Abstract: Provided are a mobile device (100) and computer-implemented method (700) for localisation in an existing map of a 3-D environment. For a first image frame, a first pose is localised based on visual features. For a second image frame, a pose is predicted (810) based on inertial measurements, combined with the pose of the first image frame. Based on the predicted pose, the method predicts (830) a set of landmarks that are likely to be visible. A second pose is then calculated (850), for the second image frame, based on matching (840) visual features of the second image frame to the set of landmarks.

Abstract: Provided are a mobile device (100) and computer-implemented method (700) for localisation in an existing map of a 3-D environment. For a first image frame, a first pose is localised based on visual features. For a second image frame, a pose is predicted (810) based on inertial measurements, combined with the pose of the first image frame. Based on the predicted pose, the method predicts (830) a set of landmarks that are likely to be visible. A second pose is then calculated (850), for the second image frame, based on matching (840) visual features of the second image frame to the set of landmarks.

Abstract: A source deconvolutional network is adaptively trained to perform semantic segmentation. Image data is then input to the source deconvolutional network and outputs of the S-Net are measured. The same image data and the measured outputs of the source deconvolutional network are then used to train a target deconvolutional network. The target deconvolutional network is defined by a substantially fewer numerical parameters than the source deconvolutional network.

Abstract: A method of object recognition and/or registration includes receiving a point cloud, arranging the points of the point cloud into a hierarchical search tree, and determining geometric information of the points located within a region, by identifying a highest level tree nodes where all of descendent leaf nodes are contained within the region and selecting the leaf nodes for the points where no sub-tree is entirely contained within the region, such that the points falling within the region are represented by the smallest number of nodes and performing statistical operations on the nodes representing the points in the region. The geometric information includes descriptors of features in the point cloud. The method further includes comparing the feature descriptors with a database of feature descriptors for a plurality of objects.

Abstract: A source deconvolutional network is adaptively trained to perform semantic segmentation. Image data is then input to the source deconvolutional network and outputs of the S-Net are measured. The same image data and the measured outputs of the source deconvolutional network are then used to train a target deconvolutional network. The target deconvolutional network is defined by a substantially fewer numerical parameters than the source deconvolutional network.

Abstract: A method for analysing a point cloud, the method comprising: receiving a point cloud, comprising a plurality of points, each point representing a spatial point in an image; arranging the points into a hierarchical search tree, with a lowest level comprising a plurality of leaf nodes, where each leaf node corresponds to a point of the point cloud, the search tree comprising a plurality of hierarchical levels with tree nodes in each of the hierarchical levels, the nodes being vertically connected to each other though the hierarchy by branches, wherein at least one moment of the property of the descendant nodes is stored in each tree node; and determining geometric information of the points located within a region, by identifying the highest level tree nodes where all of the descendent leaf nodes are contained within the region and selecting the leaf nodes for the points where no sub-tree is entirely contained within the region, such that such that the points falling within the region are represented by the s