Edge features in point clouds are prominent due to the capability of describing an abstract shape of a set of points. Point clouds obtained by 3D scanner devices are often immense in terms of size. Edges are essential features in large scale point clouds since they are capable of describing the shapes in down-sampled point clouds while maintaining the principal information. In this paper, we tackle challenges of edge detection tasks in 3D point clouds. To this end, we propose a novel technique to detect edges of point clouds based on a capsule network architecture. In this approach, we define the edge detection task of point clouds as a semantic segmentation problem. We built a classifier through the capsules to predict edge and non-edge points in 3D point clouds. We applied a weakly-supervised learning approach in order to improve the performance of our proposed method and built in the capability of testing the technique in wider range of shapes. We provide several quantitative and qualitative experimental results to demonstrate the robustness of our proposed EDC-Net for edge detection in 3D point clouds. We performed a statistical analysis over the ABC and ShapeNet datasets. Our numerical results demonstrate the robust and efficient performance of EDC-Net.

This paper introduces DCG-Net (Dynamic Capsule Graph Network) to analyze point clouds for the tasks of classification and segmentation. DCG-Net aggregates point cloud features to build and update the graphs based on the dynamic routing mechanism of capsule networks at each layer of a convolutional network. The first layer of DGC-Net exploits the geometrical attributes of the point cloud to build a graph by neighborhood aggregation while the deeper layers of the network dynamically update the graph based on the feature space of convolutions. We conduct extensive experiments on public datasets, ModelNet40, ShapeNet-Part. Our experimental results demonstrate that DCG-Net achieves state-of-the-art performance on public datasets, 93.4% accuracy on ModelNet40, and 85.4% instance mIoU (mean Intersection over Union) on ShapeNet-Part.

Exploring the underwater world presents significant physical and financial barriers. Telepresence technologies offer a potential solution by a providing a more accessible version of an underwater experience. Our research involved a scoping review to consolidate previous findings on vision-based technologies that aim to recreate underwater experiences and their user evaluations. We searched 5 academic databases for papers describing or evaluating technologies providing visual underwater experiences without actual submersion. We systematically searched YouTube to include immersive experiences not documented in academic publications. Our review included 45 academic papers and 23 YouTube videos classified by their level of ‘reality’, ‘degrees of freedom’, and presence of interactive elements. The technologies reviewed included virtual reality, 360 $$^{\circ }$$∘ video and imaging, augmented and mixed reality, head-mounted displays, mobile devices, cameras, sensors, remotely operated vehicles (ROVs), and games. Half of the selected papers featured user evaluations (with sample sizes ranging from 5 to 1006 participant); these methods included interviews, performance tracking, and questionnaires. We identified six main application areas for these technologies: (i) general environmental awareness, (ii) formal education about marine life, (iii) therapeutic interventions, (iv) access to underwater heritage sites, (v) ROV teleoperation and simulations, and (vi) entertainment. Immersive technologies, such as head-mounted displays and augmented reality, were prevalent across all application categories, though their usability varied. Cost considerations were also diverse, with costs ranging from expensive ROVs and simulated environments to cheaper 360 $$^{\circ }$$∘ videos. Our findings indicate a need for more robust user studies, including long-term research and comparisons among real-time, pre-recorded, and simulated experiences. A better understanding of entertainment-driven applications could benefit education, environmental conservation, and healthcare. The findings of the scoping review are discussed with respect to the technologies identified and the corresponding user studies.

Quality inspection is an industrial field with a growing interest in anomaly detection research. An anomaly in an image can either be structural or logical. While structural anomalies lie on the image objects, challenging logical anomalies are hidden in the global relations between the image components. The proposed approach, Vision Graph based Logical Anomaly Detection (ViGLAD), uses the graph representation of an image for logical anomaly detection. Defining an image as a structure of nodes and edges leverages new possibilities for detecting hidden logical anomalies by introducing vision graph autoencoders. Our experiments on public datasets show that using vision graphs enhances the performance of state-of-the-art teacher-student-autoencoder neural networks in logical anomaly detection while achieving robust results in structural anomaly detection.

Older adults often need guidance when visiting new buildings for the first time. However, indoor navigation remains challenging due to the lack of Global Positioning System (GPS) availability, visually repetitive corridors, and frequent location failures. This article presents a multimodal indoor navigation assistant that combines graph-based route planning with visual landmark verification to provide step-by-step guidance. The environment is modelled as a directed graph whose nodes are annotated with semantic landmarks, and the graph is constructed primarily from a video of the building, reducing the need for 3D scanners, beacons, or other specialised instruments. Routes are calculated using Dijkstra’s shortest-path algorithm over the semantic graph. During navigation, camera frames are analysed using a restricted vision-language recognition strategy that only considers candidate landmarks from the current and next nodes, reducing false detections and improving interpretability. To increase robustness, a temporary voting mechanism was introduced to confirm node transitions, as well as a hierarchical redirection strategy with local and global recovery. The system is implemented in two modes: handheld mode with visual cues using augmented reality arrows, mini map and voice instructions, and hands-free mode with front camera using voice instructions and keywords. Evaluation involved preliminary technical testing in the United Kingdom followed by formal user validation in Spain. During these trials, participants reported high usability, strong confidence and safety, and increased perceived independence.