Professional swimming coaches make use of videos to evaluate their athletes’ performances. Specifically, the videos are manually analyzed in order to observe the movements of all parts of the swimmer’s body during the exercise and to give indications for improving swimming technique. This operation is time-consuming, laborious and error prone. In recent years, alternative technologies have been introduced in the literature, but they still have severe limitations that make their correct and effective use impossible. In fact, the currently available techniques based on image analysis only apply to certain swimming styles; moreover, they are strongly influenced by disturbing elements (i.e., the presence of bubbles, splashes and reflections), resulting in poor measurement accuracy. The use of wearable sensors (accelerometers or photoplethysmographic sensors) or optical markers, although they can guarantee high reliability and accuracy, disturb the performance of the athletes, who tend to dislike these solutions. In this work we introduce swimmerNET, a new marker-less 2D swimmer pose estimation approach based on the combined use of computer vision algorithms and fully convolutional neural networks. By using a single 8 Mpixel wide-angle camera, the proposed system is able to estimate the pose of a swimmer during exercise while guaranteeing adequate measurement accuracy. The method has been successfully tested on several athletes (i.e., different physical characteristics and different swimming technique), obtaining an average error and a standard deviation (worst case scenario for the dataset analyzed) of approximately 1 mm and 10 mm, respectively.

The possibility of achieving real-time evaluation of human pose enables the ability to control robotic platforms based on user’s pose (or even on user’s inertial properties) in Human-In-The-Loop simulators, for sports and rehabilitation as an example. This study presents a vision-based, marker-less measurement system for real-time 3D human pose estimation. The system exploits pre-trained 2D human pose detection models and integrates an α-β-γ filter to reduce fluctuations in detected key points. It also introduces a novel Weighted Direct Linear Triangulation method, enhancing 3D reconstruction accuracy by assigning higher weights to key points consistent across current and previous frames. The method’s accuracy and execution time are assessed using the public Human3.6M dataset, evaluating different model configurations, formats, camera setups, and acquisition modes for real-time applications. The YOLOv8x-pose model with four cameras achieves the highest accuracy, with a Mean-Per-Joint Position Error of 18.2 mm and an execution time of 15 ms, outperforming state-of-the-art methods. Converting models to the TensorRT framework reduces execution time by 4.2 ms without significant accuracy loss. The system is integrated into a clinical rehabilitation device, a three-degree-of-freedom parallel kinematic machine, to facilitate patient participation in exergames. The proposed human-pose estimation method achieves real-time performance, enabling the motion platform to be controlled dynamically based on the patient’s actual standing pose.

Marine organisms have been observed ingesting microplastic particles, with field analyses indicating fibers and fragments as prevalent forms. Current microplastic detection methods are mainly time-consuming, susceptible to cross-contamination, and expensive. Furthermore, these techniques, being disruptive, do not allow for the exact localization of the microplastic in the sample. This study proposes a new approach using Computed Tomography (CT scan) and Artificial Intelligence for the automatic and non-destructive detection of microplastics in fishes and other species based on the combination of several factors, such as density and shape. The advantages of this methodology include accurate identification of plastic localization, a low risk of cross-contamination, rapid processing, automatic tomographic measurement, efficient data processing, cost-effectiveness, and a high cost-benefit ratio. The herein results highlight how artificial intelligence applied to conventional techniques can significantly improve precision and efficiency in microplastic research. Indeed, the semantic segmentation model clearly recognized the presence of 100 % of the plastic particles, both in their location and in their volume, accelerating the identification process and surpassing the limitations of traditional spectral analysis methodologies.

In the recent past, hyper-spectral imaging has found widespread application in forensic science, performing both geometric characterization of biological traces and trace classification by exploiting their spectral emission. Methods proposed in the literature for blood stain analysis have been shown to be effectively limited to collaborative surfaces. This proves to be restrictive in real-case scenarios. The problem of the substrate material and color is then still an open issue for blood stain analysis. This paper presents a novel method for blood spectra correction when contaminated by the influence of the substrate, exploiting a neural network-based approach. Blood stains hyper-spectral images deposited on 12 different substrates for 12 days at regular intervals were acquired via a hyper-spectral camera. The data collected were used to train and test the developed neural network model. Starting from the spectra of a blood stain deposited in a generic substrate, the algorithm at first recognizes whether it is blood or not, then allows to obtain the spectra that the same blood stain, at the same time, would have on a reference white substrate with a mean absolute percentage error of 1.11%. Uncertainty analysis has also been performed by comparing the ground truth reflectance spectra with the predicted ones by the neural model.