The explosion of online video streaming in recent years resulted in advanced services both in terms of efficiency and convenience. However, Internet-connected video cameras are prone to exploitation, ...leading to information security issues and data privacy concerns. The proliferation of video-capable Internet of Things devices and cloud-managed surveillance systems further extend these security issues and concerns. In this paper, a novel approach is proposed for video camera deception via honeypots, offering increased security measures compared to what is available on conventional Internet-enabled video cameras.
In this paper, the task of combining recognition results from multiple images is considered. Systems in which such problems occur are analyzed, and some known approaches are described. It should be ...noted that currently there is no unified approach that could be used to solve the combination problem for increasing text recognition accuracy using multiple images or in a video stream. As an example, a comparative study of three different approaches to the combination of per-frame recognition results of identity document fields is presented, and it is demonstrated that different approaches may be advantageous for different parts of a data set, while a selection of the potential best single result still significantly outperforms all of the analyzed methods. The task of the per-frame combination of recognition results is an important component in video stream recognition systems and requires careful consideration and the formulation of general approaches that would be applicable to various domains.
In Mobile Edge Computing (MEC), the collaboration between end devices and servers guarantees the low-latency and high-accuracy video stream analysis. However, such paradigm of video stream offloading ...poses a serious threat to the location privacy and the usage pattern privacy of end devices. The existing works offer strict privacy guarantee for users, but they do not take the features of video stream into consideration, thus leading to the relatively higher computation cost. To tackle this issue, we propose a personalized and differential privacy-aware video stream offloading scheme that supports users personalized and time-varying privacy requirements, provides corresponding differential privacy preservation, and generates minimal latency and energy cost. Specifically, we formulate an NP-hard optimization that jointly optimizes the video frame rate, frame resolution and offloading ratio to maximize the analysis accuracy of video stream and minimize the energy cost and the latency subject to the channel bandwidth, computing resources, and personalized and time-varying privacy requirements. Then, we design a online learning-based and personalized privacy-aware video stream offloading algorithm for the optimization problem and thereby obtain the optimal video stream offloading scheme. Last, the extensive experimental results validate the superior performance of the proposed scheme, compared to the three latest existing works.
It is common practice for unmanned aerial vehicle (UAV) flight planning to target an entire area surrounding a single rooftop’s photovoltaic panels while investigating solar-powered roofs that ...account for only 1% of the urban roof area. It is very hard for the pre-flight route setting of the autopilot for a specific area (not for a single rooftop) to capture still images with high overlapping rates of a single rooftop’s photovoltaic panels. This causes serious unnecessary data redundancy by including the surrounding area because the UAV is unable to focus on the photovoltaic panel installed on the single rooftop. The aim of this research was to examine the suitability of a UAV video stream for building 3-D ortho-mosaics focused on a single rooftop and containing the azimuth, aspect, and tilts of photovoltaic panels. The 3-D position accuracy of the video stream-based ortho-mosaic has been shown to be similar to that of the autopilot-based ortho-photo by satisfying the mapping accuracy of the American Society for Photogrammetry and Remote Sensing (ASPRS): 3-D coordinates (0.028 m) in 1:217 mapping scale. It is anticipated that this research output could be used as a valuable reference in employing video stream-based ortho-mosaics for widely scattered single rooftop solar panels in urban settings.
In recent years, crowdsourced livecast has seen remarkable progress due to the interactivity and real-time nature, playing an essential role in multimedia applications in the post-epidemic era. Given ...the delay sensitivity, large viewing volumes, and heterogeneous viewing patterns, the traditional video streaming methods fail to provide the optimized Quality of Experience (QoE) for viewers using the minimum system cost over an edge-assisted service architecture. The emerging technology of mobile edge computing (MEC) offers a new perspective of reducing user latency and enhancing the quality of dispatched videos in a promising way. In this article, we propose Proffler , an integrated framework that addresses this problem through effective stream caching at the network edge server. We first examine the underlying correlations in viewing patterns across different regions and propose a novel transformer-based algorithm, Chili-TF, that achieves accurate viewer request prediction, even for regions with insufficient data. We then design a scalable algorithm, U2VR, that achieves near-optimal video stream allocation as well as viewer scheduling. Extensive real-data-driven experiments further confirm that Proffler can achieve improvements of 20%–55% in average QoE compared to state-of-the-art solutions.
Accurate traffic simulation models play a crucial role in developing intelligent transport systems that offer timely traffic information to users and efficient traffic management. However, ...calibrating these models to represent real-world traffic conditions accurately poses a significant challenge due to the dynamic nature of traffic flow and the limitations of traditional calibration methods. This article introduces a machine learning-based approach to calibrate macroscopic traffic simulation models using real-time traffic video stream data. The proposed method for creating and calibrating a traffic simulation model has significantly improved the statistical correspondence between the generated vehicle characteristics and real data about cars on the simulated road section. The correspondence has increased from 37% to 73%. Machine learning models trained on generated data and tested on real data show improved accuracy rates. Mean absolute error, mean square error, and mean absolute percentage error decreased by more than two orders of magnitude. The coefficient of determination has also increased, approaching 1. This method eliminates the need to deploy wireless sensor networks, which can reduce the cost of implementing intelligent transport systems.
To illustrate a new technological advance in the standard drug-induced sleep endoscopy (DISE) model, a new machine was used, the Experimental 5 Video Stream System (5VsEs), which is capable of ...simultaneously visualizing all the decisional parameters on a single monitor, and recording and storing them in a single uneditable video. The DISE procedure was performed on 48 obstructive sleep apnea (OSA) or snoring patients. The parameters simultaneously recorded on a single monitor are (1) the pharmacokinetics and pharmacodynamics of propofol (through the target controlled infusion (TCI) pump monitor), (2) the endoscopic upper airway view, (3) the polygraphic pattern, and (4) the level of sedation (through the bispectral index (BIS) value). In parallel to the BIS recording, the middle latency auditory evoked potential (MLAEP) was also recorded and provided. Recorded videos from the 5VsEs machine were re-evaluated six months later by the same clinician and a second clinician to evaluate the concordance of the therapeutic indications between the two. After the six-month period, the same operator confirmed all their clinical decisions for 45 out of 48 videos. Three videos were no longer evaluable for technical reasons, so were excluded from further analysis. The comparison between the two operators showed a complete adherence in 98% of cases. The 5VsEs machine provides a multiparametric evaluation setting, defined as an “all in one glance” strategy, which allows a faster and more effective interpretation of all the simultaneous parameters during the DISE procedure, improving the diagnostic accuracy, and providing a more accurate post-analysis, as well as legal and research advantages.
Smart cities will be significantly shaped by their modes of mobility. For the blend of public and individual transport, smart mobility will introduce autonomous vehicles on a large scale, which often ...heavily rely on communication. As the capabilities of autonomous vehicles are still limited nowadays, driver-less vehicles have to be able to be remotely monitored and controlled in real-time. This creates high performance demands for the vehicle's communication link, especially regarding latency and uplink, which can easily exceed the limits of communication standards like Long Term Evolution (LTE). Therefore, the development of the communication system for the newly developed autonomous monorail vehicle MONOCAB aims towards the use of the 5G standard. This paper presents experiences and measurements from a first outdoor field test conducted in the context of monitoring and remotely controlling the MONOCAB via 5G. Previously, all communication services were subjected to ITU-T Y.1564 compliant tests for the network planning and the deployment of a 5G Non-Public Network (NPN). This deployed 5G NPN was then used to test remote monitoring the MONOCAB, at it's first public presentation on the 3rd of October 2022, by transmitting video streams and telemetry data from the vehicle to a central control station. Additionally, a glass-to-glass latency measurement of a video stream transmitted via 5G was conducted, to point out the latency impact of 5G.