Sara Baldoni

Accurate train positioning is crucial for ensuring the safety and operational efficiency of intelligent railway systems. Traditional Global Navigation Satellite System (GNSS) and Inertial Navigation System (INS) integration often performs reliably only under ideal conditions. However, in GNSS-denied environments such as tunnels, signal blockage can cause significant positioning errors. To overcome these limitations, this paper proposes a seamless train positioning framework that dynamically switches between Visual Place Recognition (VPR) /INS and GNSS/INS integration. The framework operates adaptively: in tunnel or signal-denied scenarios, where GNSS is unavailable, VPR/INS integration maintains accurate localization; in open-sky environments, GNSS/INS integration ensures continuous positioning. To enable VPR-based localization, a reference image database of the railway line is pre-constructed, and the NetVLAD model is employed to extract robust global image descriptors. A location-guided image retrieval strategy is then introduced to accelerate global feature matching, providing a coarse estimation of the train’s position based on retrieval results. To ensure the accuracy of the matching process, we have implemented a double-check mechanism that accepts matching results only when validated, thereby enhancing overall railway positioning safety. Field experiments conducted on the Lhasa–Nyingchi Railway show that during GNSS signal blockage, the proposed switching system effectively reduces positioning errors, achieving an overall RMS error of approximately 1.03m.

Saliency estimation has received growing attention in recent years due to its importance in a wide range of applications. In the context of 360-degree video, it has been particularly valuable for tasks such as viewport prediction and immersive content optimization. In this paper, we propose SalFormer360, a novel saliency estimation model for 360-degree videos built on a transformer-based architecture. Our approach is based on the combination of an existing encoder architecture, SegFormer, and a custom decoder. The SegFormer model was originally developed for 2D segmentation tasks, and it has been fine-tuned to adapt it to 360-degree content. To further enhance prediction accuracy in our model, we incorporated a viewing center bias to reflect user attention in 360-degree environments. Extensive experiments on the three largest benchmark datasets for saliency estimation demonstrate that SalFormer360 outperforms existing state-of-the-art methods. In terms of Pearson correlation coefficient, our model achieves 8.4% higher performance on Sport360, 2.5% on PVS-HM, and 18.6% on VR-EyeTracking compared to previous state-of-the-art.

Saliency estimation has received growing attention in recent years due to its importance in a wide range of applications. In the context of 360-degree video, it has been particularly valuable for tasks such as viewport prediction and immersive content optimization. In this paper, we propose SalFormer360, a novel saliency estimation model for 360-degree videos built on a transformer-based architecture. Our approach is based on the combination of an existing encoder architecture, SegFormer, and a custom decoder. The SegFormer model was originally developed for 2D segmentation tasks, and it has been fine-tuned to adapt it to 360-degree content. To further enhance prediction accuracy in our model, we incorporated Viewing Center Bias to reflect user attention in 360-degree environments. Extensive experiments on the three largest benchmark datasets for saliency estimation demonstrate that SalFormer360 outperforms existing state-of-the-art methods. In terms of Pearson Correlation Coefficient, our model achieves 8.4% higher performance on Sport360, 2.5% on PVS-HM, and 18.6% on VR-EyeTracking compared to previous state-of-the-art.

The evaluation of the quality perceived by a user when experiencing extended reality is a multifaceted challenge. Studies in the state-of-the-art show that it depends on several factors such as user comfort, level of immersivity, cognitive load, and content quality. In addition, extended reality systems are moving towards the realization of collaborative and multi-user applications. In this scenario, additional aspects should be taken into account such as the social presence and the quality of interaction. Currently, to the best of our knowledge, the literature lacks common practices or standards for designing experimental tests that encompass all these aspects. In this work, we aim at providing practical guidelines for assessing the quality of experience in multi-user applications. Therefore, we focus on a flexible task that can be applied to many extended reality technologies. We provide a thorough set of technological scenarios for the application of the proposed methodology and we compare the perceived quality of experience in different technological settings by analyzing the results of a multi-lab subjective study.