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; determining an electronic rolling shutter correction mapping for the first image and the second image; determining a parallax correction mapping based on the first image and the second image for stitching the first image and the second image; determining a warp mapping based on the parallax correction mapping and the electronic rolling shutter correction mapping, wherein the warp mapping applies the electronic rolling shutter correction mapping after the parallax correction mapping; applying the warp mapping to image data based on the first image and the second image to obtain a composite image; and storing, displaying, or transmitting an output image that is based on the composite image.

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: An image capture device may capture video frames while experiencing motion. The video frames may be stored in a visual track, and rotational positions of the image capture device may be stored in a rotational position track. The visual track and the rotational position track may not be temporally aligned. A looping stabilized view of the view frames and a synchronization adjustment option may be presented on a display. The synchronization adjustment option may enable user modification of timing of the rotational positions stored within the rotational position track. Timing modification of the rotational positions may cause changes in the looping stabilized view, which may be used as feedback on whether the synchronization between the visual track and the rotational position track is being improved or not by the timing modification of the rotational positions.

Abstract: A viewing window for a spherical video may define which extents of the spherical video are viewable. Abrupt changes in the extents defined by the viewing window may result in non-smooth views of the spherical video, such as stagger, jitter, and/or other jerky motions being included in the views of the spherical video. Changes in the extents defined by the viewing window may be smoothed to provide smoother views of the spherical video.

Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include determining a sequence of orientation estimates based on sensor data from one or more motion sensors; based on the sequence of orientation estimates, invoking a mechanical stabilization system to reject motions of an image sensor occurring within a first operating bandwidth with an upper cutoff frequency; receiving an image from the image sensor; based on the sequence of orientation estimates, invoking an electronic image stabilization module to correct the image for rotations of the image sensor occurring within a second operating bandwidth with a lower cutoff frequency to obtain a stabilized image, wherein the lower cutoff frequency is greater than the upper cutoff frequency; and storing, displaying, or transmitting an output image based on the stabilized image.

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: 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: 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 video may be captured by an image capture device in motion. A stabilized view of the video may be generated by providing a punchout of the video. The punchout of the video may compensate for rotation of the image capture device during capture of the video. The size of the punchout of the video may be changed based on different rotational positions of to provide a view that includes different extents of the captured visual content. The changes in the size of the punchout may simulate changes in zoom of the visual content.

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: A method for a zero shutter-lag (ZSL) mode of an image capture device includes, in response to detecting a first event indicative of the ZSL mode, setting the image capture device to the ZSL mode. Setting the image capture device to the ZSL mode includes setting a sensor of the image capture device to a first resolution that is higher than a second resolution of a non-ZSL mode, and setting a timer to expire after a predefined period. The method also includes, in response to the timer expiring after the predefined period, setting the image capture device to the non-ZSL mode. The non-ZSL mode cancels the ZSL mode.

Abstract: Implementations of the present disclosure are generally directed to receiving, a plurality of items of digital content from one or more data sources associated with a user, providing a plurality of clusters of digital content, each cluster including one or more items of digital content of the plurality of items of digital content, for a cluster: determining a goodness measure for each item of digital content within the cluster, the goodness measure being at least partially based on metadata associated with a respective item of digital content, and selecting at least one item of digital content from the cluster for inclusion in the media presentation, and providing the media presentation for display on a computing device of the user, the media presentation including the at least one item of digital content.

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: Systems and methods are disclosed for reducing unwanted noise during image capture. The noise may be airborne or structure-borne. For example, airborne sound may be sound that is emitted from a motor of a motorized gimbal into the air, which is then detected by a microphone of an imaging device along with the desired sound. Structure-borne noise may include vibrations from the motor that reach the microphone. Structure-borne noise may lead to local acoustic pressure variation by the microphone or pure vibration of the microphone.

Abstract: A gimbal sleeve for connecting to a camera gimbal may float between a floor surface and a ceiling surface of an aerial vehicle chassis such that the gimbal sleeve has freedom of motion in yaw, pitch, and roll directions relative to the vehicle chassis. The gimbal sleeve may comprise a pair of connection points to the lower dampers on a floor surface of the vehicle chassis. The gimbal sleeve may furthermore comprise a ball joint coupled to a back surface of the vehicle chassis. The connection points include spring forces that enable the gimbal sleeve to return to an equilibrium position in response to external vibrations and reduce the magnitude of vibrations transferred from the aerial vehicle to the gimbal and camera systems.

Abstract: Disclosed is an aerial vehicle. The aerial vehicle may include a removable battery. Various embodiments of removable battery assemblies include a pull-bar battery assembly, a latch battery assembly, and a lever battery assembly. The aerial vehicle may also include a propeller locking mechanism to which propellers may be removably coupled. The propeller locking mechanism may obviate the need for tools for coupling or decoupling propellers to the aerial vehicle. Vents in the arm of the aerial vehicle may provide an air pathway, providing convective cooling for the electronics aerial vehicle.

Abstract: A method and system for configuring a USB3 input/output port in a camera are disclosed. The method comprises responsive to an indication that a peripheral device is a non-USB3 device, remapping pins of the USB3 input/output port to a first predefined port configuration associated with an I2C protocol by remapping a RX1? pin to communicate a first I2C signal and remapping a RX1+ pin to communicate a second I2C signal, and responsive to successful authentication between the camera and the peripheral device via the I2C protocol, enabling communication with the peripheral device and remapping the pins of the USB3 input/output port to a second predefined port configuration compatible with operation of the authenticated peripheral device by remapping a TX2+ pin to communicate a first general purpose input/output signal and remapping a TX2? pin to communicate a second general purpose input/output signal.

Abstract: Implementations disclosed herein include an image capture device, a system, and a method for performing multiscale denoising of an image. An image processor of the image capture device obtains a first image. The first image may be in any format and may include noise artifacts. The image processor decomposes the first image into one or more sub-images. The sub-images may range from a coarse scale to a fine scale. In some implementations, the image processor iteratively denoises each of the one or more sub-images from the coarse scale to the fine scale. The image processor reconstructs the one or more denoised sub-images to produce a denoised image. A memory of the image capture device may be configured to store the denoised image.

Abstract: A camera system includes a camera and an underwater housing. The underwater housing, when submerged underwater, causes refraction of light entering the camera, thereby affecting focus. The camera includes a lens assembly adjustable between a first secured position at a first distance from an image sensor to enable the camera to capture images that are in focus when the camera is outside of water. The lens assembly is adjustable to a second secured position at a second distance from the image sensor to enable the camera to capture images that are in focus when the camera operates within the underwater housing and submerged under water.

Abstract: Dual-lens assemblies and cameras including dual lens-assemblies that include a first lens barrel securing a first lens having a first optical axis and a second lens barrel securing a second lens having a second optical axis are disclosed. In one dual-lens assembly, the first optical axis is approximately parallel to and spaced from the second optical axis by a lateral offset, axial lengths of the first lens barrel and the second lens barrel are approximately equal, and the first lens and the second lens are oriented in opposite directions at opposing ends of the first lens barrel and the second lens barrel.

Abstract: A motor controller of an unmanned aerial vehicle (UAV) is optimized to improve operation of the UAV. The motor control optimizations include controlling a motor of a UAV to reduce an operating temperature of the UAV, reducing an amount of latency or jitter resulting from motor operation, and applying a smoothing filter for motor operation. For example, controlling a motor of a UAV to reduce an operating temperature of the UAV can include using a temperature model for the unmanned aerial vehicle or an operating temperature measurement to determine a current operating temperature and comparing that current operating temperature to a threshold. If the threshold is exceeded, settings of the motor are adjusted to cause the motor to operate in a manner that reduces the current operating temperature.

Abstract: Image captured with an image capture device with a rolling shutter may be deformed due to changes in imaging sensor orientation during image capture. Image deformities may occur due to rolling shutter that exposes rows of pixels to light at slightly different times during image capture. Deformities such as wobble, for example, and/or other deformities may be corrected by constructing an output image. The output image may be constructed by determining corresponding pixels within the input image. The location of the input pixel may be determined by performing one or more fixed point iterations to identify one or more input pixels within the input image. A value of the output pixel within the output image may be determined based on a value of a corresponding pixel within the input image.

Abstract: An image or a video may include a spherical capture of a scene. A punchout of the image or the video may provide a panoramic view of the scene.

Abstract: Systems and method of identifying a horizon depicted in an image are presented herein. Information defining an image may be obtained. The image may include visual content comprising an array of pixels. The array may include pixel rows. Parameter values for a set of pixel parameters of individual pixels of the image may be determined. Individual average parameter values of the individual pixel parameters of the pixels in the individual pixel rows may be determined. Based on the average parameter values a pixel row may be identified as depicting a horizon in the image.

Abstract: Multiple punchouts of a video may be presented based on multiple viewing windows. The video may include visual content having a field of view. Multiple viewing windows may be determined for the video, with individual viewing window defining a set of extents of the visual content. Different punchouts of the visual content may be presented based on the different viewing windows. Individual punchout of the visual content may include the set of extents of the visual content defined by corresponding viewing window.

Abstract: Multiple lookup tables (LUTs) storing different numbers of control point values are used to process pixels within different blocks of an image, such as after image processing using tone mapping and/or tone control, and/or to collect histogram information or implement 3D LUTs. First control point values stored within a first LUT are applied against pixels of a given block of an image to produce a distorted image block. Second control point values stored within a second lookup table are applied against a pixel of the distorted image block to produce a processed pixel. The second LUT is one of a plurality of second LUTs and stores fewer values than the first LUT. A processed image is produced using the processed pixel. The processed image is then output for further processing or display.

Abstract: Disclosed is an electronic motor with two bearings. The motor is structured so that, when loaded, the majority of the load (e.g., a radial load) is borne by one of the bearings. The bearing that bears a greater load may be larger and, thus, better suited for a heavy load. In some embodiments, the larger bearing may include rolling elements that have respective radii larger than respective radii of rolling elements of the other bearing by a ratio of at least 1.5 (150%). In some embodiments, the larger bearing may have an outer race with a radius that is greater than a radius of the outer race of the smaller bearing by a ratio of at least 1.5. In some embodiments, the motors may include a third bearing between the two bearings. The third bearing may reduce vibration in the motor.

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: Systems and methods are disclosed for image signal processing. For example, methods may include accessing an image from an image sensor; detecting an object area on the image; classifying the object area on the image; applying a filter to an object area of 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: A phased camera array captures images from a plurality of image sensor assemblies, each image sensor assembly capturing at a framerate and a resolution. The phased camera array is configured to generate images captured from the independent image sensor assemblies to be stitched into a single composite image with a higher resolution than the independent images. The higher resolution composite images can then be phased together to generate a video with a higher framerate than what the independent images were captured at. The image sensor assemblies of the camera system are positioned in such a way to minimize the footprint of the camera system and minimize negative effects from image stitching and video phasing.

Abstract: Implementations disclosed herein include an image capture device, a system, and a method for performing multiscale denoising of a video. An image processor of the image capture device obtains a video frame. The video frame may be in any format and may include noise artifacts. The image processor decomposes the video frame into one or more sub-frames. In some implementations, the image processor denoises each of the one or more sub-frames. The image processor decomposes one or more video frames in a temporal buffer into one or more temporal sub-frames. The image processor denoises each of the temporal sub-frames. The image processor reconstructs the one or more denoised sub-frames and the one or more temporal sub-frames to produce a denoised video frame. A memory of the image capture device may be configured to store the denoised video frame.

Abstract: An image capture device may detect and repair banding artifacts in a video. The image capture device may include an image sensor and an image processor. The image sensor may capture a frame that includes a sinusoidal light waveform banding artifact. The image processor may detect a sinusoidal light waveform in the frame. The image processor may perform a sinusoidal regression. The image processor may obtain an inverted gain map. The image processor may apply the inverted gain map to the frame. The image processor may output the frame.

Abstract: Systems and methods are disclosed for field of view adjustment for image capture devices. For example, methods may include receiving a field of view selection; oversampling, using an image sensor, to obtain an image at a capture resolution that is greater than an encode resolution; determining a crop setting based on the field of view selection; cropping the image using the crop setting to obtain a cropped image; down-scaling the cropped image to obtain a scaled image at the encode resolution; encoding the scaled image at the encode resolution; and storing, displaying, or transmitting an output image based on the scaled image.

Abstract: Multiple pipelines are used for image and video processing. In a first image processing pipeline, an image is retrieved from a buffer and processed using one or more image processing units. An altered image produced using the first image processing pipeline replaces the earlier version of the image stored in the buffer. The altered image may also be immediately output for display or encoding. In the second image processing pipeline, the altered image is retrieved from the buffer and processed according to image processing control statistics collected at the first image processing pipeline. The resulting processed image may then be encoded. A processed image output from the second image processing pipeline has a higher resolution than the altered image output from the first image processing pipeline.

Abstract: The present disclosure relates to processing a plurality of audio signals. The method includes receiving the plurality of audio signals in the frequency domain and determining an overall attenuation multiplier based on the plurality of audio signals and an overall lookup table that relates decibel values to different overall attenuation multipliers. The method further includes determining an attenuation vector comprising a plurality of bin-specific attenuation multipliers, each bin-specific attenuation multiplier respectively corresponding to a different frequency bin of the plurality of frequency bins. The method further includes scaling each bin-specific attenuation value in the attenuation vector with the overall attenuation multiplier, and editing each of the audio signals based on the scaled bin-specific attenuation values in the attenuation vector.

Abstract: Disclosed is a cross loop antenna system for an aerial vehicle. In one embodiment, the cross loop antenna system includes a cross bar antenna and a ground plane. The cross bar antenna includes two thin coplanar perpendicular bars that intersect in the middle and are parallel to the ground plane. Each bar couples to the ground plane at each end, comprising an antenna loop. Thus, the cross loop antenna system comprises two intersecting single-fed loops. The antenna can operate at a wavelength that is approximately twice the length of the bars. In such an embodiment, the antenna system may be resonant. The distance between the bars and the ground plane may be relatively small, thus minimalizing the vertical profile of the antenna. The antenna may be operated as a dual-band antenna and may produce an omnidirectional radiation pattern. An aerial vehicle may include two such antennas.

Abstract: Ultrasonic ranging state management for a UAV is described. A transducer transmits an ultrasonic signal and receives an ultrasonic response thereto using a gain value. A noise floor estimation mechanism determines a noise floor estimate. A state mechanism sets an ultrasonic ranging state used by the transducer to a first ultrasonic ranging state. The transducer transmits an ultrasonic signal and responsively receive an ultrasonic response to the ultrasonic signal using a gain value according to the noise floor estimate. The state mechanism processes the ultrasonic response to determine whether to determine a new noise floor estimate, adjust the gain value used by the transducer, or change the ultrasonic ranging state of the UAV to a second ultrasonic ranging state. The configurations of the first and second ultrasonic ranging states differ as to, for example, power and gain levels used by the transducer to receive ultrasonic responses.

Abstract: A camera controller is configured to control a camera through voice commands. The camera controller includes drain mechanisms that allow the camera controller to be used in environments in which the camera controller is exposed to fluids. The camera controller device comprises a housing body with an outer surface including a first opening and a second opening. A first channel extends from the first opening into the housing body and to a cavity in which a microphone is located, enabling audio signals entering the first opening to be captured by the microphone. A membrane is located between the first channel and the microphone to create a waterproof seal over the microphone. A second channel extends from the first channel to the second opening to create a drain such that fluid entering from the first opening can flow from the first channel through the second channel and out the second opening.

Abstract: A camera is configured for use with a removable camera lens cover, which can be secured to or removed from the camera by a user without the use of a tool set. The mechanism which allows the lens cover to be secured to and removed from the camera includes a set of wires embedded into the lens cover and a set of wedges protruding from the lens wall of the camera. To secure the lens cover to the camera, the lens cover is placed onto the front of the camera and rotated until the wires align with corresponding wedges, securing the wires underneath the tapered surface of the wedges. To remove the lens cover from the camera, a force is applied outward and normal to the lens cover, causing the wires to flex outward and enabling the rotation and removal of the lens cover from the camera.

Abstract: Video information, visual information, and rendering instructions 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 of view as a function of progress through the spherical video content. The visual information may define additional visual content to be presented with the spherical video content. The rendering instructions may define how the additional visual content is to be presented with the spherical video content during playback. Container information defining a container file may be generated. The container information may include the video information, the visual information, and the rendering instructions within a structure corresponding to a type of the container file. A playback of the spherical video content using the container file may include a presentation of the additional visual content with the spherical video content based on the rendering instructions.

Abstract: Systems and methods are disclosed for image capture. For example, systems may include an image capture module including an image sensor configured to capture images, a connector, and an integrated mechanical stabilization system configured to control an orientation of the image sensor relative to the connector; an aerial vehicle configured to be removably attached to the image capture module by the connector and to fly while carrying the image capture module; and a handheld module configured to be removably attached to the image capture module by the connector, wherein the handheld module includes a battery and an integrated display configured to display images received from the image sensor.

Abstract: An image capture device may capture visual content during a visual capture duration and audio content during an audio capture duration. The audio capture duration may be shorter than the visual capture duration. The captured audio content may provide audio for playback of the captured visual content.