Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include receiving an image from an image sensor; applying a filter to the image to obtain a low-frequency component image and a high-frequency component image; determining a first enhanced image based on a weighted sum of the low-frequency component image and the high-frequency component image, where the high-frequency component image is weighted more than the low-frequency component image; determining a second enhanced image based on the first enhanced image and a tone mapping; and storing, displaying, or transmitting an output image based on the second enhanced image.

Abstract: An image capture device is described that includes a body; a mounting structure that is connected to the body; an integrated sensor-lens assembly (ISLA) that defines an optical axis and extends through the body and the mounting structure; and an accessory that is releasably connectable to the mounting structure via rotation through a range of motion less than approximately 90 degrees. The mounting structure and the accessory include corresponding angled bearing surfaces that are configured for engagement such that rotation of the accessory relative to the mounting structure creates a bearing effect that displaces the accessory along the optical axis to thereby reduce any axial force required during connection and disconnection of the accessory.

Abstract: Depiction of a physical whiteboard may be captured by an image capture device. The depiction of the physical whiteboard may be detected and used to generate a virtual whiteboard. A change in the depiction of the physical whiteboard may be detected and used to change the virtual whiteboard. A virtual change to the virtual whiteboard may be received and used to change the virtual whiteboard. The change to the virtual whiteboard based on the virtual change may be projected on top of the physical whiteboard.

Abstract: Methods and apparatus for multi-encoder processing of high resolution content. In one embodiment, the method includes capturing high resolution imaging content; splitting up the captured high resolution imaging content into respective portions; feeding the split up portions to respective imaging encoders; packing encoded content from the respective imaging encoders into an A/V container; and storing and/or transmitting the A/V container. In another embodiment, the method includes retrieving and/or receiving an A/V container; splitting up the retrieved and/or received A/V container into respective portions; feeding the split up portions to respective imaging decoders; stitching the decoded imaging portions into a common imaging portion; and storing and/or displaying at least a portion of the common imaging portion.

Abstract: A user interface of an image capture device may provide options for a user to schedule future capture of visual content by the image capture device. The user may interact with the options to specify the start time and the capture duration for the future capture of visual content. Information on scheduled future capture of visual content may be presented on one or more displays.

Abstract: Pose of a person depicted within a video may be determined. The pose of the person depicted within the video may be used to edit the video. Visual effects may be applied to the video based on the pose of the person depicted within the video. Timing of the video may be remapped to timing of music providing accompaniment for the video edit.

Abstract: A camera system includes a camera and a camera case. The camera includes a lens on a front side thereof, a rear display screen on a rear side thereof, and a mount on a bottom side thereof. The camera case is formed of a compliant foam material that defines a cavity in which the camera is removably received, a front opening that allows light to pass to the front lens, a rear opening through which the rear display screen is visible, and a mount opening through which the mount extends. The camera case includes a sufficient amount of the compliant foam material for the camera system to float in water. The camera case may extend rearward from the rear side of the camera further than the camera case extends from the front side, the rear side, a top side, a left side, and a right side of the camera.

Abstract: A camera mount, comprising: a base and a bottom. The bottom is movably connected to the base. The bottom includes recesses configured to receive flexible fasteners. The bottom and the base are movable to a closed position where the recesses are inaccessible and the flexible fasteners are held between the base and the bottom and an open position where the recesses are exposed so that the flexible fasteners are at least one of insertable, removable, or interchangeable.

Abstract: An image capture device having a housing and a heatsink. The image capture device includes an integrated sensor and lens assembly. The heatsink is located partially or completely within the housing. The heatsink includes a through which a portion of the integrated sensor and lens assembly extends, and a planar surface located adjacent to the cutout. The planar surface includes a front side and a rear side. A printed circuit board in communication with a rear side of the planar surface of the heatsink. An LCD recess located in a front side of the planar surface of the heatsink that is configured to receive a liquid crystal display, wherein the LCD recess is opposite the printed circuit board.

Abstract: Apparatus and methods for optimized stitching of overcapture content. In one embodiment, the optimized stitching of the overcapture content includes capturing the overcapture content; producing overlap bands associated with the captured overcapture content; downsampling the produced overlap bands; generating derivative images from the downsampled overlap bands; generating a cost map associated with the generated derivative images; determining shortest path information for the generated cost map; generating a warp file based on the determined shortest path information, the generated warp file being utilized for the optimized stitching of the overcapture content. Camera apparatus and a non-transitory computer-readable apparatus are also disclosed.

Abstract: A camera mode to use for capturing an image or video is selected by estimating high dynamic range (HDR), motion, and light intensity with respect to a scene of the image or video to capture. An image capture device includes a HDR estimation unit to detect whether HDR is present in a scene of an image to capture, a motion estimation unit to determine whether motion is detected within the scene, and a light intensity estimation unit to determine whether a scene luminance for the scene meets a threshold. A mode selection unit selects a camera mode to use for capturing the image based on output of the HDR estimation unit, the motion estimation unit, and the light intensity estimation unit. An image sensor captures the image according to the selected camera mode.

Abstract: An image capture device (100) is disclosed that includes a body (102) and a door assembly (400) that is configured for removable connection to the body (102). The door assembly (400) includes a door body (500); a locking mechanism (600) that is slidable in relation to the door body (500) between a locked position and an unlocked position; and at least one biasing member (700) that is configured for engagement (contact) with the door body (500) and the locking mechanism (600) to automatically move the locking mechanism (600) into the locked position upon closure of the door assembly (400).

Abstract: Apparatus and methods for the non-uniform downsampling of captured panoramic images. In one embodiment, a computing device is disclosed that includes a processing apparatus and a non-transitory computer readable apparatus comprising a storage medium have one or more instructions stored thereon. The one or more instructions, when executed by the processing apparatus, being configured to: receive captured images, the captured images obtained using two or more image sensors; non-uniformly downsample the received captured images; and encode the non-uniformly downsampled images. In some variants, the non-uniformly downsampled images take into account a desired area of interest within the captured images. In some implementations, the computing device includes an image capture device. Methods and non-transitory computer readable apparatus are also disclosed.

Abstract: Before capture of images, capture aspects of image capture devices (e.g., movement of image capture devices, sounds around image capture devices, GPS times of image capture devices) may be used to identify matching clock times of the image capture devices. Start of image capture by the image capture devices may be restricted using the matching clock times to time-synchronize images captured by different image capture devices.

Abstract: An integrated mobile device enclosure which encloses a mobile device includes features configured to enhance the capturing and/or processing of content at the mobile device. An integrated mobile device enclosure may include a body configured to enclose at least a portion of a mobile device, one or more microphones configured to capture sound external to the mobile device, and one or more lights configured to support a camera of the mobile device. The one or more microphones and the one or more lights are used with a software application running on the mobile device for content capture and/or processing. The software application in at least some cases may selectively enable or disable ones of the microphones and/or lights based on environmental information measured within a location of the mobile device.

Abstract: An image capture device may switch operation between a spherical capture mode or a non-spherical capture mode. Operation of the image capture device in the spherical capture mode includes generation of spherical visual content based on the visual content generated by multiple image sensors. Operation of the image capture device in the non-spherical capture mode includes generation of non-spherical visual content based on visual content generated by a single image sensor.

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. A video summary can be generated including one or more of the identified best scenes. The video summary can be generated using a video summary template with slots corresponding to video clips selected from among sets of candidate video clips. Best scenes can also be identified by receiving an indication of an event of interest within video from a user during the capture of the video. Metadata patterns representing activities identified within video clips can be identified within other videos, which can subsequently be associated with the identified activities.

Abstract: Apparatus and methods for applying motion blur to overcapture content. In one embodiment, the motion blur is applied by selecting a number of frames of the captured image content for application of motion blur; selecting a plurality of pixel locations within the number of frames of the captured image content for the application of motion blur; applying motion blur to the captured image content in accordance with the selected number of frames and the selected plurality of pixel locations; and outputting the captured image content with the applied motion blur. In some implementations, motion blur is applied via implementation of a virtualized neutral density filter. Computerized devices and computer-readable apparatus for the application of motion blur are also disclosed.

Abstract: Video information may define video content. The video content may be characterized by capture information. A 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. The remote device may stream one or more portions of the video information defining at least some of the identified portion(s) of the video content to the computing device. The streamed video information may enable the computing devices to provide a presentation of at least some of the identified portion(s) of the video content using a buffer of the streamed video information, which may allow the computing device to present the video content without permanently storing the video information.

Abstract: Implementations of a mobile platform for image capture device control may use voice recognition. A user may use a mobile platform, such as a mobile application, on a mobile device to interpret and relay voice commands to an image capture device. Voice recognition services may be integrated into the mobile application, the mobile device operating system (OS), or both.

Abstract: An image capture device may include a touchscreen display, which may be used to receive user input. The image capture device may determine whether it is under water based on analysis of visual content captured by the image capture device. Responsive to determination that it is under water, the image capture device may change operation with respect to the touchscreen display.

Abstract: Methods and apparatus for seamlessly transitioning between lens projections. In one exemplary embodiment, a piecewise lens projection is composed of three (3) functions: (i) a first polynomial-based lens projection, (ii) a second “joining” lens projection, and (iii) a trigonometric lens projection. The piecewise lens projection characterizes virtualized lens distortion as a function of FOV; image data can be dynamically projected based on the virtualized lens distortion, regardless of FOV. In this manner, a user may achieve the visually familiar effects associated with a first lens definition for a first FOV, while still smoothly animating transitions to other lens projections (e.g., a larger FOV using stereographic projections).

Abstract: Reducing artifacts in decoded images includes decoding a first facet of an image, where the first facet includes first edge pixels. A second facet of the image that includes second edge pixels is decoded. The first edge pixels are not adjacent to the second edge pixels and the second facet is decoded independently of the first facet. The first edge pixels are copied to an area adjacent to the second edge pixels. The second edge pixels are filtered using the copied first edge pixels. The second edge pixels are copied to an area adjacent to the first edge pixels. The first edge pixels are filtered using the copied second edge pixels.

Abstract: Image captured through a non-rectilinear lens may exhibit distortions. The distortions may be reduced by warping the image. However, warping the image may degrade the fidelity of the image. The warped image may be enhanced to increase the fidelity of the image. The enhancement may be applied to the portions of the image that were degraded from the warping.

Abstract: Apparatus and methods for the stitch zone calculation of a generated projection of a spherical image. In one embodiment, a computing device is disclosed which includes logic configured to: obtain a plurality of images; map the plurality of images onto a spherical image; re-orient the spherical image in accordance with a desired stitch line and a desired projection for the desired stitch line; and map the spherical image to the desired projection having the desired stitch line. In a variant, the desired stitch line is mapped onto an optimal stitch zone, the optimal stitch zone characterized as a set of points that defines a single line on the desired projection in which the set of points along the desired projection lie closest to the spherical image in a mean square sense.

Abstract: Image capture devices and methods may use field variable tone mapping for 360 content. An image capture device may comprise an image sensor and a processor. The image sensor may capture a hyper-hemispherical image that includes an image circle portion. The processor may perform local tone mapping (LTM) on a first area of the image circle portion and perform global tone mapping (GTM) on a second area of pixels of the image circle portion. The GTM may be performed on a condition that a portion of a predefined area of pixels overlaps with a stitch line. The processor may be configured to stitch the hyper-hemispherical image and a second hyper-hemispherical image at the stitch line to obtain a processed image. The processor may be configured to display, store, output, or transmit the processed image.

Abstract: An image or a video may include a spherical capture of a scene. A punchout of the image or the video may be generated by placement of a viewing window at a center of a two-dimensional plane onto which the image or the video is mapped. The punchout of the image or the video may provide a panoramic view of the scene.

Abstract: Information may be visually encoded within visual content of an image using a distortion projection. The distortion projection may cause stretching of a visual element defined within a pixel array of the image. Information may be visually encoded within the pixel array using visual characteristic(s) of the pixel array. Presentation of the visual content based on a non-distortion projection may reduce a number of pixels that defines the visual element within the pixel array and may reduce visual impact of the information visually encoded within the pixel array.

Abstract: A graphical user interface may switch between presentation of a timeline representation of media items and a tile representation of media items. The timeline representation may include graphical representation of the lengths of the media items. The tile representation may include graphical representation of the content of the media items.

Abstract: Systems, apparatus, and methods for super-resolution of non-uniform spatial blur. Non-uniform spatial blur presents unique challenges for conventional neural network processing. Existing implementations attempt to handle super-resolution with a “brute force” optimization. Various embodiments of the present disclosure subdivide the super-resolution function into sub-steps. “Unfolding” super-resolution into smaller closed-form functions allows for operation generic plug-and-play convolutional neural network (CNN) logic. Additionally, each step can be optimized with its own step-specific hyper parameters to improve performance.

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: Apparatus and methods for stitching images, or re-stitching previously stitched images. Specifically, the disclosed systems in one implementation save stitching information and/or original overlap source data during an original stitching process. During subsequent retrieval, rendering, and/or display of the stitched images, the originally stitched image can be flexibly augmented, and/or re-stitched to improve the original stitch quality. Practical applications of the disclosed solutions enable, among other things, a user to create and stitch a wide field of view (FOV) panorama from multiple source images on a device with limited processing capability (such as a mobile phone or other capture device). Moreover, post-processing stitching allows for the user to convert from one image projection to another without fidelity loss (or with an acceptable level of loss).

Abstract: A graphical user interface may provide presentation of a video edit during video edit playback. The video edit may include a segment of a video. When a user modifies the segment of the video included in the video edit, the graphical user interface may automatically switch the presentation of the video edit into presentation of the original video.

Abstract: A camera, having: microphones including: a first microphone; and a second microphone. The camera including a sensor controller. The sensor controller being configured to receive audio, select between the microphones, and record the audio. The sensor controller receives the audio inputs from the first microphone and the second microphone. The sensor controller selects the first microphone or the second microphone based on the audio inputs so that one of the first and second microphones is a selected microphone, wherein the selected microphone receives the audio input having the lowest level of background noise within a predetermined frequency range associated with background noise. The sensor controller records audio data from only the selected microphone.

Abstract: An unmanned aerial vehicle (“UAV”), the UAV including an electronic speed controller and a flight controller. The electric speed controller is interfaced with thrust motors of the UAV. The flight controller is configured to: determine a geographic location and a velocity of the UAV. The flight controller configured to: determine a distance between the geographic location of the UAV and a closest segment of a no-fly-zone. The flight controller in response to the distance being less than a threshold distance, control a speed and thrust applied by the thrust motors through the electric speed controller to reduce both the first component and the second component of the velocity of the UAV based on the distance. The flight controller configured to: override a user input received via a user interface so that the UAV is moved relative to the closest segment of a no-fly-zone according to instructions from the flight controller.

Abstract: Systems and methods for controlling an unmanned aerial vehicle are disclosed. The system comprises an image sensor configured to generate output signals conveying visual information, the visual information including one or more images of a user, and one or more physical processors. The one or more physical processors are configured by computer-readable instructions to recognize one or more gestures from the user based on the visual information, interpret the one or more gestures from the user as flight control information, and provide flight control for the unmanned aerial vehicle based on the flight control information.

Abstract: Methods and apparatus for shared image processing among multiple devices. In one embodiment, an exemplary action camera performs a partial multiband blend. Even though the action camera may not have resources to handle the multiband blend of the entire action camera's footage, it can do a significant portion. The partially blended content can be used in ready-to-share applications, or completely blended by another device.

Abstract: Auto exposure metering is adapted for spherical panoramic content. Using input image data, a first metering map is generated for a selected image sensor and a second metering map is generated for an unselected image sensor. Auto exposure level values for the selected image sensor and for the unselected image sensor are respectively metered using the first metering map and the second metering map, such as by adjusting luminance weights in certain locations of the respective image sensor panoramic image capture band. Hemispherical images are processed using the auto exposure metered level values and stitched together in a panoramic format to produce a spherical panoramic image. The metering maps are generated to account for areas of greatest image data importance relative to a primary orientation direction of the spherical panoramic image. This allows for effective auto exposure metering of such areas within the resulting spherical panoramic image.

Abstract: Video content may be captured by an image capture device during a capture duration. The video content may include video frames that define visual content viewable as a function of progress through a progress length of the video content. Rotational position information may characterize rotational positions of the image capture device during the capture duration. Time-lapse video frames may be determined from the video frames of the video content based on a spatiotemporal metric. The spatiotemporal metric may characterize spatial smoothness and temporal regularity of the time-lapse video frames. The spatial smoothness may be determined based on the rotational positions of the image capture device corresponding to the time-lapse video frames, and the temporal regularity may be determined based on moments corresponding to the time-lapse video frames. Time-lapse video content may be generated based on the time-lapse video frames.

Abstract: An image capture system and methods for auto-recording media data are herein disclosed. A method includes selecting an activity-specific monitor based on an activity type. The activity-specific monitor defines one or more auto-recording conditions that, when satisfied, cause the image capture system to record data. The auto-recording conditions are based on an audio profile, a video profile, a motion profile, or any combination thereof. The auto-recording conditions include one or more scene descriptions that correspond to the activity type.

Abstract: Systems and methods are disclosed for circular stitching of images. For example, methods may include accessing a first image captured using a first image sensor; accessing a second image captured using a second image sensor; determining a cost table for a circular stitching boundary that includes overlapping regions of the first image and the second image; determining an extended disparity profile based on a periodic extension of the cost table and a smoothness criterion, wherein the extended disparity profile has a length greater than the width of the cost table; determining a binocular disparity profile of a length equal to the width of the cost table based on a contiguous subsequence of the extended disparity profile; and stitching the first image and the second image using the binocular disparity profile to obtain a combined image.

Abstract: An image capture device includes a processor for wind noise processing. The processor receives signals from a first microphone, a first plurality of microphones, and a second plurality of microphones. The processor may segment the signals into low frequency bins and high frequency bins. The processor may select a minimum level signal bin for the low frequency bins. For the high frequency bins, the processor may select a minimum level signal bin for a first group of microphones or a second group of microphones. The processor may generate a composite signal by combining the selected minimum level signal bins for the low frequency bins and the selected minimum level signal bins for the high frequency bins.

Abstract: A video including visual content may be captured by an image capture device in motion. Stabilization performance information for the visual content may be determined. The stabilization performance information may characterize an extent to which desired stabilization is able to be performed using the visual content. The stabilization for the visual content may be changed based on the stabilization performance information.

Abstract: A method and apparatus for night lapse video capture are disclosed. The apparatus includes an image sensor, a processor, a denoiser, and an encoder. The image sensor is configured to capture image data. The image data includes a first image that is temporally precedent to a second image. The processor is configured to process the image using an image processing pipeline. The denoiser is configured to perform denoising based on a motion estimation that is based on a comparison of a portion of the first image and a portion of the second image. The encoder is configured to encode the denoised image in a video format. The encoder is configured to output a video file in the video format.

Abstract: A video may include visual content having a progress length. A user may interact with a mobile device to set framings of the visual content at moments within the progress length. The framings of the visual content may be provided to a video editing application. The video editing application may utilize the framings set via the mobile device to provide preliminary framings of the visual content at the moments within the progress length.

Abstract: An image capture device includes a first housing, a second housing, a first integrated sensor-lens assembly (ISLA), and a second ISLA. The second housing is coupled to the first housing to form an internal compartment. The first ISLA includes a first image sensor coupled to a first lens in fixed alignment. The second ISLA includes a second image sensor coupled to a second lens in fixed alignment. The first ISLA is positively statically connected to the first housing, and the second ISLA is coupled to the first housing indirectly via the first ISLA.