Gopro, Inc.

Anandhakumar Chinnaiyan

Ravi Kumar Belagutti Shivanandappa

Naveen Chinya Krishnamurthy

Nicholas Ryan Gilmour

Jonathan Leland Thorn

Clark Weber

Shishir Rao Ayalasomayajula

Shiva Kumar Belavadi Mallegowda

Aditi Saha

Ojas Gandhi

Romain Gounelle

Etienne Terree

Jerome Labarthe

Guillaume Oulès

Alexis Lefebvre

Anaïs Oulès

Kasturi Rangam

Michael A Ramirez

Maxime Renaudet

Feng Li

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.

Generating time-lapse videos with audio

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.

Systems and methods for providing punchouts of videos

Image capture devices and methods may be used to pre-buffer media storage. The pre-buffering method includes recording an image capture segment in a circular buffer. The circular buffer includes a number of recordable segments. The pre-buffering method includes determining whether a key moment command is received. If a key moment command is not received, the method includes recording a next image capture segment in a next adjacent recordable segment of the circular buffer if the next adjacent recordable segment of the predetermined number of recordable segments is available. If a key moment command is not received, the method includes overwriting an oldest recordable segment if the next adjacent recordable segment of the predetermined number of recordable segments is not available. If a key moment command is received, the pre-buffering method includes marking a wrap point in the circular buffer and switching from recording in the circular buffer to linear recording.

Method and apparatus for pre-buffer media storage

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.

Method and apparatus for in-camera night lapse video

An image captured using an image sensor is processed to determine control statistics and to produce an altered image which can be output for display or further processing at an image capture device, and the image is then processed according to the control statistics to produce a processed image which can be output for display or further processing at the image capture device or at another device. The altered image may have a lower resolution than the processed image. The image may be stored in a buffer. For example, the image may be retrieved from the buffer to produce the altered image, and again retrieved from the buffer to produce the processed image. The altered image may replace the image within the buffer. For example, the processed image may be produced to represent the altered image at a higher resolution.

Image and video processing using multiple pipelines

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 specific value and/or falling within a range of values.

An image capture device may provide playback of audio content during capture of visual content. Moments within the audio content may be associated with cue markers. The visual content may be synchronized with the audio content provided during capture, and a video edit may be automatically generated based on the moments associated with the cue markers.

Generation of audio-synchronized visual content

A method and apparatus for night lapse video capture are disclosed. The apparatus includes an image sensor, an image processor, and a video 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 image processor is configured to determine a motion estimation. The motion estimation is based on a comparison of a portion of the first image and a portion of the second image. The image processor is configured to subtract a mask from the second image to obtain a denoised image. The mask is based on the motion estimation. The video encoder is configured to receive the denoised image from the image processor. The video encoder is configured to encode the denoised image in a video format. The video encoder is configured to output a video file in the video format.

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.

Cameras may monitor its operation and automatically switch between operation modes thereby to best capture users' experiences. Auxiliary sensor data collected by the one or more sensors and/or captured image data may be analyzed to determine when a camera should switch to a high-motion operation mode. The auxiliary sensor data include motion information of the camera and the content of the captured images include motion information of the captured objects. When a camera or objects captured by the camera are moving rapidly, the camera is switched to operate at the high-motion operation mode to ensure image quality and minimize artifacts to best capture users' experiences. Motion of the camera may be detected or predicted by analyzing the auxiliary sensor data and motion of the captured objects may be detected by analyzing the captured image data thereby to determine whether or not the camera should switch to the high-motion operation mode.

Growing community of inventors

Fremont, CA, United States of America

Anandhakumar Chinnaiyan