In the domain of extended object tracking, the tracker's output includes detailed extent information, which complicates the task of accurately measuring the distance between the estimated and actual ground truth. This complexity arises from the need to account for both the spatial extent and the dynamic interactions within groups of objects, such as drone swarms. To address this challenge, this paper introduces a measure designed to evaluate the performance of group tracking algorithms, suited to real world situations. The distance combines location error and group feature errors for a more comprehensive assessment of performances. We illustrate the behavior of the proposed distance on real data collected in an operationally controlled environment. For illustration purposes, we compare two state-of-the-art approaches in their ability to accurately track a drone swarm in a real world situation with bird flights. We also propose a spatial sampling version of the classical OSPA metric as a baseline for comparison. The results show that the proposed distance better captures the trackers' efficiency and enables an easier interpretation of their behavior. We conclude on future work which includes studying properties of the distance in a simulation controlled environment.

In urban drone surveillance, conventional anomaly detection methods often falter amid unstable data and high noise levels. We propose a Sim2Real approach within a ValuationBased System framework that integrates expert knowledge into its model structure. Our method involves two phases: training on simulated drone trajectories to learn behavioral dependencies with probabilities, using a Dynamic Bayesian Network, and performing inference via an evidential network for explicit uncertainty modeling. The incorporation of expert-driven structural insights enhances the transfer of simulation-trained parameters to real-world conditions. Real-world tests with actual flight data demonstrate that our approach outperforms traditional techniques in detection accuracy and recall, robustly handling sensor noise and incomplete information.

Evaluating information fusion algorithms and systems is instrumental to the proper prediction of error, to the rational improvement of solutions and in fine to the acceptance of solutions by end-users. Performance criteria define general semantics for a desirable behavior of the systems, while corresponding metrics implement that semantics for computable quality. Evaluation of the first levels of the JDL model of data fusion (detection and individual object assessment) is classically measured with objective and more or less standardized metrics. Evaluation of higher levels of processing such as situation assessment is less formalized as the evaluation criteria seat somewhere between the tactical picture quality and the decision-maker situation awareness. In this paper, we propose a formalization of the situation assessment problem, which bridges level 1 and 2 of the JDL model. Secondly, we define a global measure of quality encompassing the criteria of completeness, accuracy, clarity, which can be applied to both level 1 and level 2. We illustrate the metrics on a Counter-Unmanned-Aerial System (CUAS) scenario, comparing two uncertainty handling methods for a threat assessment solution through a Dynamic Bayesian Network. We finally conclude and sketch ideas for future steps of this research.

Countering unmanned aerial threats is critical for both military and civilian surveillance and protection systems. The complementarity and redundancy of sensors enables detecting, tracking and classifying Unmanned Aerial Vehicles (UAVs), further assessing their possible threat and planning the proper counter-measure. Despite efforts to develop dedicated systems (sensors, processing, hard and soft kill systems), Counter Unmanned Aerial Systems (CUAS) are often deployed in complex civilian areas, which requires an adequate understanding of the situation including the UAVs behavior for an appropriate response. The evaluation of a CUAS should thus consider not only its ability to provide a tactical picture of sufficient quality, but also its ability to provide semantic information, to establish possible links between objects and to contextualize their behavior. In this paper, we set up the basics for an evaluation platform covering the lower levels but also higher levels of the JDL (Joint Directors of Laboratories) functional model of information fusion. We consider the six classical criteria of a tactical picture (used in Level 1) and extend them to higher level tasks. Evaluation criteria are aligned with the URREF (Uncertainty Representation and Reasoning Evaluation Framework) ontology evaluation criteria. Furthermore, we propose some metrics to quantity such evaluation criteria. The framework is illustrated in a CUAS scenario, with data provided by the LEXLUTOR platform. Several fusion solutions are compared which differ in the way uncertainty is represented, handled and provided to the user.

Multiple ground targets tracking with a GMTI (ground moving target indicator) sensor is considered a challenging problem in order to establish battlefield assessment. An IMM algorithm with a variable structure is adapted to the road network and used to track multiple manoeuvring ground targets. However, the case of undetected targets due to terrain elevation or Doppler obscuration was not taken into account in our tracking process. In this paper, we present our approach to track ground targets with the possibility for the target to be undetected. The perceivability probability is computed to update the estimated state and a "sentinel" concept is used to palliate the association ambiguities when several targets enter and exit the same terrain mask.