Abstract: A non-transitory computer-readable storage medium stores executable instructions that, when executed by a processor, cause performance of operations comprising operations to access an image captured by an image sensor, obtain a transfer function for mapping pixel values, determine a faces indication that reflects a proportion of a scene depicted in the image that includes one or more human faces, and modify the transfer function based on the faces indication. Modifying the transfer function based on the faces indication comprises adjusting a gain of the transfer function to move the gain closer to unity. The operations include to apply the transfer function to pixel values of the image to produce a tone mapped image and output the tone mapped image.

Abstract: Systems, apparatus, and methods for augmenting dense depth maps using sparse data. Various embodiments combine single-image depth estimation (SIDE) techniques with structure-from-motion techniques for improved depth accuracy. In some examples, a machine learning (ML) model is used to generate a dense depth map based on one or more frames/images of a video. Structure-from-motion (SfM) analysis is performed on the video to determine depth information from camera movement in the video. The structure-from-motion techniques may generate more accurate data than the ML model, however, the data from the ML model may be denser compared with the SFM depth data. The dense ML model depth map may be augmented by the SFM depth data. Augmentation may include fitting the relative depths determined by the ML model depth map to the absolute depth in the SFM data resulting in more accurate dense depth information.

Abstract: The present teachings provide a camera housing that includes a first housing portion, a second housing portion, a hinge, a latch mechanism, and protrusions. The first housing portion forms a first portion of a cavity. The second housing portion forms a second portion of the cavity The hinge is located within the first housing portion so that the first housing portion is divided into a first piece and a second piece. The hinge movably connects the first housing portion to the second housing portion so that the second housing portion is movable relative to the first housing. The latch mechanism is movable between an open position and a closed position. The protrusion extend from a third housing portion, and the third housing portion is located opposite the first housing portion with respect to the cavity.

Abstract: A first device includes a processor and instructions. The instructions, when executed by the processor, cause the processor to configure the first device to receive network credentials; accept a connection request from a second device to connect to the first device; obtain the network credentials from the second device; configure the first device to connect to a third device subsequent to obtaining the network credentials; and transmit a request to connect to the third device, where request includes the network credentials.

Abstract: An unmanned aerial vehicle including a housing, a first front arm, a first back arm, a second front arm, and a second back arm. The first front arm has an end at a first elevational plane when in a closed position. The first back arm has an end at a second elevational plane when in the closed position, the second elevational plane higher than the first elevational plane to provide an offset. The second front arm has an end at the first elevational plane when in the closed position. The second back arm has an end at the second elevational plane when in the closed position, the second elevational plane higher than the first elevational plane to provide the offset.

Abstract: An image capture device may process first frames from a first image sensor obtained at a first frame rate and store the processed first frames in a memory. The image capture device may obtain first camera control statistics based at least on partially processed second frames from a second image sensor obtained at a second frame rate. The image capture device may switch a capture mode to obtain third frames at the second frame rate from the first image sensor and to obtain fourth frames at the first frame rate from the second image sensor.

Abstract: In one aspect of the present disclosure, a digital image capturing device (DICD) is disclosed that includes a device body with a printed circuit board (PCB), and an integrated sensor-lens assembly (ISLA) that is configured for releasable connection to the device body. The PCB defines a plurality of openings that extend therethrough and includes a plurality of connector pins that are fixedly positioned within the openings. The ISLA includes at least one connective surface that is configured for contact with the connector pins to establish electrical communication between the device body and the ISLA.

Abstract: Video frames of a video may be marked with visual patterns to identify individual video frames. The video may be changed by applying one or more effects to the video. The accuracy with which the changes were made to the video by the effect(s) may be determined using the visual patterns marked on the video frames.

Abstract: Auto exposure processing for spherical images improves image quality by reducing visible exposure level variation along a stitch line within a spherical image. An average global luminance value is determined based on luminance values determined for first and second images, which are based on auto exposure configurations of first and second image sensors used to obtain those first and second images. Delta luminance values are determined for the first and second images using the average global luminance value. The first and second images are then updated using the delta luminance values, and the updated first and second images are used to produce a spherical image.

Abstract: An image capture device is disclosed that includes: a body; first and second image capture devices supported within the body so as to define respective, overlapping first and second fields-of-view; and a thermal spreader. The first image capture device includes a first integrated sensor-lens assembly (ISLA) with a first image sensor and a first lens, and the second image capture device includes a second ISLA with a second image sensor and a second lens. The first lens faces in a first direction, and is positioned to receive and direct light onto the first image sensor, and the second lens faces in a second direction, and is positioned to receive and direct light onto the second image sensor, wherein the second direction is generally opposite to the first direction. The thermal spreader extends between, and is connected to, the first and second ISLAs, and is configured to transfer heat therebetween.

Abstract: A video edit may include one or more segment of a video. A graphical user interface may convey information that indicates video editing decisions made to generate the video edit. The graphical user interface may include a timeline element to represent the length of the video and one or more inclusion elements to visually indicate the segment(s) of the video included in the video edit. The graphical user interface may convey information on the segment(s) of the video that have been automatically included in the video edit and the segment(s) of the video that have been manually included in the video edit.

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: A device includes a mechanical stabilization system is used in image signal processing. The mechanical image stabilization system has an operating bandwidth and includes a motor to control an orientation of an image sensor. A processing apparatus of the device determines a temperature of the motor and adjusts a cutoff frequency of the operating bandwidth based on the temperature of the motor.

Abstract: A handheld module including a battery, an electro-mechanical interface, and a display. The electro-mechanical interface is configured to attach the handheld module to an image capture module, wherein when attached to the image capture module, the handheld module forms a communication link to the image capture module via the electro-mechanical interface and supplies power from the battery to the image capture module via conductors of the electro-mechanical interface. The display is configured to present images captured by the image capture module and received from the image capture module via the communication link.

Abstract: Apparatus and methods for the stitch zone calculation of a generated projection of a spherical image. In one embodiment, a non-transitory computer-readable apparatus comprising a storage apparatus, the storage apparatus comprising instructions configured to, when executed by a processor apparatus, cause a computerized apparatus to identify a stitch line associated with an equatorial area of a plurality of spherical images; re-orient the plurality of spherical images in accordance with the stitch line; and project the re-oriented plurality of spherical images to a selected image projection type.

Abstract: An image capture device may capture two hemispherical views of a scene. The two hemispherical view of the scene may be stitched along a stitch line. The image capture device may be rotated to align the stitch line with a mid-line of a panoramic field of view of the scene. Separate exposure settings may be used to capture the two hemispherical views of the scene, with the exposure settings increasing the dynamic range of the scene depicted within the panoramic field of view of the scene. The panoramic field of view of the scene may be punched out as panoramic visual content.

Abstract: Disclosed is an electronic gimbal with camera and mounting configuration. The gimbal can include an inertial measurement unit which can sense the orientation of the camera and three electronic motors which can manipulate the orientation of the camera. The gimbal can be removably coupled to a variety of mount platforms, such as an aerial vehicle, a handheld grip, or a rotating platform. Moreover, a camera can be removably coupled to the gimbal and can be held in a removable camera frame. Also disclosed is a system for allowing the platform, to which the gimbal is mounted, to control settings of the camera or to trigger actions on the camera, such as taking a picture, or initiating the recording of a video. The gimbal can also provide a connection between the camera and the mount platform, such that the mount platform receives images and video content from the camera.

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: Described is an image capture device which provides substantially immediate indications to a user that an image capture device is on after the user has turned on the image capture device. The image capture device can include a processor and a low power processor. The low power processor can perform or initiate multiple substantially parallel processes upon detection of an image capture device power on event. In some implementations, the low power processor can initiate a boot-up process for the processor and a light emitting device (LED) power on process for a LED indicator. In some implementations, the low power processor can initiate a boot-up process for the processor, a LED power on process for a LED indicator, and a battery authentication process for a battery inserted in the image capture device.

Abstract: Tone mapping for image capture may include accessing a first image detected using an image sensor; accessing an exposure parameter (exposure duration, or time, multiplied by ISO or gain) used to detect the first image; scaling pixel values of the first image by a scale factor inversely proportional to the exposure parameter to obtain a scaled image; determining a scene luminance based on an average of pixel values of the scaled image; determining a target luminance based on the scene luminance; determining a target histogram based on the target luminance; determining a first histogram of luminance values of the first image; determining a transfer function based on the first histogram and the target histogram; applying the transfer function to pixel values of the first image to produce a tone mapped image; and storing or transmitting an output image based on the tone mapped image.

Abstract: Field variable tone mapping is performed for 360 content. An image capture device includes an image sensor and a processor. The image sensor obtains a hyper-hemispherical image and the processor performs local tone mapping (LTM) on a first area of the hyper-hemispherical image and performs global tone mapping (GTM) on a second area of the hyper-hemispherical image to obtain a processed image. The processor may be configured to display, store, output, or transmit the processed image.

Abstract: Systems and methods are disclosed for high dynamic range processing based on angular rate measurements. For example, methods may include receiving a short exposure image that was captured using an image sensor; receiving a long exposure image that was captured using the image sensor; receiving an angular rate measurement captured using an angular rate sensor attached to the image sensor during exposure of the long exposure image; determining, based on the angular rate measurement, whether to apply high dynamic range processing to an image portion of the short exposure image and the long exposure image; and responsive to a determination not to apply high dynamic range processing to the image portion, selecting the image portion of the short exposure image for use as the image portion of an output image and discard the image portion of the long exposure image.

Abstract: An image capture device with a housing, a drainage microphone, processor, and drainage channel. The housing defining an audio depression. The drainage microphone coupled to the housing at a location of the audio depression and configured to capture audio. The processor coupled with a memory storing instructions that when executed cause the processor to apply a set of tuned beamforming parameters to the captured audio. The drainage channel within the housing to drain moisture from the drainage microphone. The drainage channel defining a channel entrance having a channel entrance width and a channel entrance height.

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: Systems and methods are disclosed for dynamic power allocation for memory using multiple interleaving patterns. For example, a system may include a set of memory devices, including a first subset and a second subset, and a memory management circuitry configured to translate virtual addresses into physical addresses of memory locations in the set of memory devices using a first interleaving pattern when operating in a first mode; and translate virtual addresses using a second interleaving pattern when operating in a second mode. The first and second interleaving patterns both map virtual addresses in a first range exclusively to memory devices in the first subset. The first interleaving pattern maps virtual addresses in a second range to memory devices in the first subset and in the second subset. The second interleaving pattern maps virtual addresses in the second range exclusively to memory devices in the first subset.

Abstract: Face detection in a spherical image is performed using overcapture. Multiple views of a spherical image are separately processed using face detection, and results of the face detection for those views are projected to a format for further processing of the spherical image.

Abstract: An accessory for an image capture device is disclosed that includes: a body; a rotatable first support that is configured for connection to the image capture device; a second support that is pivotably reconfigurable between stowed and deployed configurations; and a third support including first and second legs that are pivotably connected to the body such that the third support is reconfigurable between collapsed and expanded configurations. In the stowed configuration, the second support is concealed within the body, and in the deployed configuration, the second support extends outwardly from the body to facilitate connection of the accessory to an ancillary product. In the collapsed configuration, the third support defines a grip for the image capture device, and in the expanded configuration, the body defines a third leg that cooperates with the first and second legs to provide a freestanding base for the image capture device.

Abstract: A camera mount, comprising: a body, one or more magnets, and one or more pins. The one or more magnets located within the body and configured to connect to a magnetic portion or a ferromagnetic portion of a camera. The one or more pins that extend axially outward from the body above the one or more magnets and are configured to extend into recesses within the camera.

Abstract: An image capture device continuously generates time-lapse video frames to be included within a time-lapse video using a dynamic time-lapse video frame rate, with the value of the dynamic time-lapse video frame rate changing based on activation of a trigger to change the dynamic time-lapse video frame rate. The dynamic time-lapse video frame rate alternates between different values.

Abstract: An image capture device may receive GPS data during capture of video frames. GPS data may be used to increase accuracy of GPS time of the image capture device. GPS time of the image capture device at a later moment in the capture duration may be used to determine the times of earlier captured video frames.

Abstract: Systems and processes for cameras with a reconfigurable lens assembly are described. For example, some methods include automatically detecting that an accessory lens structure has been mounted to an image capture device including a mother lens and an image sensor configured to detect light incident through the mother lens, such that an accessory lens of the accessory lens structure is positioned covering the mother lens; responsive to detecting that the accessory lens structure has been mounted, automatically identifying the accessory lens from among a set of multiple supported accessory lenses; accessing an image captured using the image sensor when the accessory lens structure is positioned covering the mother lens; determining a warp mapping based on identification of the accessory lens; applying the warp mapping to the image to obtain a warped image; and transmitting, storing, or displaying an output image based on the warped image.

Abstract: Systems, apparatus, and methods for real-time guided encoding. In one exemplary embodiment, an image processing pipeline (IPP) is implemented within a system-on-a-chip (SoC) that includes multiple stages, ending with a codec. The codec compresses video obtained from the previous stages into a bitstream for storage within removable media (e.g., an SD card), or transport (over e.g., Wi-Fi, Ethernet, or similar network). While most hardware implementations of real-time encoding allocate bit rate based on a limited look-forward (or look-backward) of the data in the current pipeline stage, the exemplary IPP leverages real-time guidance that was collected during the previous stages of the pipeline.

Abstract: Disclosed herein are implementations of a cooling apparatus for use with a battery or battery pack. The battery may be a lithium-ion battery, and the battery pack may be two or more lithium-ion batteries. A cooling apparatus may include a heatsink. The heatsink may have a clearance portion configured to allow expansion of the lithium-ion battery. The cooling apparatus may include a metal plate coupled to the heatsink. The heatsink may be configured to contact the battery on at least three sides.

Abstract: A video may include a capture of a scene, such as a wide-field of view capture of the scene. Context of the video may be assessed and used to suggest framing of the video. The framing of the video may be presented within a user interface. A user may select, through the user interface, the framing to be used in generating presentation of the video.

Abstract: Systems, apparatus, and methods for encoding telemetry data as audio waveforms. Action cameras may be used to capture telemetry data, which in some applications, may be more useful than its audio/visual media capture. For example, a user may desire the “look-and-feel” of one camera but would like to use the telemetry track information from an action camera. In so-called “piggybacking” operation, the user may rigidly affix the two cameras and use the video track with the telemetry track in post-processing. Unfortunately, time-aligning the two tracks can result in relative drift over time. Various embodiments of the present disclosure transfer telemetry data as data-over-audio. The data-over-audio may be sampled according to the recipient device and recorded at capture. Subsequent post-processing may be performed with the time-aligned tracks.

Abstract: A system with an integrated internal battery, a removable battery, and a power management integrated circuit. The power management integrated circuit is configured to provide power to the image capture device from the removable battery; provide power to the image capture device from the integrated internal battery when the removable battery is disconnected from the image capture device or the removable battery does not have a sufficient charge to drive the image capture device; and recharge the integrated internal battery before the removable battery until the integrated internal battery has a sufficient charge to power the image capture device. The power is continuously supplied to the image capture device from the integrated internal battery while the removable battery is disconnected from the image capture device or does not have sufficient power to drive the image capture device.

Abstract: A video may be captured by an image capture device. A stabilized view of the video may be generated by using a punchout of the video. The shape and/or size of the punchout may be dynamically changed based on stabilization performance of the video. The shape and/or size of the punchout may be changed when the punchout is moving within the video. The shape and/or size of the punchout may not be changed when the punchout is not moving within the video.

Abstract: An image capture device reduces noise floor using multiple microphones. The image capture device includes a processor that obtains a front microphone signal from a front microphone, the front microphone signal having a noisy noise floor portion, obtains a rear microphone signal from a rear microphone, sets a splice point based on mitigation of the noisy noise floor portion relative to a speech frequency range, and combines a substantially clean noise floor portion of the rear microphone signal at or below the splice point with a remaining portion of the front microphone signal above the splice point to generate a microphone signal.

Abstract: A constraint model that includes a representation of feasible viewing window placement within a source field of view of visual content may be generated by using a roll-pitch-yaw axes representation of viewing window placement and having a diagonal dimension of the viewing window that fit within vertical and horizonal dimensions of the source field of view. The constraint model may enable full horizon leveling of the visual content.

Abstract: An image capture device may capture visual content based on a time-lapse video frame rate. Audio content may be captured along with the visual content based on the time-lapse video frame rate being a target time-lapse video frame rate. Capture of the audio content may be stopped based on the time-lapse video frame rate being different from the target time-lapse video frame rate.

Abstract: Video frames are captured by an image capture device and stabilized to generate stabilized video frames. Multiple stabilized video frames are combined into single motion blurred video frames. Combination of multiple stabilized video frames into single motion blurred video frames produces motion blur within the single motion blurred video frames that is both physical and real.

Abstract: A playback of a video may be generated to include accompaniment of music. For parts of the video that includes voice, an instrumental version of the music may be used. For parts of the video that does not include voice, a singing version of the music may be used.

Abstract: The lens attachment includes a body that overlays a lens of an image capture device and one or more lights integrated with the body that emits light in a direction so that the light is not directed into the lens of the image capture device. The lens attachment includes a connector integrated with the body that secures the lens attachment against a housing of the image capture device.

Abstract: Wind processing performance is improved by the placement of one or more microphones on a device. The device includes one or more microphones on the front surface, one or more microphones on the top surface, and one or more microphones on the rear surface. The rear surface is a heatsink, and the one or more microphones on the rear surface are located in recesses created by two or more fins of the heatsink. The device includes a processor that performs wind processing based on signals from the one or more microphones on the front surface, signals from the one or more microphones on the top surface, signals from the one or more microphones on the rear surface, or any combination thereof.