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: Systems in accordance with embodiments of the invention can perform parallax detection and correction in images captured using array cameras. Due to the different viewpoints of the cameras, parallax results in variations in the position of objects within the captured images of the scene. Methods in accordance with embodiments of the invention provide an accurate account of the pixel disparity due to parallax between the different cameras in the array, so that appropriate scene-dependent geometric shifts can be applied to the pixels of the captured images when performing super-resolution processing. In a number of embodiments, generating depth estimates considers the similarity of pixels in multiple spectral channels. In certain embodiments, generating depth estimates involves generating a confidence map indicating the reliability of depth estimates.

Abstract: An image acquisition system determines first and second sets of points defining an iris-pupil boundary and an iris-sclera boundary in an acquired image; determines respective ellipses fitting the first and second sets of points; determines a transformation to transform one of the ellipses into a circle on a corresponding plane; using the determined transformation, transforms the selected ellipse into a circle on the plane; using the determined transformation, transforms the other ellipse into a transformed ellipse on the plane; determines a plurality of ellipses on the plane for defining an iris grid, by interpolating a plurality of ellipses between the circle and the transformed ellipse; moves the determined grid ellipses onto the iris in the image using an inverse transformation of the determined transformation; and extracts an iris texture by unwrapping the iris and interpolating image pixel values at each grid point defined along each of the grid ellipses.

Abstract: A camera comprises a lens assembly coupled to an event-sensor, the lens assembly being configured to focus a light field onto a surface of the event-sensor, the event-sensor surface comprising a plurality of light sensitive-pixels, each of which cause an event to be generated when there is a change in light intensity greater than a threshold amount incident on the pixel. The camera further includes an actuator which can be triggered to cause a change in the light field incident on the surface of the event-sensor and to generate a set of events from a sub-set of pixels distributed across the surface of the event-sensor.

Abstract: A vehicle can include one or more movably mounted cameras that are able to move to adjust a viewing angle of the camera(s) relative to a body of the vehicle. The camera(s) may be movable by virtue of being coupled to a movable side mirror, such that movement of the side mirror changes a field of view of the camera coupled to the side mirror. For example, the side mirror can be rotated about a rotational axis between a first position in which a field of view of the camera is directed in a first direction (e.g. toward a ground proximate the vehicle), and a second position in which the field of view of the camera is directed in a second direction, different than the first direction (e.g., outward from the vehicle or toward a door of the vehicle).

Abstract: Systems and methods in accordance with embodiments of the invention are disclosed that use super-resolution (SR) processes to use information from a plurality of low resolution (LR) images captured by an array camera to produce a synthesized higher resolution image. One embodiment includes obtaining input images using the plurality of imagers, using a microprocessor to determine an initial estimate of at least a portion of a high resolution image using a plurality of pixels from the input images, and using a microprocessor to determine a high resolution image that when mapped through the forward imaging transformation matches the input images to within at least one predetermined criterion using the initial estimate of at least a portion of the high resolution image.

Abstract: A handheld computing device comprises a display comprising an array of pixels illuminated by a plurality of visible light sources, and a plurality of infra-red light sources interleaved between the visible light sources, the IR light sources being actuable to emit diffuse IR light with a first intensity. A camera has an image sensor comprising an array of pixels responsive to infra-red light and a lens assembly with an optical axis extending from the image sensor through the surface of the display. A dedicated illumination source is located outside the display and is actuable to emit infra-red light with a second greater intensity. A processor is configured to switch between an iris region processing mode in which a subject is illuminated at least by the dedicated light source and a face region processing mode in which a subject is illuminated by the plurality of IR light sources.

Abstract: A system includes an image sensor, an adjustable aperture, and a memory. THE memory includes computer executable instructions that, when executed by a processor, cause the system to perform operations including obtaining a first image via the image sensor based at least in part on a first aperture stop of the adjustable aperture, identifying a first pixel of the first image, identifying a second pixel of the first image, determining a second aperture stop of the adjustable aperture based at least in part on the first pixel, determining a third aperture stop of the adjustable aperture based at least in part on the second pixel, obtaining a second image via the image sensor based at least in part on the second aperture stop, and obtaining a third image via the image sensor based at least in part on the third aperture stop.

Abstract: A method operable by a computing device for configuring access for a limited user interface (UI) device to a network service via a local network access point is disclosed. The method comprises the steps of: obtaining from the limited UI device a device identifier via a first out-of-band channel. The device identifier is provided to the network service via a secure network link. A zero knowledge proof (ZKP) challenge is received from the network service. Configuration information is provided to the limited-UI device via a second out-of-band channel, the configuration information including information sufficient to enable the limited-UI device to connect to the local network access point. The ZKP challenge is provided to the limited-UI device via the second out-of-band channel.

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 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: The technology relates to tuning a data translation block (DTB) including a generator model and a discriminator model. One or more processors may be configured to receive training data including an image in a second domain. The image in the second domain may be transformed into a first domain with a generator model. The transformed image may be processed to determine one or more outputs with one or more deep neural networks (DNNs) trained to process data in the first domain. An original objective function for the DTB may be updated based on the one or more outputs. The generator and discriminator models may be trained to satisfy the updated objective function.

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: This disclosure describes, in part, systems and techniques for performing eye tracking. For instance, a system may include a first imaging device that generates first image data. The system may then analyze the first image data to determine a location of a face of a user. Using the location, the system may cause an actuator to move from a first position to a second position in order to direct a second imaging device towards the face of the user. While in the second position, the second imaging device may generate second image data representing at least the face of the user. The system may then analyze the second image data to determine a gaze direction of the user. In some instances, the first imaging device may include a first field of view (FOV) that is greater than a second FOV of the second imaging device.

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: Systems and methods in accordance with embodiments of the invention estimate depth from projected texture using camera arrays. One embodiment of the invention includes: at least one two-dimensional array of cameras comprising a plurality of cameras; an illumination system configured to illuminate a scene with a projected texture; a processor; and memory containing an image processing pipeline application and an illumination system controller application. In addition, the illumination system controller application directs the processor to control the illumination system to illuminate a scene with a projected texture.

Abstract: A method of generating landmark locations for an image crop comprises: processing the crop through an encoder-decoder to provide a plurality of N output maps of comparable spatial resolution to the crop, each output map corresponding to a respective landmark of an object appearing in the image crop; processing an output map from the encoder through a plurality of feed forward layers to provide a feature vector comprising N elements, each element including an (x,y) location for a respective landmark. Any landmarks locations from the feature vector having an x or a y location outside a range for a respective row or column of the crop are selected for a final set of landmark locations; with remaining landmark locations tending to be selected from the N (x,y) landmark locations from the plurality of N output maps.

Abstract: A dynamically reconfigurable heterogeneous systolic array is configured to process a first image frame, and to generate image processing primitives from the image frame, and to store the primitives and the corresponding image frame in a memory store. A characteristic of the image frame is determined. Based on the characteristic, the array is reconfigured to process a following image frame.

Abstract: Embodiments of the invention provide a camera array imaging architecture that computes depth maps for objects within a scene captured by the cameras, and use a near-field sub-array of cameras to compute depth to near-field objects and a far-field sub-array of cameras to compute depth to far-field objects. In particular, a baseline distance between cameras in the near-field subarray is less than a baseline distance between cameras in the far-field sub-array in order to increase the accuracy of the depth map. Some embodiments provide an illumination near-IR light source for use in computing depth maps.