In recent years, drones have increasingly supported First Responders (FRs) in monitoring incidents and providing additional information. However, analysing drone footage is time-intensive and cognitively demanding. In this research, we investigate the use of AI models for the detection of humans in drone footage to aid FRs in tasks such as locating victims. Detecting small-scale objects, particularly humans from high altitudes, poses a challenge for AI systems. We present first steps of introducing and evaluating a series of YOLOv8 Convolutional Neural Networks (CNNs) for human detection from drone images. The models are fine-tuned on a created drone image dataset of the Dutch Fire Services and were able to achieve a 53.1% F1-Score, identifying 439 out of 825 humans in the test dataset. These preliminary findings, validated by an incident commander, highlight the promising utility of these models. Ongoing efforts aim to further refine the models and explore additional technologies.
MULTIFILE
On April 12th 2019, researchers, students and consortia gathered at the World Horti Centre for an update on the overall status of the HiPerGreen project. The day consisted of presentations from a variety of the HiPerGreen students, staff and guest speakers. There were a variety of exciting updates from the technological and biological realms of the project, as well as an insightful presentation from Deliflor’s Geert Van Geest on Deliflor and their interests in imaging of chrysanthemums. Several new pieces of technology have arisen from the HiPerGreen project. The first being a rail-based imaging system capable of traversing the greenhouse using the heating pipes commonly found in Dutch greenhouses. The drone landing dock has also taken great steps forward and finally, HiPerGreen has partnered with drone manufacture Avular, a company working on the world’s first ‘ultra-wide band’ localized indoor drone. From a biological standpoint significant progress has been made regarding long-term plant monitoring with a focus on reducing fusarium occurrence in the crop. Students are working in climate chambers to model the symptoms of fusarium infection in orchids. Students are also working at Deliflor using the railsystem to measure uniformity in chrysanthemum test crops. Research with the multispectral camera continued and the team hopes to integrate the imaging into mass plant monitoring. The sympoium was concluded with a drink.
DOCUMENT
The two-year education programme HiPerGreen initiated by Inholland University of Applied Sciences came to a closure on Friday 27th September 2019 at the World Horti Center in Naaldwijk. The Final symposium gave consortium partners and other guests the opportunity to learn about the HiPerGreen’s team achievements and the various outputs the programme delivered. After the welcome word of lector Robotica Cock Heemskerk, Tom KerneyMitchell, biology researcher, summarized the efforts that the team made in plant monitoring (ranging from growth monitoring and prediction, chamber testing research to delivering fusarium maps to growers). Next Lucien Fesselet, project manager at HiPerGreen and CTO of Applied Drone Innovations) took the public through the team’s technology fails, trials and successes over the two-year programme. Sheelagh Bouvier, market researcher for HiPerGreen, shortly explained that she conducted desk research, field visits in greenhouses, interviews with growers and IP research. Then partner Roy van Rosmalen from Ter Laak Orchids, explained how crucial data was in order to run large orchid greenhouses. He saw HiPerGreen’s monitoring solutions such as the drone and the rail system as the answers to current data gaps. Mauro Gallo, lector Biomimicry at InHolland, announced HiPerGreens follow up project Flapping Wings. The symposium’s final speaker was William Simmonds, CEO of Applied Drone Innovations , a spinoff startup born from the HiPerGreen programme. The symposium was concluded with a drink.
DOCUMENT
Hoofdstuk 15 15.1 Introduction 15.2 An international law perspective 15.3 The American position 15.4 International human rights developments 15.5 Effective remedy and reparations 15.6 Reflections References In the international arena there are some encouraging developments in relation to accountability and transparency for the use of armed drones. It is increasingly recognized that remote pilotless aircraft have become part of modern warfare, and that sometimes they are also used outside the context of armed conflict. Subsequently, both international humanitarian and human rights law can apply. The issue of access to justice, however, receives less explicit socio-political attention. Victims of armed remote pilotless aircraft strikes meet countless challenges in effectuating their right to an effective remedy. Often even a formal recognition that a strike has taken place is lacking. Furthermore, the states involved fail to publicly release information about their own investigations. This makes it difficult for those affected to substantiate their status as a victim and seek justice, including reparations. The international community should, in addition to urging involved states to independently and impartially investigate all armed drone strikes, ensure that access to an effective remedy for civilian victims, whether on an international, transnational or national level, becomes a reality.
LINK
Friday 23rd March 2018 the first HiPerGreen semi-annual symposium took place at the newly opened World Horti Center in Naaldwijk. Participants in the form of students, professors and company representatives came together to share progress and ideas. Cock Heemskerk, lector Robotica, opened the event with a welcoming speech. Lucien Fesselet, assistant project manager, followed with general updates on the project. Then the floor was given to the students to present their results and progress. Pieter van der Hoeven, associate lector, presented on behalf of four graduating students from the Business, Finance and Law department the assignment on market research. The findings show great potential in business opportunity with the Orchid market. Amora Amir, a potential PhD researcher on big data, gave a speech on the usefulness and the need to understand big amounts of data. Lucien Fesselet performed a live flight demonstration to give an idea of the capabilities and the behaviour of the drone. After the risk analasys the sympoium was concluded with a drink.
DOCUMENT
Currently, published risk analyses for drones refer mainly to commercial systems, use data from civil aviation, and are based on probabilistic approaches without suggesting an inclusive list of hazards and respective requirements. Within this context, this paper presents: (1) a set of safety requirements generated from the application of the Systems Theoretic Process Analysis (STPA) technique on a generic small drone system; (2) a gap analysis between the set of safety requirements and the ones met by 19 popular drone models; (3) the extent of the differences between those models, their manufacturers, and the countries of origin; (4) the association of drone prices with the extent they meet the requirements derived by STPA. The application of STPA resulted in 70 safety requirements distributed across the authority, manufacturer, end user, and drone automation levels. A gap analysis showed high dissimilarities regarding the extent to which the 19 drones meet the same safety requirements. Statistical results suggested a positive correlation between drone prices and the extent that the 19 drones studied herein met the safety requirements generated by STPA, and significant differences were identified among the manufacturers. This work complements the existing risk assessment frameworks for small drones, and contributes to the establishment of a commonly endorsed international risk analysis framework. Such a framework will support the development of a holistic and methodologically justified standardization scheme for small drone flights.
DOCUMENT
Students, researchers, professors and company representatives gathered to share progress and ideas at the second half-year symposium of HiPerGreen at the World Horti Center in Naaldwijk. HiPerGreen is a Raak MKB subsidised research project aiming to bring value to horticultural growers. Cock Heemskerk, head of the HiPerGreen project and lector Robotica at InHolland University of Applied Sciences, welcomed everyone and gave an overall status update. Then Lucien, Fesselet project manager at HiPerGreen, talked about the minimal viable product (MVP) to make automated detection of fusarium in Phalaenopsis (a type of orchid) possible. Three consortium partners were invited to explain what they do for HiPerGreen and what their motives for participation are: Igno Breukers (DB2-Vision, start-up of a new type of multispectral camera for Precision Agriculture), Tim Brander (head grower at Hazeu Orchids) and Tom Kearny-Mitchel (plant biology advisor at Applied Drone Innovations). Next several students summarised their team’s work, findings and failures to the audience. During the live demo Lucien unveiled one of the team’s newly-built technologies: live stream thermal images of plants. The sympoium was concluded with a brainstorm session and drink.
DOCUMENT
The remarkable and continuous growth of the unmanned aircraft market has brought new safety related challenges, as those are recorded in various accident and incident reports. Although drones with an operating weight higher than 20-25Kgs are technologically advanced and often subject to standards (e.g., technical reliability, airspace management, licensing, certification), the regulatory framework for (ultra) light drones focuses almost exclusively on the limitations that the operator needs to consider. Thus, the protection from accidents seems to rely mostly on the competency of the operator to fly a drone safely, and his/her observance of the rules published by the respective authorities. In addition, the hazards lying in the interaction between an operator and a small drone have not been systematically studied. In this paper, we present (1) the first results from a System-Theoretic Process Analysis (STPA) based approach to the identification of hazards and safety requirements in small drone operations, and (2) an adaptation of the Risk Situation Awareness Provision Capability (RiskSOAP) methodology in order to quantify the differences amongst 4 drone models regarding the extent to which they fulfill the safety requirements identified through STPA. The results showed that the drones studied satisfy the safety requirements at low and moderate levels and they present high dissimilarities between them regarding the extent to which they meet the same safety requirements. Future work will include: (a) comparison of a larger sample of small drones against the safety requirements, as well as pairwise, and (b) assessment of the degree to which various regulatory frameworks worldwide address the safety requirements generated with STPA and assigned to the authority level.
DOCUMENT
The continuous increase of accident and incident reports has indicated the potential of drones to threaten public safety. The published regulatory framework for small drones is not visibly based on a comprehensive hazard analysis. Also, a variety in the constraints imposed by different regulatory frameworks across the globe might impede market growth and render small-drone operations even more complicated since light drones might be easily transferred and operated in various regions with diverse restrictions. In our study we applied the Systems-Theoretic Process Analysis (STPA) method to small-drone operations and we generated a first set of Safety Requirements (SR) for the authority, manufacturer, end-user and automation levels. Under the scope of this paper, we reviewed 56 drone regulations published by different authorities, and performed (1) a gap analysis against the 57 SRs derived by STPA for the authority level, and (2) Intra-Class Correlations in order to examine the extent of their harmonization. The results suggest that the regulations studied satisfy 5.3% to 66.7% of the SRs, and they are moderately similar. The harmonization is even lower when considering the range of values of various SRs addressed by the authorities. The findings from the drones’ case show that regulators might not similarly and completely address hazards introduced by new technology; such a condition might affect safety and impede the distribution and use of products in the international market. A timely and harmonized standardization based on a systematic hazard analysis seems crucial for tackling the challenges stemmed from technological advancements, especially the ones available to the public.
DOCUMENT
The decomposition of a body is influenced by burial conditions, making it crucial to understand the impact of different conditions for accurate grave detection. Geophysical techniques using drones have gained popularity in locating clandestine graves, offering non-invasive methods for detecting surface and subsurface irregularities. Ground-penetrating radar (GPR) is an effective technology for identifying potential grave locations without disturbance. This research aimed to prototype a drone system integrating GPR to assist in grave localization and to develop software for data management. Initial experiments compared GPR with other technologies, demonstrating its valuable applicability. It is suitable for various decomposition stages and soil types, although certain soil compositions have limitations. The research used the DJI M600 Pro drone and a drone-based GPR system enhanced by the real-time kinematic (RTK) global positioning system (GPS) for precision and autonomy. Tests with simulated graves and cadavers validated the system’s performance, evaluating optimal altitude, speed, and obstacle avoidance techniques. Furthermore, global and local planning algorithms ensured efficient and obstacle-free flight paths. The results highlighted the potential of the drone-based GPR system in locating clandestine graves while minimizing disturbance, contributing to the development of effective tools for forensic investigations and crime scene analysis.
MULTIFILE
