Blind and Visually impaired people (BVIP) face a range of practical difficulties when undertaking outdoor journeys as pedestrians. Over the past decade, a variety of assistive devices have been researched and developed to help BVIP navigate more safely and independently. In addition, research in overlapping domains are addressing the problem of automatic environment interpretation using computer vision and machine learning, particularly deep learning, approaches. Our aim in this article is to present a comprehensive review of research directly in, or relevant to, assistive outdoor navigation for BVIP. We breakdown the navigation area into a series of navigation phases and tasks. We then use this structure for our systematic review of research, analysing articles, methods, datasets and current limitations by task. We also provide an overview of commercial and non-commercial navigation applications targeted at BVIP. Our review contributes to the body of knowledge by providing a comprehensive, structured analysis of work in the domain, including the state of the art, and guidance on future directions. It will support both researchers and other stakeholders in the domain to establish an informed view of research progress.
Outdoor navigation remains a challenging activity for people with visual impairment. Having examined the current literature, we conclude that there are very few publications providing a nuanced understanding of how PBVI undertake a journey in an outdoor environment and what their main challenges and obstacles are. This is a critical step towards developing robust solutions that meet the requirements of this user group. We undertook a questionnaire-based study with the National Council for the Blind of Ireland (NCBI) and 49 UBVI. According to the feedback from our questionnaire, current journey navigation apps do not provide sufficient information about traffic lights, crossroads, and physical obstacles to support satisfactory interaction. Our study reveals key aspects of how UBVI interact with outdoor navigation applications. Critical gaps exist, with over 63% of respondents indicating they had suffered an injury on at least one previous occasion when navigating outdoors. Based on the questionnaire feedback, we present a solution covering the main aspects of outdoor navigation for UBVI. Our work aims to contribute to the improvement of interaction between UBVI and outdoor navigation applications in the future.
23 March 2026 in Journal of Online Trust and Safety
Video-sharing platforms such as TikTok, YouTube, and Instagram implement content moderation policies to reduce the exposure of minors to harmful videos. As video has become the dominant and most immersive form of online content, assessing how effectively these systems protect younger users is increasingly important. This study evaluates the effectiveness of video moderation for different age groups on TikTok, YouTube, and Instagram, based on a focused set of experimental accounts. Accounts were created for simulated users aged 13 and 18, and 3,000 recommended videos were analyzed in two interaction modes: passive scrolling and search-based scrolling. Each video was manually assessed for the severity of the harm using a unified harm classification framework. While low-severity harm was the most prevalent form encountered, the results show that accounts configured as 13-year-olds encountered harmful videos more frequently and rapidly than accounts configured as 18-year-olds. On YouTube, 15% of videos recommended to 13-year-old accounts during passive scrolling were classified as harmful, compared to 8.17% for adult accounts, with exposure occurring within an average of 3:06 minutes. This exposure appeared without user-initiated searches, highlighting weaknesses in algorithmic filtering. Results from our targeted study point to gaps in video moderation systems, suggesting the need for more effective safeguards to better protect minors from harmful online content.
Automatic detection of road intersections is an important task in various domains such as navigation, route planning, traffic prediction, and road network extraction. Road intersections range from simple three-way T-junctions to complex large-scale junctions with many branches. The location of intersections is an important consideration for vulnerable road users such as People with Blindness or Visually Impairment (PBVI) or children. Route planning applications, however, do not give information about the location of intersections as this information is not available at scale. As a first step to solving this problem, a mechanism for automatically mapping road intersection locations is required, ideally using a globally available data source. In this paper, we propose a deep learning framework to automatically detect the location of intersections from satellite images using convolutional neural networks. For this purpose, we labelled 7,342 Google maps images from Washington, DC, USA to create a dataset. This dataset covers a region of 58.98 km2 and has 7,548 intersections. We then applied a recent object detection model (EfficientDet) to detect the location of intersections. Experiments based on the road network in Washington, DC, show that the accuracy of our model is within 5 meters for 88.6% of the predicted intersections. Most of our predicted centre of the intersections (approx 80%) are within 2 metres of the ground truth centre. Using hybrid images, we obtained an average recall and an average precision of 76.5% and 82.8% respectively, computed for values of Intersection Over Union (IOU) from 0.5 to 0.95, step 0.05. We have published an automation script to enable the reproduction of our dataset for other researchers.
Today, the number of users of social network increases and a lot of users share opinions on different aspects of life every day. So the rate of colloquial written text increases dramatically as a medium of expressing ideas especially across the WWW. Therefore, social networks are rich sources of data for opinion mining and sentiment analysis. Arab colloquial dialects are languages that people used to communicate with each other in social networks. Recently, there is a massive amount of Arab colloquial data on Social networks. By increasing the available data, the needing for processing this data and using it is increased. However, most available tools and resources (morphological analyzers, disambiguation systems, annotated data, and parallel corpora) are for Modern Standard Arabic (MSA). Therefore, the need for the automatic transformation from Arab colloquial dialects to Modern Standard Arabic becomes urgent to use Modern Standard Arabic tools and resources for Arab colloquial dialects. The most famous colloquial is Egyptian colloquial dialect, which is considered the most widely used and understood dialect throughout the Arab world. Consequently, the focus of the proposed system is the Egyptian colloquial dialect to prove our approach.
In this paper, the problem of scrambling code (SC) planning and optimization in 3G networks is addressed. Scrambling Codes are used to identify and distinguish cells from one another in WCDMA networks. These SCs are reported by the mobile users to the network to declare which cells they are able to connect to. Under the limitation of available SCs to be assigned to the cells we propose various allocation schemes that assign the scrambling codes according to the planner needs. In addition, a detection algorithm of SC clashes1 has been developed and the recommended assignment is then proposed to decrease the overall interference. Our results were applied to a live WCDMA cellular network and the achieved performance benefit is presented.