In the area of fluid mechanics, the validation of numerical or analytical models need to develop metrological tools for non-invasive global measurements with very high spatial or temporal resolution, even both if possible. These essential data are needed for two reasons: initialize the CFD codes and validate the numerical simulation models. Currently, there are only a few optical methods simultaneously having the ability to initialize and validate analytical and numerical models developed for the analysis of complex unsteady two-dimensional and three-dimensional phenomena. The only global methods identified now relate primary HS PIV (time-resolved PIV), BOS or CBOS and digital holographic interferometry. With one or more wavelengths. Some of these methods provide access to the field of instantaneous velocity obtained by image correlation, others provide the first derivative or the absolute value of the refractive index, which allows obtaining the field of instantaneous gas density. Of course, all these methods have their limitations which are mainly related to the quality and the coherence length of the laser sources used, the number of sensors and the pixel size of sensors used for recording, the flows studied which can have large velocity or gas density gradients and data processing softwares. The aim of the HONEFI 3D project is to extend one of the above methods, namely digital holographic interferometry for studying three-dimensional flows with high and low refractive index gradients such as those encountered in transonic, supersonic and hypersonic flows. For that, we propose to study on the one hand, the digital reconstruction of the diffracted field from recording of digital holographic interferograms, where the involvement of partner 2 (LAUM) and the other hand, to reconstruct the three-dimensional field of gas density from digital holographic interferograms recorded in several directions. This objective requires obtaining global information with a high temporal and spatial resolution according to the different viewing directions. The project’s objective is double because two types of three-dimensional flows are studied: the first flow case has a known 3D solution and the goal is to determine the optimal number of sight of view to reconstruct the 3D flow field with a good accuracy. The civil application is directly related to flow control and manipulation of boundary layers by jets. The second case concerns the 3D the 3D reconstruction of the supersonic flow around a missile equipped with a spike, application where the partner 3 (ISL) has equipment makes it possible to rotate the model and some results obtained by the technique of BOS (Back Oriented Schlieren). Again, the optimal number of view-sight will be determined to rebuild the 3D flow field.

The thermal accelerometer appears as a real technological breakthrough compared to traditional pendulum accelerometers which are very poorly suited to the high-level shock measurement and their resistance to harsh environments. Indeed, thanks to their architecture, thermal accelerometers are resistant to accelerations up to 50 000g (1g=9,8m/s-2). Besides the ability to survive these extreme environments, the sensor must also allow the measurement of this high level of acceleration with high bandwidth as we have begun to demonstrate with the preliminary results of the initial project. The main purpose of this study is to use the principle of thermal accelerometer to measure strong shock levels with a bandwidth from DC to more than 10 KHz. The use of microtechnologies will significantly reduce footprint and volume but also achieve competitive manufacturing costs. This technology allows us to measure both high acceleration or gravity in continuous operation. This would envisage dual applications both in civilian and defense fields. Indeed in the latter case, there would be applications for the measurement of strong deceleration levels on impact of the specimen in concrete target and then trace the movements with the ability to measure continuous acceleration . In the second case, these devices could be used as shock or vibration sensors in areas such as transport, aerospace, civil engineering or oil exploration, ... At present, there are only very few sensors operating in this range of accelerations having good stability and accuracy. The technology that is used most often is "piezo-resistive" and is North American. They are subject to strong export constraints (ITAR). It is essential to have a European technology or French in order to overcome a US dependency. It is by the way strategic for the defense industry. That is why the development of such a MEMS sensor (Micro Electro Mechanical System) based on the heat transfer would in itself a major innovation in this area.

The illegal or malicious use of unmanned aircrafts vehicles (UAVs) represents an emerging threat, which is only partially addressed by existing anti-intrusion systems. The DEEPLOMATICS project proposes an innovative and adaptive solution for the real-time identification and robust tracking of UAVs. The main objective is to address the problem of intrusion detection on critical sites and infrastructures, both in open spaces and in urban areas. The DEEPLOMATICS consortium proposes a new approach, entirely based on innovative Deep Learning techniques. This approach will allow a robust real-time identification and tracking of low-signature UAVs, thanks to the use of a multimodal and heterogeneous sensors connected to specialized artificial intelligences (AI). This interdisciplinary project jointly uses advanced localization techniques using scalable networks of microphone arrays, and an optronic active imaging system, each feeding specialized deep neural networks. Each independent smart acoustic devices consists in a compact digital MEMS microphone array, which achieve high directivity in a broadband frequency range. These smart microphone arrays will be complemented by an optronics active imaging system, which will also be connected to an independent AI. This modular and scalable approach will allow us to adapt the sensors topology to the protected sites. We aim at offering an autonomous system, by taking advantage of the convergence of acoustic signal processing, data sciences, and optronics. The proposed approach will simultaneously enable dynamic localization and automatic recognition of drones, while adapting to the measurement environment and to the topology of the heterogeneous on-site sensor network. The audio and video data will feed deep neural networks connected to each modules. Each AI will be pre-trained for UAV dynamic tracking and identification. Acoustic and optronic sensors do not operate in the same wavelength range, and they operate autonomously. Deep Learning acoustic strategies for target tracking will allow to identify the target and assess its position with a precise angular localization, over a wide coverage. The overall coverage area offered by this scalable network therefore only depends on the number of smart microphone arrays in the acoustic surveillance network. One of the proposed network topologies allows to cover a 1.7 km diameter surveillance zone. The optronics active imaging system has a narrow viewing angle and has a maximum operational range of 1.5 km. The computer vision methods associated to the active imaging system will allow estimating the targeted UAV distance, while tracking its trajectory in real time, after having locked onto the target thanks to the localization data transmitted by the acoustic network. Target recognition will also benefit from this multimodal and modular approach, thanks to the high contrast of the video feed obtained by active imaging, and the spatial filtering achieved by smart acoustic arrays. One advantage of this solution comes from the complementarity of the two localization modalities. Data fusion of video and audio artificial intelligences will exploit this complementarity in order to address most of intruding scenarios. Classical acoustic localization approaches, based on propagation models, can be replaced by Machine Learning methods. Our preliminary investigations reveal the superiority of the latter approach in a complex environment, even when the microphone array calibration is difficult. Deep learning approaches implicitly incorporate a robust self-calibration that automatically adapts the AI to the array specificities, even during the life of the on-site sensor. They also allow an automatic adaptation of the localization and identification algorithms to the protected site, and give access to array directivities that are not attainable with classical techniques, while being strongly robust to environmental noise.

The aim of the project proposed by Bertin Technologies, CEA and ISL is to develop a system to assist in the detection, recognition and identification of threats in the visible and infrared domains. The algorithm developed during this project is intended to be embedded in optronic systems used in the battlefield. It will therefore be subject to material and energy frugality constraints. The proposed approach will rely on artificial intelligence solutions based on deep neural networks. This technology is very promising for detection, recognition and identification applications. However, it requires supervised learning with a lot of annotated data representative of the usecases, which is difficult to obtain for military applications, as well as a high computing power during use. ISL, CEA and Bertin Technologies will bring their expertise to bear in data acquisition, AI training and optimisation, hardware integration and optronics to overcome the three technical hurdles of learning from a frugal dataset, joint exploitation of visible and infrared data, and frugality in computing power. A demonstration model based on Bertin Technologies' existing optronic solutions will be produced in order to validate the solution developed. This project is in line with French and European strategies to pursue research efforts in the field of AI, which has major economic and strategic implications. From a military point of view, it addresses strong tactical and operational challenges, in particular for surveillance, reconnaissance, identification and intelligence gathering applications. Embedded in optronic systems, artificial intelligence can facilitate the processing of information transmitted by sensors, limit the risks of human error, facilitate rapid decision-making and optimize the consumption of sensor batteries. Threat detection, recognition and identification functions are also of interest in civilian areas, particularly in the surveillance of sensitive areas (ports, borders) or industrial sites, as well as self driving cars.