Abstract: A saliency detection explicitly models complementary information between appearance, or color, and depth information in images. A mutual-information minimization is used as a regularizer to reduce the redundancy between appearance features from RGB and geometric features from depth in the latent space. Then the latent features of each of the appearance and geometric modalities are fused to achieve multi-modal feature fusion for saliency detection.

Abstract: There is provided a method for creating artificial vision with an implantable visual stimulation device. The method comprises receiving image data comprising, for each of multiple points of the image, a depth value, performing a local background enclosure calculation on the input image to determine salient object information, and generating a visual stimulus to visualise the salient object information using the visual stimulation device. Determining the salient object information is based on a spatial variance of at least one of the multiple points of the image in relation to a surface model that defines a surface in the input image.

Abstract: A method for creating artificial vision with an implantable visual stimulation device. The method comprises receiving image data comprising, for each of multiple points of an image, a depth value, performing a local background enclosure calculation on the image data to determine salient object information, and generating a visual stimulus to visualise the salient object information using the implantable visual stimulation device. Performing the local background enclosure calculation is based on a subset of the multiple points of the input image, and the subset of the multiple points is defined based on the depth value of the multiple points.

Abstract: A saliency detection explicitly models complementary information between appearance, or color, and depth information in images. A mutual-information minimization is used as a regularizer to reduce the redundancy between appearance features from RGB and geometric features from depth in the latent space. Then the latent features of each of the appearance and geometric modalities are fused to achieve multi-modal feature fusion for saliency detection.

Abstract: The present disclosure provides a computer-implemented method for enhancing vision for a vision impaired user. The method comprises, for a point in an input image, determining (210) a weight for the point based on visual importance of the point in the input image; comparing (220) the weight for the point to a threshold; and if the weight for the point meets the threshold, determining (230) a first output value for an imaging element of a vision enhancement apparatus so that a difference between the first output value and an intensity level of a portion of the input image neighbouring the point increases with the weight, wherein the difference is at least one Just-Noticeable-Difference of the vision enhancement apparatus, such that when the first output value is applied to the imaging element of the vision enhancement apparatus to create a first visual stimulus, the first visual stimulus is substantially perceivable by the vision impaired user.

Abstract: The present disclosure provides a computer-implemented method for representing intensity levels indicative of a first type of sense of a subject (150) by parameter values for a different second type of sense of the subject (150). The method comprises determining (210) a first parameter value for the second type of sense representing a first intensity level indicative of the first type of sense; and determining (220) a second parameter value for the second type of sense representing a second intensity level indicative of the first type of sense with reference to the first parameter value, wherein the first parameter value differs from the second parameter value by at least one Just-Noticeable-Difference (JND) of the second type of sense of the subject (150).

Abstract: This invention concerns the tracking of objects in video data for artificial vision; for instance for a bionic eye. More particularly, the invention concerns a vision enhancement apparatus for a vision-impaired user. In other aspects, the invention concerns a method for enhancing vision and software to perform the method. The image processor operates to process video data representing images of a scene. Automatically detect and track a user selected object, such as a face, in the images. And, automatically modify the video data, by reserving a user selected area of the displayed images for displaying the tracked object as a separate video tile within the scene. The separate video tile remains in the selected area despite movement of the camera relative to the scene, or movement of the user relative to the object or the scene.

Abstract: This disclosure concerns a method for enhancing vision for a vision impaired user comprises. A processor, such as a controller of a retinal prosthesis, determines based on input image data a shape associated with an object represented by the input image data. The processor then determines for each of multiple areas of the input image data a coverage value that indicates to what extent the shape covers that area of the input image. Each of the multiple areas is associated with one of multiple imaging elements of the retinal prosthesis. The processor then determines an output value for each of the multiple imaging elements of the retinal prosthesis, such that when the output values are applied to the imaging elements to create a visual stimulus, a contrast is perceivable between a first element and a second element based on their respective coverage values.

Abstract: This invention concerns the tracking of objects in video data for artificial vision; for instance for a bionic eye. More particularly, the invention concerns a vision enhancement apparatus for a vision-impaired user. In other aspects, the invention concerns a method for enhancing vision and software to perform the method. The image processor operates to process video data representing images of a scene. Automatically detect and track a user selected object, such as a face, in the images. And, automatically modify the video data, by reserving a user selected area of the displayed images for displaying the tracked object as a separate video tile within the scene. The separate video tile remains in the selected area despite movement of the camera relative to the scene, or movement of the user relative to the object or the scene.

Abstract: The present disclosure provides a computer-implemented method for enhancing vision for a vision impaired user. The method comprises, for a point in an input image, determining (210) a weight for the point based on visual importance of the point in the input image; comparing (220) the weight for the point to a threshold; and if the weight for the point meets the threshold, determining (230) a first output value for an imaging element of a vision enhancement apparatus so that a difference between the first output value and an intensity level of a portion of the input image neighbouring the point increases with the weight, wherein the difference is at least one Just-Noticeable-Difference of the vision enhancement apparatus, such that when the first output value is applied to the imaging element of the vision enhancement apparatus to create a first visual stimulus, the first visual stimulus is substantially perceivable by the vision impaired user.

Abstract: The present disclosure provides a computer-implemented method for representing intensity levels indicative of a first type of sense of a subject (150) by parameter values for a different second type of sense of the subject (150). The method comprises determining (210) a first parameter value for the second type of sense representing a first intensity level indicative of the first type of sense; and determining (220) a second parameter value for the second type of sense representing a second intensity level indicative of the first type of sense with reference to the first parameter value, wherein the first parameter value differs from the second parameter value by at least one Just-Noticeable-Difference (JND) of the second type of sense of the subject (150).

Abstract: This invention concerns the tracking of objects in video data for artificial vision; for instance for a bionic eye. More particularly, the invention concerns a vision enhancement apparatus for a vision-impaired user. In other aspects, the invention concerns a method for enhancing vision and software to perform the method. The image processor operates to process video data representing images of a scene. Automatically detect and track a user selected object, such as a face, in the images. And, automatically modify the video data, by reserving a user selected area of the displayed images for displaying the tracked object as a separate video tile within the scene. The separate video tile remains in the selected area despite movement of the camera relative to the scene, or movement of the user relative to the object or the scene.

Abstract: This disclosure concerns the determination of low dynamic range image data from high dynamic range image data. A processor determines the low dynamic range image data by optimizing a degree to which the low dynamic range image data satisfies a local contrast constraint and a global consistency constraint. The local contrast constraint is based on a local contrast in a perception space while the global consistency constraint is based on a relationship between points in the high dynamic range image data. The determined low dynamic range image data preserves the local contrast from the high dynamic range image data while also preserving the relationship between points in the high dynamic range image data to a high degree. As a result, the method prevents contrast distortion, halos and artifacts and ordering of level lines (isocontours) is preserved.

Abstract: This disclosure concerns a method for enhancing vision for a vision impaired user comprises. A processor, such as a controller of a retinal prosthesis, determines based on input image data a shape associated with an object represented by the input image data. The processor then determines for each of multiple areas of the input image data a coverage value that indicates to what extent the shape covers that area of the input image. Each of the multiple areas is associated with one of multiple imaging elements of the retinal prosthesis. The processor then determines an output value for each of the multiple imaging elements of the retinal pros thesis, such that when the output values are applied to the imaging elements to create a visual stimulus, a contrast is perceivable between a first element and a second element based on their respective coverage values.

Abstract: This invention concerns a vision enhancement apparatus that improves vision for a vision-impaired user of interface equipment. Interface equipment stimulates the user's cortex, directly or indirectly, to provide artificial vision. It may include a passive sensor to acquire real-time high resolution video data representing the vicinity of the user. A sight processor to receive the acquired high resolution data and automatically: Analyze the high resolution data to extract depth of field information concerning objects of interest. Extract lower resolution data representing the vicinity of the user. And, provide both the depth of field information concerning objects of interest and the lower resolution data representing the vicinity of the user to the interface equipment to stimulate artificial vision for the user.

Abstract: This disclosure concerns the determination of low dynamic range image data from high dynamic range image data. A processor determines the low dynamic range image data by optimising a degree to which the low dynamic range image data satisfies a local contrast constraint and a global consistency constraint. The local contrast constraint is based on a local contrast in a perception space while the global consistency constraint is based on a relationship between points in the high dynamic range image data. The determined low dynamic range image data preserves the local contrast from the high dynamic range image data while also preserving the relationship between points in the high dynamic range image data to a high degree. As a result, the method prevents contrast distortion, halos and artifacts and ordering of level lines (isocontours) is preserved.

Abstract: A stair climbing wheel and vehicles are described. The stair climbing wheel has a rolling wheel and a plurality of deployable protrusions that allow the wheel to climb stairs. The deployable protrusions can be deployed from or retracted into the rolling wheel. In the retracted position, the stair climbing wheel functions as a traditional circular wheel. These stair climbing wheels can be incorporated on a wide variety of vehicles, such as hand trucks, wheelchairs, and personal transports to allow these vehicles to climb stairs.

Abstract: This invention concerns a vision enhancement apparatus that improves vision for a vision-impaired user of interface equipment. Interface equipment stimulates the user's cortex, directly or indirectly, to provide artificial vision. It may include a passive sensor to acquire real-time high resolution video data representing the vicinity of the user. A sight processor to receive the acquired high resolution data and automatically: Analyse the high resolution data to extract depth of field information concerning objects of interest. Extract lower resolution data representing the vicinity of the user. And, provide both the depth of field information concerning objects of interest and the lower resolution data representing the vicinity of the user to the interface equipment to stimulate artificial vision for the user.

Abstract: This invention concerns the tracking of objects in video data for artificial vision; for instance for a bionic eye. More particularly, the invention concerns a vision enhancement apparatus for a vision-impaired user. In other aspects, the invention concerns a method for enhancing vision and software to perform the method. The image processor operates to process video data representing images of a scene. Automatically detect and track a user selected object, such as a face, in the images. And, automatically modify the video data, by reserving a user selected area of the displayed images for displaying the tracked object as a separate video tile within the scene. The separate video tile remains in the selected area despite movement of the camera relative to the scene, or movement of the user relative to the object or the scene.

Abstract: A stair climbing wheel and vehicles are described. The stair climbing wheel has a rolling wheel and a plurality of deployable protrusions that allow the wheel to climb stairs. The deployable protrusions can be deployed from or retracted into the rolling wheel. In the retracted position, the stair climbing wheel functions as a traditional circular wheel. These stair climbing wheels can be incorporated on a wide variety of vehicles, such as hand trucks, wheelchairs, and personal transports to allow these vehicles to climb stairs.