Abstract: Visual information defining visual content may be accessed. The visual content may include one or more views of one or more scenes. The scene(s) may include one or more human subjects. Gaze directions of the human subject(s) may be determined. The gaze directions may indicate one or more viewing directions in which the human subject(s) are looking. One or more directions of view for the visual content may be determined based on the gaze directions of the human subject(s). The direction(s) of view may include one or more of the viewing directions looked at by the human subject(s). The visual content may be presented on a display based on the direction(s) of view for the visual content.

Abstract: Video information and sensor information may be obtained. The video information may define spherical video content having a progress length. The spherical video content may define visual content viewable from a point a view as a function of progress through the progress length of the spherical video content. The spherical video content may be captured by one or more image capture devices. The sensor information may characterize capture of the spherical video content. A viewing direction for the spherical video content may be determined based on the sensor information and/or other information. The viewing direction may define a direction of view for the spherical video content from the point of view as the function of progress through the progress length of the spherical video content. The spherical video content may be presented on a display based on the viewing direction.

Abstract: Multiple image capture devices may individually generate time information and capture images. Individual image captures devices may receive time information of other image capture device(s). Individual image capture devices may transmit its time information to other image capture device(s) independent of reception of the time information of other image capture device(s). Individual image capture devices may generate time synchronization information for the captured images based on its time information and the received time information of other image capture device(s). Images captured by different image capture devices may be time-synchronized based on at least one of generated time-synchronization information.

Abstract: A viewing direction may define an angle/visual portion of a spherical video at which a viewing window is directed. A trajectory of viewing direction may include changes in viewing directions for playback of spherical video. Abrupt changes in the viewing directions may result in jerky or shaky views of the spherical video. Changes in the viewing directions may be stabilized to provide stabilized views of the spherical video. Amount of stabilization may be limited by a margin constraint.

Abstract: Spherical video content may have a progress length and include spherical video frames that define visual content viewable from a point of view as a function of progress through the progress length. Edits for the spherical video content may be used to generate an edit tree. The edit tree may include nodes corresponding to the edits and edges connecting different nodes. An edit of the spherical video content may be generated based on the edit tree.

Abstract: A spherical content capture system captures spherical video and audio content. In one embodiment, captured metadata or video/audio processing is used to identify content relevant to a particular user based on time and location information. The platform can then generate an output video from one or more shared spherical content files relevant to the user. The output video may include a non-spherical reduced field of view such as those commonly associated with conventional camera systems. Particularly, relevant sub-frames having a reduced field of view may be extracted from each frame of spherical video to generate an output video that tracks a particular individual or object of interest. For each sub-frame, a corresponding portion of an audio track is generated that includes a directional audio signal having a directionality based on the selected sub-frame.

Abstract: In a video capture system, a virtual lens is simulated when applying a crop or zoom effect to an input video. An input video frame is received from the input video that has a first field of view and an input lens distortion caused by a lens used to capture the input video frame. A selection of a sub-frame representing a portion of the input video frame is obtained that has a second field of view smaller than the first field of view. The sub-frame is processed to remap the input lens distortion to a desired lens distortion in the sub-frame. The processed sub-frame is the outputted.

Abstract: Video information defining video content may be accessed. Music information defining a music track providing an accompaniment for video content may be accessed. The music track may have pulses and one or more music events. Individual music events may correspond to different moments within the music track. One or more music events may be individually classified into one or more categories based on intensities of one or pulses occurring within the music event. One or more visual effects may be selected for different moments within the music track based on the categories of the music events. One or more visual effects may be applied to the video content. One or more visual effects may be applied to one or more moments within the video content aligned to one or more different moments within the music track.

Abstract: A three-dimensional lookup table may map input colors from an electronic file defining the input colors based on input pixel locations to output colors on a display medium based on output pixel locations. A filter may characterize one or more color transformations of an unfiltered image to a filtered image such that applying the filter to the unfiltered image generates the filtered image. The filter may be applied to the three-dimensional lookup table to generate a filtered three-dimensional lookup table. The filtered three-dimensional lookup table may map the input colors to filtered output colors such that a display of the unfiltered image based on the filtered three-dimensional lookup table simulates a display of the filtered image. An image may be displayed based on the filtered three-dimensional lookup table to simulate a display of the image after the filter is applied the image.

Abstract: Media capture apparatus and methods for obtaining metadata. Metadata may be collected and stored in a container independent of audio and/or image (media) content. Some container implementations may be configured to store metadata for a given interval, and media content for a portion of the interval. In action camera implementations, metadata may provide a context related to time, physical conditions of a person, location, surroundings of the video capture. In event recording applications, the metadata container may provide information related to a timeline of the event, environmental conditions, proximity of other capture devices. Metadata may be utilized for processing, viewing, and/or sharing of media content. Individual capture devices may communicate and/or combine metadata to one another in order to expand metadata content. Metadata, video and/or images may be shared between users and/or devices using a container.

Abstract: A camera system with image and audio capture capabilities is configured to protect the internal audio components from the external environment. The camera system includes an internal audio assembly with a microphone and an audio circuit board. The audio circuit board is structured such that a gap exists within the board that allows transmission of sound waves from external the environment to the microphone. The audio assembly also includes a compressible annulus, a support annulus, and a waterproof membrane coupled by a support structure. The waterproof membrane protects the internal components from moisture while still allowing transmission of sound waves. The support structure, compressible annulus, support annulus, and audio circuit board are structured such that a gap exists above the microphone and underneath the waterproof membrane.

Abstract: A camera system with six faces and a front housing is configured to capture images and audio content from external the camera body. The camera system includes an interior audio assembly protected from external environments by a waterproof membrane. The camera system includes drainage ports on the bottom face and the left face of the camera system to encourage moisture to drain from the system. A first drainage channel couples the internal audio assembly to the first drainage port on left face of the camera system and a second drainage channel couples the drainage port on the left face of the camera system to the drainage port on the bottom face of the camera system. A third drainage channel exists between the front face of the camera system and the front housing, the third drainage channel coupling the first and second drainage channels.

Abstract: Disclosed is a configuration of an autonomous vehicle for autonomously following a moving subject based on a radius of a virtual sphere surrounding the autonomous vehicle. The autonomous vehicle may be an unmanned ground vehicle or an unmanned aerial vehicle, which autonomously follows the subject (e.g., a device, a live entity, or any object) based on the virtual sphere. The radius of the virtual sphere may be dynamically configured according to a velocity of the autonomous vehicle or configurations of a camera coupled to the autonomous vehicle. Accordingly, the autonomous vehicle can follow the subject along a smooth trajectory, and capture images of abrupt movements of the subject in a cinematically pleasing manner.

Abstract: An aerial vehicle platform includes an aerial vehicle, a gimbal coupled to the aerial vehicle, and a camera mounted to the gimbal. An attitude sensing system includes an inertial measurement unit to sense attitude and an attitude adjustment module to generate an attitude adjustment for adjusting the sensed attitude to compensate for drift error.

Abstract: In one aspect of the present disclosure, a module is disclosed for use with a digital image capturing device (DICD) including an integrated sensor-lens assembly (ISLA). The module includes a cradle configured for connection to a housing of the DICD, and at least one dampener that is configured for positioning between the module and the housing of the DICD to reduce vibrations transmitted to the ISLA.

Abstract: A camera system configuration generates 2D or 3D images capable of being stitched together to create panoramic images. The configuration detects a communication coupling of at least two cameras for capturing a sequence of images. The cameras themselves are configured such that their rolling shutters mitigate field of view artifacts from adjacent cameras (2D panoramas) and adjacent 3D camera pairs (3D panoramas) by allowing for the substantially temporally-aligned capture of light in overlap regions between adjacent cameras.

Abstract: Systems and methods are disclosed for image capture. For example, methods may include accessing a sequence of images from an image sensor; determining a sequence of parameters for respective images in the sequence of images based on the respective images; storing the sequence of images in a buffer; determining a temporally smoothed parameter for a current image in the sequence of images based on the sequence of parameters, wherein the sequence of parameters includes parameters for images in the sequence of images that were captured after the current image; applying image processing to the current image based on the temporally smoothed parameter to obtain a processed image; and storing, displaying, or transmitting an output image based on the processed image.

Abstract: Disclosed is a system and method for calibrating a magnetometer. The method comprises responsive to a determination that a magnetic inclination is less than a threshold, measuring first magnetic field data by detecting a magnetic field with the magnetometer through a first rotation path, measuring second magnetic field data by detecting the magnetic field with the magnetometer through a second rotation path, and determining calibration values for the magnetometer based on the measured first magnetic field data and the measured second magnetic field data.

Abstract: Apparatus and methods for providing a rotated spherical viewpoint (RSV). In one or more embodiments, the RSV is implemented using equirectangular projections (ERPs). The RSV methodologies described herein are particularly suitable for panning within virtual reality (VR) or 360° panoramic content as there is minimal, if any, geometric distortions at the edge of a given viewport. Moreover, the RSV methodologies described herein may reduce the bandwidth requirements of, for example, devices operating in a client-server architecture. Additionally, the computation requirements for providing RSV are minimal and can be provided using relatively simple rotation transforms.

Abstract: Hyper-hemispherical images may be combined to generate a rectangular projection of a spherical image having an equatorial stitch line along of a line of lowest distortion in the two images. First and second circular images are received representing respective hyper-hemispherical fields of view. A video processing device may project each circular image to a respective rectangular image by mapping an outer edge of the circular image to a first edge of the rectangular image and mapping a center point of the circular image to a second edge of the first rectangular image. The rectangular images may be stitched together along the edges corresponding to the outer edge of the original circular image.

Abstract: Apparatus and methods for digital video data compression via a scalable, multi-resolution approach. In one embodiment, the video content may be encoded using a multi-resolution and/or multi-quality scalable coding approach that reduces computational and/or energy load on a client device. In one implementation, a low fidelity image is obtained based on a first full resolution image. The low fidelity image may be encoded to obtain a low fidelity bitstream. A second full resolution image may be obtained based on the low fidelity bitstream. A portion of a difference image obtained based on the second full resolution image and the first full resolution may be encoded to obtain a high fidelity bitstream. The low fidelity bitstream and the high fidelity bitstream may be provided to e.g., a receiving device.

Abstract: Video content may be presented on a touchscreen display. A viewing window for the video content may define an extent of the video content presented on the touchscreen display. Reception of an automatic movement input by the touchscreen display during the presentation of the video content may be determined. The automatic movement input may include user engagement with the touchscreen display that moves along the touchscreen display to an edge of the touchscreen display during an input period. The movement along the touchscreen display may cause a movement of the viewing window during the input period. Based on the automatic movement input, the movement of the viewing window may be continued after the input period. The movement of the viewing window after the input period may be continuous with the movement of the viewing window during the input period.

Abstract: A camera mounting system has an upper mount component, a lower mount component, and a base mount component. The upper mount component secures the camera and has a ball protrusion that reciprocally couples with a socket of the lower mount component. The upper mount component can rotate 360 degrees relative to the lower mount, and can pivot 90 degrees or more relative to the lower mount component. The lower mount component couples with the base mount component in a plurality of orientations. This camera mounting system allows for a large range of motion for the camera relative to the mounting system.

Abstract: Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. In one example, best scenes are identified based on the motion values associated with frames or portions of a frame of a video. Motion values are determined for each frame and portions of the video including frames with the most motion are identified as best scenes. Best scenes may also be identified based on the motion profile of a video. The motion profile of a video is a measure of global or local motion within frames throughout the video. For example, best scenes are identified from portion of the video including steady global motion. A video summary can be generated including one or more of the identified best scenes.

Abstract: Image analysis and processing may include using an image processor to receive image data corresponding to an input image, determine an initial gain value for the image data based on at least one of a two-dimensional gain map or a parameterized radial gain model, determine whether the initial gain value is below a threshold, determine a maximum RGB triplet value for the image data where the initial gain value is below the threshold, determine a pixel intensity as output of a function for saturation management, determine a final gain value for the image data based on the maximum RGB triplet value and the pixel intensity, apply the final gain value against the image data to produce processed image data, and output the processed image data for further processing using the image processor.

Abstract: A system and/or method configured to determine highlight segments. Content files that define content in a content segment set may be obtained. A highlight segment set may be determined from the content segment set. Determining the highlight segment set may include iterating (a)-(c) for multiple iterations. At (a), individual content segments included in the content segment set may be selected as a selected content segment for inclusion in the highlight segment set. At, (b) diversity scores for content segments that are (i) included in the content segment set and (ii) not yet selected for inclusion in the highlight segment set may be determined. At (c), one or more of the content segments may be disqualified for inclusion in the highlight segment set for future iterations based on the diversity scores.

Abstract: A video edit of first video content and second video content may be generated based on the fields of view of the first video content and the second video content. Based on the fields of view of the first video content and the second video content, a first viewing window for the first video content and a second viewing window for the second video content may be determined. The viewing windows may define one or more extents of the corresponding visual content. The video edit may include a punchout of the first video content based on the first viewing window and a punchout of the second video content based on the second viewing window.

Abstract: Systems and methods are disclosed for non-local means denoising of images. For example, methods may include receiving an image from an image sensor; determining a set of non-local means weights for the image; applying the set of non-local means weights to the image to obtain a first denoised image; applying the set of non-local means weights to the first denoised image to obtain a second denoised image; and storing, displaying, or transmitting an output image based on the second denoised image.

Abstract: Apparatus and methods for characterizing panoramic content, such as by a wide field of view and large image size. In one implementation, a panoramic image may be mapped to a cube or any other projection e.g icosahedron or octahedron. The disclosure exploits content continuity between facets, such as in the case of encoding/decoding cube-projected images. One facet may be encoded/decoded independently from other facets to obtain a seed facet. One or more transformed versions of the seed facet may be obtained; e.g., one corresponding to a 90° counterclockwise rotation, another to a 90° clockwise rotation, and one to an 180° rotation. Transformed versions may be used to form an augmented image. The remaining facets of the cube may be encoded using transformed versions within the augmented image.

Abstract: A video set of one or more videos may include video content having a progress length. The video content may be segmented into a sequence of video content segments. The sequence of video content segments may be provided for presentation on a display as individual video clips. Individual video content segments may be provided as individual video clips.

Abstract: Multiple videos having individual time durations may be obtained, including a first video with a first time duration. The videos may include visual information defined by one or more electronic media files. An initial portion of the first time duration where the one or more electronic media are to be transcoded may be determined, including determining whether the first time duration is greater than a predefined threshold and if the first time duration is greater than the predefined threshold, determining the initial portion to be an initial time duration that is less than the first time duration. One or more transcoded media files may be generated during the initial portion. A request for the first video may be received from a client computing platform. In response to receipt of the request, the one or more transcoded media files may be transmitted to the client computing platform for display.

Abstract: An unmanned aerial vehicle manages storage of data and transfer between other connected devices. The unmanned aerial vehicle captures sensor data from sensors on the unmanned aerial vehicle. The unmanned aerial vehicle transfers the captured sensor data from the unmanned aerial vehicle to a remote controller via a wireless interface. The captured data may be transferred via a TCP link, a UDP link, or a combination thereof. If a loss of link is detected, the captured sensor data is stored to a buffer and a battery level of the unmanned aerial vehicle and a flight status of the unmanned aerial vehicle is monitored. The stored sensor data is transferred from the buffer to a non-volatile storage responsive to the battery level dropping below a predefined threshold or detecting that the unmanned aerial vehicle is stationary and a shutdown may be imminent.

Abstract: A frame rate is synchronized to a detected cadence in order to generate an output image sequence that is substantially stabilized. In an in-camera process, a camera receives motion data of the camera while the camera captures the sequence of image frames. A dominant frequency of motion is determined and the capture frame rate is dynamically adjusted to match the frequency of detected motion so that each image frame is captured when the camera is at approximately the same position along the axis of motion. Alternatively, in a post-processing process, frames of a captured image sequence are selectively sampled at a sampling rate corresponding to the dominant frequency of motion so that each sampled frame corresponds to an image capture that occurred when the camera is at approximately the same position along the axis of motion.

Abstract: A method for tracking a subject in successive image frames includes obtaining previous image frames with an imaging device, processing the previous image frames, obtaining motion information of the imaging device and a subject, determining a region of interest, obtaining a subsequent image frame, and processing the region of interest. The processing includes determining previous frame positions of the subject therein. The motion information is obtained with sensors physically associated with one or more of the imaging device and the subject. The region of interest is located in a predetermined spatial relationship relative to a predicted frame position of the subject.

Abstract: Vehicles such as unmanned air vehicles that are capable of movement from an open, flight configuration to an enclosed configuration in which all major flight components can be protected by an outer shell are disclosed. In the enclosed configuration, the vehicles can take on standard geometric shapes such as a rectangular prism, sphere, cylinder, or another shape, so as to not be recognizable as an unmanned air vehicle. Embodiments of vehicles can also include interchangeable and/or wireless motor arms, motor arms which are electrically connected to the remainder of the vehicle only when in an open configuration, remote controllers removably attached to the remainder of the vehicle, and clip or other attachment mechanisms for attachment to objects such as backpacks.

Abstract: Image signal processing may include flare reduction, which may include obtaining a first input frame captured by a first image capture device of an image capture apparatus, the first image capture device having a first field-of-view, and the first input frame including lens flare corresponding to a primary light source; obtaining a second input frame captured by a second image capture device of the image capture apparatus, the second image capture device having a second field-of-view partially overlapping the first field-of-view; obtaining primary light source information corresponding to the primary light source based on the first input frame and the second input frame; obtaining a processed frame by modifying the first input frame based on the primary light source information to minimize the lens flare; and outputting the processed frame.

Abstract: A variable pitch propeller is designed to adjust the pitch of the propeller blade during flight to maximize the propeller efficiency. The propeller blade may comprise airfoil cross-sections. Each cross-section may be composed of different materials at the leading edge and trailing edge. In various embodiments, these materials are selected and oriented to achieve the necessary elastic moduli of the leading and trailing edge for the airfoil cross-section. During liftoff, the airfoil at the blade tip possesses a high blade pitch (e.g. 20 degrees), thereby increasing the generated lift on the propeller blades. During flight or hover conditions when maximal lift is no longer required, the trailing edge of the airfoil displaces upward and reduces the blade pitch to minimize the drag forces on the blade tip.

Abstract: Physical storage media accessible to a remote device may store video information defining video content. The video content may be characterized by capture information. The remote device may transmit at least a portion of the capture information to a computing device. The computing device may identify one or more portions of the video content based on the transmitted capture information. The remote device may receive the identification of the identified portion(s) of the video content from the computing device. Responsive to the reception of the identification, the remote device may transmit the video information defining at least some of the identified portion(s) of the video content to the computing device.

Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include receiving a first image from a first image sensor; receiving a second image from a second image sensor; stitching the first image and the second image to obtain a stitched image; identifying an image portion of the stitched image that is positioned on a stitching boundary of the stitched image; and inputting the image portion to a machine learning module to obtain a score, wherein the machine learning module has been trained using training data that included image portions labeled to reflect an absence of stitching and image portions labeled to reflect a presence of stitching, wherein the image portions labeled to reflect a presence of stitching included stitching.

Abstract: A camera system includes a camera with a lens assembly and image processing electronics internal to the camera housing. The lens assembly and image processing electronics are sensitive to thermal gradients within the camera body. The image processing electronics are coupled to a thermal management system that transfers thermal energy away from the electronics towards a heat diffuser. The thermal management system comprises a heat controller with a heat source, an offset arm, and a heat exchange. The thermal energy moves from the heat source to the heat exchange via the offset arm. The thermal management system also manages heat transfer between auxiliary electronic components and the image processing electronics. The thermal management system is constructed of materials that react to the compressive forces created on the system during camera assembly.

Abstract: Media items may be obtained. The media items may be characterized by capture information indicating a capture time and a capture location of individual media items. The media items may be clustered into scenes based on proximity of the capture times of the media items. The scenes may be clustered into collections based on proximity of the capture times and/or the capture locations of the media items within the scenes. The collections may be iteratively clustered into higher collections based on proximity of the capture times and/or the capture locations of the media items within the collections. One or more collections may be identified for inclusion in a media compilation based on a size of the identified collection(s). A media compilation, including one or more of the media items included in the identified collection(s), may be generated.

Abstract: Implementations are directed to providing a digital media editing environment for editing at least a portion of a digital video using a mobile device, establishing communication between the mobile device and a data source, receiving, from the data source, a first portion of the digital video, the first portion including a first set of frames including less than all frames of the digital video, applying an edit to the first portion of the digital video, while less than all frames of the first digital video are stored on the mobile device, subsequent to applying the at least one edit, receiving, from the data source, a second portion of the digital video, the second portion including a second set of frames, and storing an edited digital video including at least one frame of the first set of frames, at least one frame of the second set of frames, and the edit.

Abstract: First video information defining first video content may be accessed. The first video content may have been captured by a first image sensor from a first conveyance position. Second video information defining second video content may be accessed. The second video content may have been captured by a second image sensor from a second conveyance position. A first highlight criterion may be selected for the first video content based on the first conveyance position. A second highlight criterion may be selected for the second video content based on the second conveyance position. A first set of highlight moments within the first video content may be identified based on the first criterion. A second set of highlight moments within the second video content may be identified based on the second criterion. The identification of the first set of highlight moments and the second set of highlight moments may be stored.

Abstract: Spherical visual content represented in an image space may be obtained. The spherical visual content may have been captured by image sensor(s) during a time duration. The spherical visual content may include phenomena caused by motion of the image sensor(s) and/or optical components that guide light onto the image sensor(s). A capture path taken by the image sensor(s) during the time duration may be determined. The capture path may reflect positions and orientations of the image sensor(s) during the time duration. A smoothed path may be determined based on the capture path. The smoothed path may have smoother changes in positions and/or orientations than the capture path. The image space may be warped based on a difference between the capture path and the smoothed path. The stabilized visual content may be determined by projecting the spherical visual content represented in the warped image space to a spherical projection space.

Abstract: A processing device generates composite images from a sequence of images. The composite images may be used as frames of video. A foreground/background segmentation is performed at selected frames to extract a plurality of foreground object images depicting a foreground object at different locations as it moves across a scene. The foreground object images are stored to a foreground object list. The foreground object images in the foreground object list are overlaid onto subsequent video frames that follow the respective frames from which they were extracted, thereby generating a composite video.