Highlights•A systematic literature review leading to 108 papers where MR has been used to
support prototyping.•Contrast 'tech push'& 'design pull'views to distil dimensions of value …

We present an approach to semantic scene analysis using deep convolutional networks.
Our approach is based on tangent convolutions-a new construction for convolutional …

Common fully glazed facades and transparent objects present architectural barriers and
impede the mobility of people with low vision or blindness, for instance, a path detected …

We propose a novel direct visual-inertial odometry method for stereo cameras. Camera
pose, velocity and IMU biases are simultaneously estimated by minimizing a combined …

Semantic segmentation was seen as a challenging computer vision problem few years ago.
Due to recent advancements in deep learning, relatively accurate solutions are now …

Transparent objects, such as glass walls and doors, constitute architectural obstacles
hindering the mobility of people with low vision or blindness. For instance, the open space …

Semantic segmentation is a critical module in robotics related applications, especially
autonomous driving. Most of the research on semantic segmentation is focused on …

Building 3D maps of the environment is central to robot navigation, planning, and interaction
with objects in a scene. Most existing approaches that integrate semantic concepts with 3D …

Deep learning has become the standard model for object detection and recognition.
Recently, there is progress on using CNN models for geometric vision tasks like depth …

Abstract Grounded Situation Recognition (GSR) is capable of recognizing and interpreting
visual scenes in a contextually intuitive way, yielding salient activities (verbs) and the …