Ilham Zerrouk
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Ilham Zerrouk has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Cristina Barrado
Computer Architecture Department, Technical University of Catalonia, Castelldefels, Spain
2 shared publications - Enric Pastor
Universitat Politecnica de Catalunya
2 shared publications - Esther Salamí
Computer Architecture Department, Technical University of Catalonia, Castelldefels, Spain
2 shared publications - Gautier Hattenberger
École Nationale de l'Aviation Civile Université de Toulouse France
2 shared publications - Jamal Berrich
National School of Applied Sciences, Université Mohammed Premier
2 shared publications - Toumi Bouchentouf
National School of Applied Sciences, Université Mohammed Premier
2 shared publications
Latest Publications
- Open Access
Increasing Automation on Mission Planning for Heterogeneous Multi-Rotor Drone Fleets in Emergency Response
Drones are increasingly vital for disaster management, yet emergency fleets often consist of heterogeneous platforms, complicating task allocation. Efficient deployment requires rapid assignment based on vehicle and payload characteristics. This work proposes a three-step method composed of fleet analysis, area decomposition and trajectory generation for multi-rotor drone surveillance, aiming to achieve complete area coverage in minimal time while respecting no-fly zones. The three-step method generates optimized trajectories for all drones in less than 2 min, ensuring uniform precision and reduced flight distance compared to state-of-the-art methods, achieving mean distance gains of up to 9.31% with a homogeneous fleet of 10 drones. Additionally, a comparative analysis of area partitioning algorithms reveals that simplifying the geometry of the surveillance region can lead to more effective divisions and less complex trajectories. This simplification results in approximately 8.4% fewer turns, even if it slightly increases the total area to be covered.
Open AccessIncreasing Automation on Mission Planning for Heterogeneous Multi-Rotor Drone Fleets in Emergency Response
Drones are increasingly vital for disaster management, yet emergency fleets often consist of heterogeneous platforms, complicating task allocation. Efficient deployment requires rapid assignment based on vehicle and payload characteristics. This work proposes a three-step method composed of fleet analysis, area decomposition and trajectory generation for multi-rotor drone surveillance, aiming to achieve complete area coverage in minimal time while respecting no-fly zones. The three-step method generates optimized trajectories for all drones in less than 2 min, ensuring uniform precision and reduced flight distance compared to state-of-the-art methods, achieving mean distance gains of up to 9.31% with a homogeneous fleet of 10 drones. Additionally, a comparative analysis of area partitioning algorithms reveals that simplifying the geometry of the surveillance region can lead to more effective divisions and less complex trajectories. This simplification results in approximately 8.4% fewer turns, even if it slightly increases the total area to be covered.
- Open Access
- 15 October 2025
- Published by MDPI AG in Preprints.org
Increasing Automation on First Responders Reaction When Deploying Heterogeneous Fleet of Drones in Emergency Scenarios
Drones are becoming a very frequent and useful tool for emergency responders in supporting disaster management actions, but most emergency responders' fleets end-up in a plethora of drones with heterogeneous performances. In case of a major disaster all available resources are welcome. The allocation of task to each drone must be done taking into account the characteristics of the vehicle and of the payload, and must be done fast. In this work we present a methodology for the planning of drone trajectories for the surveillance of an area, using each available asset according to its potential and with the objective to obtain the full area scanned in the fastest possible time. This methodology accounts for no-fly zones that drones must completely avoid. Results show that, in less than 2 minutes, the trajectories of all the drones of an heterogeneous fleet can be generated to efficiently cover the area with a uniform precision, and less flight distance compared to the best state-of-the-art methods. The comparison of different area partition algorithms shows that it may be better to simplify the area for a better split despite the increase of area to cover.
- 15 October 2025
- Published by MDPI AG in Preprints.org
Open AccessIncreasing Automation on First Responders Reaction When Deploying Heterogeneous Fleet of Drones in Emergency Scenarios
Drones are becoming a very frequent and useful tool for emergency responders in supporting disaster management actions, but most emergency responders' fleets end-up in a plethora of drones with heterogeneous performances. In case of a major disaster all available resources are welcome. The allocation of task to each drone must be done taking into account the characteristics of the vehicle and of the payload, and must be done fast. In this work we present a methodology for the planning of drone trajectories for the surveillance of an area, using each available asset according to its potential and with the objective to obtain the full area scanned in the fastest possible time. This methodology accounts for no-fly zones that drones must completely avoid. Results show that, in less than 2 minutes, the trajectories of all the drones of an heterogeneous fleet can be generated to efficiently cover the area with a uniform precision, and less flight distance compared to the best state-of-the-art methods. The comparison of different area partition algorithms shows that it may be better to simplify the area for a better split despite the increase of area to cover.
- 2 April 2025
- Published by Springer Nature
- p. 67-74
Fast Drone Obstacle Detection Approach Based on MobileNet Classification CNN Architectures
- 2 April 2025
- Published by Springer Nature
- p. 67-74
Fast Drone Obstacle Detection Approach Based on MobileNet Classification CNN Architectures
- Open Access
- 24 April 2023
- Published by Springer Nature in Research Square
Evolutionary Algorithm for Optimized CNN Architecture Search Applied to Real-Time Boat Detection in Aerial Images
When processing the detection of boats in aerial images by neural networks, we have always been concerned about the execution time of these networks in the equipment on board the Unmanned Aerial Vehicle (UAV). Throughout its mission, the UAV will capture images that must be processed in real time. For this purpose, a network optimized for execution time is essential. This article proposes an enhanced Network Architecture Search (NAS) method for searching for time-optimized detection networks, for a given dataset, using an evolutionary algorithm. The search uses mutations as a mechanism of evolution that affect the structure of the network and the hyper-parameters of its layers. Its original fitness function allows the choice of architectures that are not very greedy in terms of operations, specifically favouring small networks whose advantages are to be fast and quick to train, thus accelerating the search algorithm. Using this method, we were able to obtain detection networks with an improved mean Average Precision (mAP) compared to the initial network (parent) but with much fewer FLoating-point OPerations (Flops): 68% of operations reduction. This induces considerable gain in terms of execution time with 50 Frames Processed per Second (FPS) in an embedded environment on a drone.
- 24 April 2023
- Published by Springer Nature in Research Square
Open AccessEvolutionary Algorithm for Optimized CNN Architecture Search Applied to Real-Time Boat Detection in Aerial Images
When processing the detection of boats in aerial images by neural networks, we have always been concerned about the execution time of these networks in the equipment on board the Unmanned Aerial Vehicle (UAV). Throughout its mission, the UAV will capture images that must be processed in real time. For this purpose, a network optimized for execution time is essential. This article proposes an enhanced Network Architecture Search (NAS) method for searching for time-optimized detection networks, for a given dataset, using an evolutionary algorithm. The search uses mutations as a mechanism of evolution that affect the structure of the network and the hyper-parameters of its layers. Its original fitness function allows the choice of architectures that are not very greedy in terms of operations, specifically favouring small networks whose advantages are to be fast and quick to train, thus accelerating the search algorithm. Using this method, we were able to obtain detection networks with an improved mean Average Precision (mAP) compared to the initial network (parent) but with much fewer FLoating-point OPerations (Flops): 68% of operations reduction. This induces considerable gain in terms of execution time with 50 Frames Processed per Second (FPS) in an embedded environment on a drone.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Air Surveillance Planning Approach for Large Areas
We consider an area we would like to scan using drones that can perform air surveillance, the area is too large for one drone in a mission can reach and scan. In our approach, the environment is modulated in a grid view, and each node (so called point) has a given priority, this priority define the importance of that point (the need to reach that point). The problem is processed as two sub-problems, the first part focuses on dividing the area to smaller zones which the drone can perform in a mission while meeting the required constraints. The drone has a limit energy, so a limit trajectory to perform. In the second part of the problem, we should find the best (optimal) trajectory for each zone, starting from a specific point and returning to it. The approach we present aim to maximize the gain (priorities sum) of the trajectory in each group of points that belongs to a part of the surveillance area, with the limit budget we have. Up next we detail the problem and discuss the performance of the approach.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Air Surveillance Planning Approach for Large Areas
We consider an area we would like to scan using drones that can perform air surveillance, the area is too large for one drone in a mission can reach and scan. In our approach, the environment is modulated in a grid view, and each node (so called point) has a given priority, this priority define the importance of that point (the need to reach that point). The problem is processed as two sub-problems, the first part focuses on dividing the area to smaller zones which the drone can perform in a mission while meeting the required constraints. The drone has a limit energy, so a limit trajectory to perform. In the second part of the problem, we should find the best (optimal) trajectory for each zone, starting from a specific point and returning to it. The approach we present aim to maximize the gain (priorities sum) of the trajectory in each group of points that belongs to a part of the surveillance area, with the limit budget we have. Up next we detail the problem and discuss the performance of the approach.