serves as a reference for researchers and industry professionals to advance UAV-based PV inspection.
- 14 March 2025
- Published by MDPI AG in Technologies
- Vol. 13 (3) , 117
Open AccessTowards a Holistic Approach for UAV-Based Large-Scale Photovoltaic Inspection: A Review on Deep Learning and Image Processing Techniques
This paper provides an in-depth literature review on image processing techniques, focusing on deep learning approaches for anomaly detection and classification in photovoltaics. It examines key components of UAV-based PV inspection, including data acquisition protocols, panel segmentation and geolocation, anomaly classification, and optimizations for model generalization. Furthermore, challenges related to domain adaptation, dataset limitations, and multimodal fusion of RGB and thermal data are also discussed. Finally, research gaps and opportunities are analyzed to create a holistic, scalable, and real-time inspection workflow for large-scale installation. This review serves as a reference for researchers and industry professionals to advance UAV-based PV inspection.
- Open Access
- 1 January 2025
- Published by Elsevier in Results in Engineering
- Vol. 25
A cascading decision system for enhanced anomaly classification of large-scale photovoltaic systems using Drone's thermal data with class-imbalance problem
- 1 January 2025
- Published by Elsevier in Results in Engineering
- Vol. 25
Open AccessA cascading decision system for enhanced anomaly classification of large-scale photovoltaic systems using Drone's thermal data with class-imbalance problem
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 189, 1751-1755
One to segment them All: A Data-based Domain Generalization approach for Solar Module segmentation using Thermal UAV Images
Using trained deep learning models on an out-of-distribution dataset could affect those models’ performance, which is most likely to decline due to the domain shift between the training domain and the target domain. To this end, Domain Generalization (DG) is one of the tools used to improve the generalization rate of the model and increase its adaptability to unseen data. Using a data-based domain generalization, this study intends to create a solar module segmentation model using thermal UAV images, by including various type of technologies and representations of solar modules in training data. Developing the generalization of the solar panel segmentation could enhance the performance in the workflow of automatic photovoltaic plants monitoring. The thermal images dataset was collected from six photovoltaic sites in Benguerir - Morocco in various shooting conditions. The global capacity of these systems is 1MW and they are equipped with different technologies. The training of this model achieved 99% mAP@0.5 for testing and could perform well on unseen data, that is different from the training data, ensuring the effectiveness of the approach to generalize the trained Deep learning models which can be used in other domains.
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 189, 1751-1755
One to segment them All: A Data-based Domain Generalization approach for Solar Module segmentation using Thermal UAV Images
Using trained deep learning models on an out-of-distribution dataset could affect those models’ performance, which is most likely to decline due to the domain shift between the training domain and the target domain. To this end, Domain Generalization (DG) is one of the tools used to improve the generalization rate of the model and increase its adaptability to unseen data. Using a data-based domain generalization, this study intends to create a solar module segmentation model using thermal UAV images, by including various type of technologies and representations of solar modules in training data. Developing the generalization of the solar panel segmentation could enhance the performance in the workflow of automatic photovoltaic plants monitoring. The thermal images dataset was collected from six photovoltaic sites in Benguerir - Morocco in various shooting conditions. The global capacity of these systems is 1MW and they are equipped with different technologies. The training of this model achieved 99% mAP@0.5 for testing and could perform well on unseen data, that is different from the training data, ensuring the effectiveness of the approach to generalize the trained Deep learning models which can be used in other domains.
- 13 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 153-159
A Hybrid and Scalable Architecture of a Monitoring System for Photovoltaic Installations
This study introduces a new and scalable monitoring system architecture that aims to improve O&M operations and tasks for photovoltaic installations. The proposed system includes four main layers that handle the process from data acquisition until decision support is provided to operators in the field. The main layer uses thermal imaging and electrical fault diagnosis methods to detect and classify faults at the inverter, string, and single PV panel levels, which helps enhance the operation and maintenance strategies and improve the reliability of PV system components by identifying the source and nature of the detected faults. Furthermore, the data, diagnosis results, and O&M plans are stored in a geospatial database to add spatial dimension, link each component to its data, and thus localize the detected faults. This article provides a detailed description of the proposed architecture and its key features that make the maintenance of a PV plant easier for operators by providing better insights using the hybrid approach and enabling fast interventions in the field.
- 13 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 153-159
A Hybrid and Scalable Architecture of a Monitoring System for Photovoltaic Installations
This study introduces a new and scalable monitoring system architecture that aims to improve O&M operations and tasks for photovoltaic installations. The proposed system includes four main layers that handle the process from data acquisition until decision support is provided to operators in the field. The main layer uses thermal imaging and electrical fault diagnosis methods to detect and classify faults at the inverter, string, and single PV panel levels, which helps enhance the operation and maintenance strategies and improve the reliability of PV system components by identifying the source and nature of the detected faults. Furthermore, the data, diagnosis results, and O&M plans are stored in a geospatial database to add spatial dimension, link each component to its data, and thus localize the detected faults. This article provides a detailed description of the proposed architecture and its key features that make the maintenance of a PV plant easier for operators by providing better insights using the hybrid approach and enabling fast interventions in the field.
- 8 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 255-260
Production-Ready Deep Learning Model Optimization for Anomaly Detection in Photovoltaic Systems
Anomaly detection in photovoltaic systems using deep learning models can help further automatize classification tasks and support the operator in decision making. However, the performance of pretrained deep learning models decreases in production owing to the difference between training and production data (domain shift). This performance gap can lead to serious problems when monitoring photovoltaic (PV) farms. To this end, this study proposes an approach to adapt new instances to fit the constraints of the input layer of the pretrained model by image segmentation using Niblack thresholding, padding, and resizing. In addition, the localization of single panels was calculated using metadata. Moreover, a retraining cycle was proposed to include new instances in the training process to fine-tune the models and adapt the weights to the images taken during production. The proposed algorithm extracted 81% of the panels from the images fed into it. However, the pretrained model, which was used to classify the segmented images to test its performance, did not perform well. This indicates the importance of the retraining process for optimizing the model for production.
- 8 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 255-260
Production-Ready Deep Learning Model Optimization for Anomaly Detection in Photovoltaic Systems
Anomaly detection in photovoltaic systems using deep learning models can help further automatize classification tasks and support the operator in decision making. However, the performance of pretrained deep learning models decreases in production owing to the difference between training and production data (domain shift). This performance gap can lead to serious problems when monitoring photovoltaic (PV) farms. To this end, this study proposes an approach to adapt new instances to fit the constraints of the input layer of the pretrained model by image segmentation using Niblack thresholding, padding, and resizing. In addition, the localization of single panels was calculated using metadata. Moreover, a retraining cycle was proposed to include new instances in the training process to fine-tune the models and adapt the weights to the images taken during production. The proposed algorithm extracted 81% of the panels from the images fed into it. However, the pretrained model, which was used to classify the segmented images to test its performance, did not perform well. This indicates the importance of the retraining process for optimizing the model for production.
- 24 October 2021
- Published by Springer Nature
- p. 742-772
Cloud Computing of Large UAV Datasets for 3D Photogrammetric Reconstruction
- 24 October 2021
- Published by Springer Nature
- p. 742-772
Cloud Computing of Large UAV Datasets for 3D Photogrammetric Reconstruction