Abstract: An image processing system to estimate depth for a scene. The image processing system includes a fusion engine to receive a first depth estimate from a geometric reconstruction engine and a second depth estimate from a neural network architecture. The fusion engine is configured to probabilistically fuse the first depth estimate and the second depth estimate to output a fused depth estimate for the scene. The fusion engine is configured to receive a measurement of uncertainty for the first depth estimate from the geometric reconstruction engine and a measurement of uncertainty for the second depth estimate from the neural network architecture, and use the measurements of uncertainty to probabilistically fuse the first depth estimate and the second depth estimate.

Abstract: Certain examples described herein enable a robotic device to accurate map a surrounding environment. The robotic device uses an image capture device and at least one of the image capture device and the robotic device move within the environment. Measurements associated with movement of at least one of the image capture device and the robotic device are used to determine a state of the robotic device. The state of the robotic device models the image capture device and the robotic device with respect to a model of the environment that is constructed by a mapping engine. By comparing the state of the robotic device with a measured change in the robotic device, an accurate representation of the state of the robotic device may be constructed. This state is used by the mapping engine to update the model of the environment.

Abstract: An image processing system configured to obtain a mesh representation of a scene, wherein the mesh representation comprises a plurality of polygons defined by respective vertices associated with an in-plane position, the in-plane position being in a plane comprising a first dimension and a second dimension, and the vertices having an associated vertex depth value in a third dimension different from the first dimension and the second dimension. The image processing system comprises an in-plane position estimation network configured to process image data representative of an image of the scene to estimate the in-plane positions associated with respective vertices of the mesh representation. The image processing system further comprises a depth estimation engine configured to process the in-plane positions and the image data to estimate the associated vertex depth values for the respective vertices of the mesh representation.

Abstract: Certain examples described herein relate to estimating dimensions of an enclosed space such as a room using a monocular multi-directional camera device. In examples, a movement of the camera device around a point in a plane of movement is performed, such as by a robotic device. Using the monocular multi-directional camera device, a sequence of images are obtained at a plurality of different angular positions during the movement. Pose data is determined from the sequence of images. The pose data is determined using a set of features detected within the sequence of images. Depth values are then estimated by evaluating a volumetric function of the sequence of images and the pose data. A three dimensional volume is defined around a reference position of the camera device, wherein the three-dimensional volume has a two-dimensional polygonal cross-section within the plane of movement. The three dimensional volume is then fitted to the depth values to determine dimensions for the polygonal cross-section.

Abstract: Certain examples described herein relate to a system for processing image data. In such examples, the system includes an input interface to receive the image data, which is representative of at least one view of a scene. The system also includes an initialisation engine to generate a first latent representation associated with a first segmentation of at least a first view of the scene, wherein the first segmentation is a semantic segmentation. The initialisation engine is also arranged to generate a second latent representation associated with at least a second view of the scene. The system additionally includes an optimisation engine to jointly optimise the first latent representation and the second latent representation, in a latent space, to obtain an optimised first latent representation and an optimised second latent representation.

Abstract: Examples are described that process image data to predict a thickness of objects present within the image data. In one example, image data for a scene is obtained, the scene featuring a set of objects. The image data is decomposed to generate input data for a predictive model. This may include determining portions of the image data that correspond to the set of objects in the scene, where each portion corresponding to a different object. Cross-sectional thickness measurements are predicted for the portions using the predictive model. The predicted cross-sectional thickness measurements for the portions of the image data are then composed to generate output image data comprising thickness data for the set of objects in the scene.

Abstract: Certain examples described herein enable a robotic device to accurate map a surrounding environment. The robotic device uses an image capture device and at least one of the image capture device and the robotic device move within the environment. Measurements associated with movement of at least one of the image capture device and the robotic device are used to determine a state of the robotic device. The state of the robotic device models the image capture device and the robotic device with respect to a model of the environment that is constructed by a mapping engine. By comparing the state of the robotic device with a measured change in the robotic device, an accurate representation of the state of the robotic device may be constructed. This state is used by the mapping engine to update the model of the environment.

Abstract: An image processing system to estimate depth for a scene. The image processing system includes a fusion engine to receive a first depth estimate from a geometric reconstruction engine and a second depth estimate from a neural network architecture. The fusion engine is configured to probabilistically fuse the first depth estimate and the second depth estimate to output a fused depth estimate for the scene. The fusion engine is configured to receive a measurement of uncertainty for the first depth estimate from the geometric reconstruction engine and a measurement of uncertainty for the second depth estimate from the neural network architecture, and use the measurements of uncertainty to probabilistically fuse the first depth estimate and the second depth estimate.

Abstract: A method comprising applying an object recognition pipeline to frames of video data. The object recognition pipeline provides a mask output of objects detected in the frames. The method includes fusing the mask output of the object recognition pipeline with depth data associated with the frames of video data to generate a map of object instances, including projecting the mask output to a model space for the map of object instances using a camera pose estimate and the depth data. An object instance in the map of object instances is defined using surface-distance metric values within a three-dimensional object volume, and has an object pose estimate indicating a transformation of the object instance to the model space. The object pose estimate and the camera pose estimate form nodes of a pose graph for the map of model instances.

Abstract: Certain examples described herein enable semantically-labelled representations of a three-dimensional (3D) space to be generated from video data. In described examples, a 3D representation is a surface element or ‘surfel’ representation, where the geometry of the space is modelled using a plurality of surfaces that are defined within a 3D co-ordinate system. Object-label probability values for spatial elements of frames of video data may be determined using a two-dimensional image classifier. Surface elements that correspond to the spatial elements are identified based on a projection of the surface element representation using an estimated pose for a frame. Object-label probability values for the surface elements are then updated based on the object-label probability values for corresponding spatial elements. This results in a semantically-labelled 3D surface element representation of objects present in the video data.

Abstract: Examples described herein relate to mapping a space using a multi-directional camera. This mapping may be performed with a robotic device comprising a monocular multi-directional camera device and at least one movement actuator. The mapping may generate an occupancy map to determine navigable portions of the space. A robotic device movement around a point in a plane of movement may be instructed using the at least one movement actuator. Using the monocular multi-directional camera device, a sequence of images are obtained (610) at different angular positions during the instructed movement. Pose data is determined (620) from the sequence of images. The pose data is determined using features detected within the sequence of images. Depth values are then estimated (630) by evaluating a volumetric function of the sequence of images and the pose data. The depth values are processed (640) to populate the occupancy map for the space.

Abstract: Certain examples described herein relate to modelling a three-dimensional space. Image data from at least one capture device is used to generate a three-dimensional model of the three-dimensional space. In certain examples, the three-dimensional model is segmented into active and inactive portions based on at least one model property. The examples are configured to use the active portions to update the three-dimensional model over time. Registration is also performed to align active portions of the three-dimensional model with inactive portions of the three-dimensional model over time. The registration aligns active portions of the three-dimensional model generated following an observation of a region of the three-dimensional space with inactive portions of the model generated following at least one previous observation of said region.

Abstract: Certain examples described herein relate to estimating dimensions of an enclosed space such as a room using a monocular multi-directional camera device. In examples, a movement of the camera device around a point in a plane of movement is performed, such as by a robotic device. Using the monocular multi-directional camera device, a sequence of images are obtained at a plurality of different angular positions during the movement. Pose data is determined from the sequence of images. The pose data is determined using a set of features detected within the sequence of images. Depth values are then estimated by evaluating a volumetric function of the sequence of images and the pose data. A three dimensional volume is defined around a reference position of the camera device, wherein the three-dimensional volume has a two-dimensional polygonal cross-section within the plane of movement. The three dimensional volume is then fitted to the depth values to determine dimensions for the polygonal cross-section.

Abstract: Certain examples described herein enable semantically-labelled representations of a three-dimensional (3D) space to be generated from video data. In described examples, a 3D representation is a surface element or ‘surfel’ representation, where the geometry of the space is modelled using a plurality of surfaces that are defined within a 3D co-ordinate system. Object-label probability values for spatial elements of frames of video data may be determined using a two-dimensional image classifier. Surface elements that correspond to the spatial elements are identified based on a projection of the surface element representation using an estimated pose for a frame. Object-label probability values for the surface elements are then updated based on the object-label probability values for corresponding spatial elements. This results in a semantically-labelled 3D surface element representation of objects present in the video data.

Abstract: Certain examples described herein relate to apparatus and techniques suitable for mapping a 3D space. In examples, a height map is generated in real-time from depth map and camera pose inputs provided from at least one image capture device. The height map may be processed to generate a free-space map to determine navigable portions of the space by a robotic device.

Abstract: Examples described herein relate to mapping a space using a multi-directional camera. This mapping may be performed with a robotic device comprising a monocular multi-directional camera device and at least one movement actuator. The mapping may generate an occupancy map to determine navigable portions of the space. A robotic device movement around a point in a plane of movement may be instructed using the at least one movement actuator. Using the monocular multi-directional camera device, a sequence of images are obtained (610) at different angular positions during the instructed movement. Pose data is determined (620) from the sequence of images. The pose data is determined using features detected within the sequence of images. Depth values are then estimated (630) by evaluating a volumetric function of the sequence of images and the pose data. The depth values are processed (640) to populate the occupancy map for the space.

Abstract: Certain examples described herein relate to modelling a three-dimensional space. Image data from at least one capture device is used to generate a three-dimensional model of the three-dimensional space. In certain examples, the three-dimensional model is segmented into active and inactive portions based on at least one model property. The examples are configured to use the active portions to update the three-dimensional model over time. Registration is also performed to align active portions of the three-dimensional model with inactive portions of the three-dimensional model over time. The registration aligns active portions of the three-dimensional model generated following an observation of a region of the three-dimensional space with inactive portions of the model generated following at least one previous observation of said region.

Abstract: Provided is an aircraft having a spherical body which generates buoyancy or which may generate buoyancy when filled with gas, wherein the aircraft further comprises four actuation units arranged on the surface of the body for movement of the aircraft in a translation and/or rotation through air, and at least one camera arranged on or in the surface of the body. Further provided is a method for providing optical information to a person in the environment of a flying aircraft, a method for providing optical information about an object and/or surveying of an object, a method for transmission of acoustic information and a method for observing or tracking an object.