A5038657204- Indoor and Outdoor Localization Technologies
- Autonomous Vehicle Technology and Safety
- Railway Engineering and Dynamics
- GNSS positioning and interference
- Image Enhancement Techniques
- Image Processing Techniques and Applications
- Robotics and Sensor-Based Localization
- Advanced Vision and Imaging
- Visual Attention and Saliency Detection
- Image and Object Detection Techniques
- Advanced Image Processing Techniques
- Vehicle License Plate Recognition
- Infrastructure Maintenance and Monitoring
- Inertial Sensor and Navigation
- Image and Video Quality Assessment
- Railway Systems and Energy Efficiency
- Virtual Reality Applications and Impacts
- Geological Modeling and Analysis
- Advanced Steganography and Watermarking Techniques
- Visual perception and processing mechanisms
- Radio Wave Propagation Studies
- Augmented Reality Applications
- Advanced Optical Sensing Technologies
- 3D Modeling in Geospatial Applications
- Advanced Fluorescence Microscopy Techniques
Roma Tre University
2017-2024
University of Padua
2021-2022
Nantes Université
2019
Université Sorbonne Paris Nord
2019
Radiolabs
2019
This paper presents the results of depth estimation challenge for dense light fields, which took place at second workshop on Light Fields Computer Vision (LF4CV) in conjunction with CVPR 2017. The consisted submission to a recent benchmark [7], allows thorough performance analysis. While individual are readily available web page http://www.lightfield-analysis.net, we take this opportunity give detailed overview current participants. Based algorithms submitted our challenge, develop taxonomy...
The transport sector is experiencing a fast and revolutionary development, moving toward the deployment of autonomous vehicles. Thus, accuracy position information integrity navigation system have become key factors. In this article, we address problem enhancement provided by global satellite receiver exploiting sensor fusion. To aim, estimate lateral offset heading vehicle with respect to georeferenced roadway centerline from images supplied an on-board camera. Moreover, perform monitoring...
With the development of advanced driver assistance systems (ADAS) and autonomous vehicles (AV), recent years have seen an increasing evolution onboard sensors communication interfaces capable interacting with available infrastructures, including satellite constellations, road structures, modern heterogeneous network (e.g., 5G beyond) even adjacent vehicles. Consequently, it is essential to develop architectures that cover data fusion (multi–sensor approach), communication, power management,...
The objective of this work is to evaluate the feasibility integration visual sensors in framework GNSS-based vehicle localization systems. Undoubtedly GNSS plays a key role localization. However, impact faults (e.g. satellite and constellation failure), signal degradation ionospheric scintillations, multipath) external threats jamming spoofing) need be taken into account. To address issue, we propose three-level based on use additional sensors. Thanks input, inaccurate measurements are...
Detection of multipath feared events is a fundamental capability current and future High Accuracy Integrity positioning systems for rail transport based on Global Navigation Satellite Systems. In this work, method cascade barriers proposed Signal Space measurement selection integrity monitoring. To aim, mathematical framework the analytic assessment achievable performance Fault Exclusion algorithms Solution Separation defined, accounting impact that exclusion observable has PVT accuracy...
A novel technique for building a detailed Digital Map of the rail environment has been implemented and tested. It is based on fusion multiple rides acquired by means on-board GNSS receivers, IMUs visual sensors from trains in commercial operation. More detail, an efficient incremental procedure processing collected data to reduce computational complexity storage requirements proposed. We demonstrate that proposed system able obtain accurate track geometry trackside objects position...
In this work, we propose the use of velocity directly derived from Global Navigation Satellite System observables in safety-critical applications. particular, extend Solution Separation method originally introduced for positioning to estimated starting carrier phases. Exploiting phases temporal differences as done here removes need ambiguity fixing, but hazards caused by cycle slips remain. Therefore, specific barriers (cycle slip detectors) and robust methods like one, providing also...
The objective of this work was to explore the subjective quality assessment dynamic point clouds with compression artifacts and analyze exploration behavior users while visualizing them a Head-Mounted Display 6 Degrees-of-Freedom. Thus, paper presents study on using Absolute Category Rating methodology considering different rates MPEG standard Video-based Point Cloud Compression. Firstly, results impact perceived Quality Experience are reported, showing validity Rating, although more than 20...
The upcoming transport revolution is dramatically increasing the navigation integrity requirements. However, traditional techniques for improving of position information are usually based on use a high number satellite signals. We propose to add an external source on-board visual sensors. Shift and rotation vehicle estimated from vanishing point road markings, exploited define virtual track its motion. GNSS-only solution then compared one constrained track, check performed threshold....
In this contribution, a watermarking system for omni-directional images is presented. To cope with the peculiarities of media, an ad-hoc technique has been designed. particular, since users can only view small portion 360° images, viewport, procedure designed allowing extraction watermark even from single viewport. way it possible to protect ownership content if viewport illegally distributed. The experimental results show that proposed robust against several kinds attacks, outperforming...
This paper explores the use of Global Navigation Satellite System (GNSS) integrity monitoring techniques into Collaborative RTK systems. (C-RTK) leverages data from multiple GNSS receivers to improve accuracy and robustness positioning solutions. By enhancing this collaborative approach with monitoring, we aim mitigate impact errors anomalies in signals, thus reliability safety applications that depend on high-precision urban scenarios.
The COVID pandemic in 2020 caused an unpredictable disruption to maritime transportation, affecting the smooth operating of global supply chains. To make this transport sector more resilient a key enabling factor is introduction novel smart systems both on port and ship side. This contribution addresses topic. Specifically, it introduces GNSS Digital Beamforming Platform (DBP) for Assisted Berthing System that exploits satellite signals support officers during docking undocking manoeuvre. In...
One of the major challenges in design high accuracy, integrity localization procedures for rail applications based on Global Navigation Satellite Systems is represented by local hazards that cannot be mitigated resorting to augmentation networks. By fact, combining smoothed code pseudoranges with (differential) carrier phase and/or Inertial Measurement Unit's outputs ineffective against multipath low frequency components. These issues can processing images, depth maps pointclouds provided...
Light field imaging is increasingly spreading and its applications are reaching a larger number of users. The quality the rendered content as perceived by viewers key factor for future development this technology. Many factors can cause degradation Field quality, from data acquisition/creation to final rendering. To increase content, usually performed 2D 3D processing techniques be applied. In work, an approach enhancing videos presented. proposed based on characteristics human visual system...
Light Field imaging systems allow capturing a larger amount of information scene with respect to conventional cameras. In fact, light field cameras record, in single shot, multiple instances the same taken from slightly different points view. This enables new applications, like digital refocusing and free-viewpoint content creation. The main drawback this hardware is trade-off between spatial angular resolution, which has an impact on depth refocused images. paper we propose technique for...
Recently, multi-sensor localization strategies are gaining attention in the railway scenario. In fact, current trend is to reduce or remove physical equipment deployed along track for positioning purposes and exploit on-board sensors realize same functionalities. Although GNSS one of major resources perform this task, its performances dramatically decrease presence sources local hazards like multipath, shadowing blockage. For reason, methods under study. Among them, those based on detection...
Over the last few years applications based on use of immersive environments, where physical and digital objects coexist interact, have gained widespread attention. Thanks to development new visualization devices, even at low cost, increasingly effective rendering processing techniques, these are reaching a growing number users. While adoption information makes it possible provide experiences in different applications, there still many unexplored aspects. In this work, preliminary step...
Traditional image and video enhancement techniques do not consider the subjective preferences of user, who might be interested in modifying or highlighting specific elements a scene. In fact, most post-processing are applied to entire frame. this work, framework for selective is presented. It based on an adaptive multi-resolution edge technique performed Laguerre–Gauss complex wavelet domain. proposed scheme, edges selectively enhanced attenuated according inputs taking into account...
A Digital Map of the rail infrastructure in a key element to support adoption GNSS railway signalling and satisfy strict accuracy integrity requirements even presence feared events that may hinder positioning solution. In this work, we tackle issue providing an accurate for localization purposes, bridging gaps produced by loss Global Navigation Satellite System (GNSS) coverage using forward backward post-processing inertial navigation. Experimental results show proposed method is able...