Context. Observations of meteors in the Earth’s atmosphere offer a unique tool for determining the flux of meteoroids that are too small to be detected by direct telescopic observations. Although these objects are routinely observed from ground-based facilities, such as meteor and fireball networks, space-based instruments come with notable advantages and have the potential to achieve a broad and uniform exposure. Aims. In this paper, we describe the first observations of meteor events with Mini-EUSO, a very wide field-of-view telescope launched in August 2019 from the Baikonur cosmodrome and installed on board the Russian Zvezda module of the International Space Station. Mini-EUSO can map the night-time Earth in the near-UV range (290-130 nm) with a field of view equal to 44° × 44° and a spatial resolution of about 4.7 km at an altitude of 100 km from the ground. The detector saves triggered transient phenomena with a sampling frequency of 2.5 µs and 320 µs, as well as a continuous acquisition at 40.96 ms scale that is suitable for meteor observations. Methods. We designed two dedicated and complementary trigger methods, together with an analysis pipeline able to estimate the main physical parameters of the observed population of meteors, such as the duration, horizontal speed, azimuth, and absolute magnitude. To compute the absolute flux of meteors from Mini-EUSO observations, we implemented a simulation framework able to estimate the detection efficiency as a function of the meteor magnitude and the background illumination conditions. Results. The instrument detected 24 thousand meteors within the first 40 data-taking sessions from November 2019 to August 2021, for a total observation time of approximately 6 days with a limiting absolute magnitude of +6. Our estimation of the absolute flux density of meteoroids in the range of mass between 10⁻⁵ kg to 10⁻¹ kg was found to be comparable to other results available in the literature. Conclusions. The results of this work prove the potential for space-based observations to increase the statistics of meteor observations achievable with instruments operating on the ground. The slope of the mass distribution of meteoroids sampled with Mini-EUSO suggests a mass index of either s = 2.09 ± 0.02 or s = 2.31 ± 0.03, according to two different methodologies for the computation of the pre-atmospheric mass starting from the luminosity of each event.

In this article, we present cutting-edge machine learning-based techniques for the detection and reconstruction of meteors and space debris in the Mini-EUSO experiment, a detector installed on board of the International Space Station, and pointing toward the Earth. We base our approach on a recent technique, the STACKing method plus Convolutional Neural Network (STACK-CNN), originally developed as an online trigger in an orbiting remediation system to detect space debris. Our proposed method, the refined-STACKing method plus convolutional neural network (R-Stack-CNN), makes the STACKing method plus convolutional neural network (STACK-CNN) more robust, thanks to a random forest that learns the temporal development of these events in the camera. We prove the flexibility of our method by showing that it is sensitive to any space object that moves linearly in the field of view. First, we search small space debris, never observed by Mini-EUSO. Due to the limiting statistics, also in this case, no debris were found. However, since meteors produce signals similar to space debris but they are much more frequent, the R-Stack-CNN is adapted to identify such events while avoiding the numerous false positives of the Stack-CNN. Results from real data show that the R-Stack-CNN is able to find more meteors than a classical thresholding method and a new method of two neural networks. We also show that the method is also able to accurately reconstruct speed and direction of meteors with simulated data.

The detection of faint, fast-moving objects such as space debris, in optical data is a major challenge due to their low signal-to-background ratio and short visibility time. This work addresses this issue by implementing the Stack-CNN algorithm, originally designed for offline analysis, on an FPGA-based platform to enable real-time triggering capabilities in constrained space hardware environments. The Stack-CNN combines a stacking method to enhance the signal-to-noise ratio of moving objects across multiple frames with a lightweight convolutional neural network optimized for embedded inference. The FPGA implementation was developed using a Xilinx Zynq Ultrascale+ platform and achieves low-latency, power-efficient inference compatible with CubeSat systems. Performance was evaluated using both a physics-based simulation framework and data acquired during outdoor experimental campaigns. The trigger maintains high detection efficiency for 10 cm-class targets up to 30–40 km distance and reliably detects real satellite tracks with signal levels as low as 1% above background. These results validate the feasibility of on-board real-time debris detection using embedded AI, and demonstrate the robustness of the algorithm under realistic operational conditions. The study was conducted in the context of a broader technology demonstration project, called DISCARD, aimed at increasing space situational awareness capabilities on small platforms.

Space debris poses a significant threat, driving research into active and passive mitigation strategies. This work presents an innovative collision avoidance system utilizing event-based cameras - a novel imaging technology well-suited for Space Situational Awareness (SSA) and Space Traffic Management (STM). The system, employing a Stack-CNN algorithm (previously used for meteor detection), analyzes real-time event-based camera data to detect faint moving objects. Testing on terrestrial data demonstrates the algorithm's ability to enhance signal-to-noise ratio, offering a promising approach for on-board space imaging and improving STM/SSA operations.

The detection of faint, fast-moving objects such as space debris, in optical data is a major challenge due to their low signal-to-background ratio and short visibility time. This work addresses this issue by implementing the Stack-CNN algorithm, originally designed for offline analysis, on an FPGA-based platform to enable real-time triggering capabilities in constrained space hardware environments. The Stack-CNN combines a stacking method to enhance the signal-to-noise ratio of moving objects across multiple frames with a lightweight convolutional neural network optimized for embedded inference. The FPGA implementation was developed using a Xilinx Zynq Ultrascale+ platform and achieves low-latency, power-efficient inference compatible with CubeSat systems. Performance was evaluated using both a physics-based simulation framework and data acquired during outdoor experimental campaigns. The trigger maintains high detection efficiency for 10 cm-class targets up to 30-40 km distance and reliably detects real satellite tracks with signal levels as low as 1% above background. These results validate the feasibility of on-board real-time debris detection using embedded AI, and demonstrate the robustness of the algorithm under realistic operational conditions. The study was conducted in the context of a broader technology demonstration project, called DISCARD, aimed at increasing space situational awareness capabilities on small platforms.