Abstract: A method for producing a textural image from event information generated by an event camera comprises: accumulating event information from a plurality of events occurring during successive event cycles across a field of view of the event camera, each event indicating an x,y location within the field of view, a polarity for a change of detected light intensity incident at the x,y location and an event cycle at which the event occurred; in response to selected event cycles, analysing event information for one or more preceding event cycles to identify one or more regions of interest bounding a respective object to be tracked; and responsive to a threshold event criterion for a region of interest being met, generating a textural image for the region of interest from event information accumulated from within the region of interest.

Abstract: A method for producing a textural image from event information generated by an event camera comprises: accumulating event information from a plurality of events occurring during successive event cycles across a field of view of the event camera, each event indicating an x,y location within the field of view, a polarity for a change of detected light intensity incident at the x,y location and an event cycle at which the event occurred; in response to selected event cycles, analysing event information for one or more preceding event cycles to identify one or more regions of interest bounding a respective object to be tracked; and responsive to a threshold event criterion for a region of interest being met, generating a textural image for the region of interest from event information accumulated from within the region of interest.

Abstract: A method for determining an absolute depth map to monitor the location and pose of a head (100) being imaged by a camera comprises: acquiring (20) an image from the camera (110) including a head with a facial region; determining (23) at least one distance from the camera (110) to a facial feature of the facial region using a distance measuring sub-system (120); determining (24) a relative depth map of facial features within the facial region; and combining (25) the relative depth map with the at least one distance to form an absolute depth map for the facial region.

Abstract: Systems and methods for depth estimation in accordance with embodiments of the invention are illustrated. One embodiment includes a method for estimating depth from images. The method includes steps for receiving a plurality of source images captured from a plurality of different viewpoints using a processing system configured by an image processing application, generating a target image from a target viewpoint that is different to the viewpoints of the plurality of source images based upon a set of generative model parameters using the processing system configured by the image processing application, and identifying depth information of at least one output image based on the predicted target image using the processing system configured by the image processing application.

Abstract: An image processing system is configured to receive a first high resolution stream of images and a second lower resolution stream of images from image sources with substantially the same field of view. The system comprises a localizer component configured to provide a location for any object of interest independently of class within successive images of the second stream of images; a classifier configured to: receive one or more locations selectively provided by the localizer, identify a corresponding portion of an image acquired from the first stream at substantially the same time at which an image from the second stream in which an object of interest was identified and return a classification for the type of object within the identified portion of the image from the first stream; and a tracker configured to associate the classification with the location through acquisition of successive images in the second stream.

Abstract: A method for producing a textural image from event information generated by an event camera comprises: accumulating event information from a plurality of events occurring during successive event cycles across a field of view of the event camera, each event indicating an x,y location within the field of view, a polarity for a change of detected light intensity incident at the x,y location and an event cycle at which the event occurred; in response to selected event cycles, analysing event information for one or more preceding event cycles to identify one or more regions of interest bounding a respective object to be tracked; and responsive to a threshold event criterion for a region of interest being met, generating a textural image for the region of interest from event information accumulated from within the region of interest.

Abstract: Systems and methods of detecting an unauthorized data insertion into a stream of data segments extending between electronic modules or between electronic components within a module, wherein a Secret embedded into the data stream is compared to a Replica Secret upon receipt to confirm data transmission integrity.

Abstract: Systems and methods in accordance with embodiments of the invention are configured to render images using light field image files containing an image synthesized from light field image data and metadata describing the image that includes a depth map. One embodiment of the invention includes a processor and memory containing a rendering application and a light field image file including an encoded image, a set of low resolution images, and metadata describing the encoded image, where the metadata comprises a depth map that specifies depths from the reference viewpoint for pixels in the encoded image. In addition, the rendering application configures the processor to: locate the encoded image within the light field image file; decode the encoded image; locate the metadata within the light field image file; and post process the decoded image by modifying the pixels based on the depths indicated within the depth map and the set of low resolution images to create a rendered image.

Abstract: A method for stabilizing a video sequence comprises: obtaining an indication of camera movement from acquisition of a previous camera frame to acquisition of a current camera frame; determining an orientation for the camera at a time of acquiring the current camera frame; and determining a candidate orientation for a crop frame for the current camera frame by adjusting an orientation of a crop frame associated with the previous camera frame according to the determined orientation. A boundary of one of the camera frame or crop frame is traversed to determine if a specific point on the boundary of the crop frame exceeds a boundary of the camera frame. If so, a rotation of the specific point location which would bring the specific point location onto the boundary of the crop frame is determined and the candidate crop frame orientation updated accordingly before the crop frame is displayed.

Abstract: Systems and methods for calibrating an array camera are disclosed. Systems and methods for calibrating an array camera in accordance with embodiments of this invention include the capturing of an image of a test pattern with the array camera such that each imaging component in the array camera captures an image of the test pattern. The image of the test pattern captured by a reference imaging component is then used to derive calibration information for the reference component. A corrected image of the test pattern for the reference component is then generated from the calibration information and the image of the test pattern captured by the reference imaging component. The corrected image is then used with the images captured by each of the associate imaging components associated with the reference component to generate calibration information for the associate imaging components.

Abstract: Systems and methods for dynamically calibrating an array camera to accommodate variations in geometry that can occur throughout its operational life are disclosed. The dynamic calibration processes can include acquiring a set of images of a scene and identifying corresponding features within the images. Geometric calibration data can be used to rectify the images and determine residual vectors for the geometric calibration data at locations where corresponding features are observed. The residual vectors can then be used to determine updated geometric calibration data for the camera array. In several embodiments, the residual vectors are used to generate a residual vector calibration data field that updates the geometric calibration data. In many embodiments, the residual vectors are used to select a set of geometric calibration from amongst a number of different sets of geometric calibration data that is the best fit for the current geometry of the camera array.

Abstract: A technique of generating a stereoscopic panorama image includes panning a portable camera device, and acquiring multiple image frames. Multiple at least partially overlapping image frames are acquired of portions of the scene. The method involves registering the image frames, including determining displacements of the imaging device between acquisitions of image frames. Multiple panorama images are generated including joining image frames of the scene according to spatial relationships and determining stereoscopic counterpart relationships between the multiple panorama images. The multiple panorama images are processed based on the stereoscopic counterpart relationships to form a stereoscopic panorama image.

Abstract: A video super resolution method comprises successively executing instances of a first plurality of layers (SISR) of a neural network for generating a first image (St) at a higher resolution than an input image frame (Xt); successively executing a second plurality of layers (VSR) of the neural network for generating a second image (Vt) at the higher resolution, at least one of the second plurality of layers generating intermediate output information (Ht), the second plurality of layers taking into account an output image (Yt?1) at the higher resolution generated by a previous instance of the network from a previous input image frame (Xt?1) and intermediate output information (Ht?1) generated by the second plurality of layers of the previous instance, and executing a third plurality of layers for combining the first (St) and second (Vt) images to produce an output image (Yt) for the instance of the network.

Abstract: An image processing apparatus comprises a normalisation module operatively connected across a bus to a memory storing an image in which a region of interest (ROI) has been identified within the image. The ROI is bound by a rectangle having a non-orthogonal orientation within the image. In one embodiment, the normalisation module is arranged to divide the ROI into one or more slices, each slice comprising a plurality of adjacent rectangular tiles. For each slice, the apparatus successively reads ROI information for each tile from the memory including: reading a portion of the image extending across at least a width of the slice line-by-line along an extent of a slice. For each tile, the apparatus downsamples the ROI information to a buffer to within a scale SD<2 of a required scale for a normalised version of the ROI.

Abstract: A device, such as a head-mounted device (HMD), may include a frame and a plurality of mirrors coupled to an interior portion of the frame. An imaging device may be coupled to the frame at a position to capture images of an eye of the wearer reflected from the mirrors. The HMD may also include a mirror angle adjustment device to adjust an angle of one or more of the mirrors relative to the imaging device so that the mirror(s) reflect the eye of the wearer to the imaging device.

Abstract: A convolutional neural network (CNN) for an image processing system comprises an image cache responsive to a request to read a block of N×M pixels extending from a specified location within an input map to provide a block of N×M pixels at an output port. A convolution engine reads blocks of pixels from the output port, combines blocks of pixels with a corresponding set of weights to provide a product, and subjects the product to an activation function to provide an output pixel value. The image cache comprises a plurality of interleaved memories capable of simultaneously providing the N×M pixels at the output port in a single clock cycle. A controller provides a set of weights to the convolution engine before processing an input map, causes the convolution engine to scan across the input map by incrementing a specified location for successive blocks of pixels and generates an output map within the image cache by writing output pixel values to successive locations within the image cache.

Abstract: A hardware acceleration module may generate a channel-wise argmax map using a predefined set of hardware-implemented operations. In some examples, a hardware acceleration module may receive a set of feature maps for different image channels. The hardware acceleration module may execute a sequence of hardware operations, including a portion(s) of hardware for executing a convolution, rectified linear unit (ReLU) activation, and/or layer concatenation, to determine a maximum channel feature value and/or argument maxima (argmax) value for a set of associated locations within the feature maps. An argmax map may be generated based at least in part on the argument maximum for a set of associated locations.

Abstract: Systems and methods of detecting an unauthorized data insertion into a stream of data segments extending between electronic modules or between electronic components within a module, wherein a pseudo data segment included in the data stream upon transmission is detected upon receipt to confirm data transmission integrity.

Abstract: A hand-held digital camera has a touch-sensitive display screen (“touch screen”) for image preview and user control of the camera, and a user-selectable panorama mode. Upon entering panorama mode the camera superimposes upon the touch screen a horizontal rectangular bar whose width and/or height are user-adjustable by interaction with the touch screen to select a desired horizontal sweep angle. After the sweep angle is set the camera automatically captures successive horizontally overlapping images during a sweep of the device through the selected sweep angle. Subsequently the camera synthesises a panoramic image from the successively captured images, the panoramic image having a width corresponding to the selected sweep angle.

Abstract: Systems and methods of detecting an unauthorized data insertion into a stream of data segments extending between electronic modules or between electronic components within a module, wherein a Secret embedded into the data stream is compared to a Replica Secret upon receipt to confirm data transmission integrity.