Electronic devices, methods, and program storage devices for achieving smooth zooming operations during video capture are disclosed. In particular, smooth zooming may be desirable during video capture operations that involve a single image capture device and/or transitioning between two or more distinct image capture devices, e.g., having different optical and/or zooming properties, during the video capture. When video zooming is done abruptly, it can lead to an unpleasant user experience. The techniques described herein to improve the smoothness of zooming operations include: the use of longer zoom ramps for image capture devices; the early transitioning between image capture devices during video capture; and the performance of additional digital zoom smoothing-aware video image stabilization operations. The embodiments described herein also provide for a more consistent user experience between video streaming (i.e., preview) modes and the recorded (i.e., final) zoomed video that is produced using the various zoom smoothing techniques described herein.

Provided are methods for maintaining intrinsic calibration of IBIS cameras, which can include obtaining a first camera sensor position at which a movable sensor of a camera is positioned when the camera captures a first image, selecting, from at least one database including a plurality of intrinsic calibration data sets indexed by a respective plurality of second camera sensor positions, one of the plurality of second camera sensor positions based on the first camera sensor position of the movable sensor, retrieving, from the at least one database and for the camera, a first intrinsic calibration data set, of the plurality of intrinsic calibration data sets, that is indexed by the selected one of the plurality of second camera sensor positions, and rectifying, by the at least one processor, the first image using the first intrinsic calibration data set of the camera retrieved from the at least one database.

Provided is a video correction method comprising: extracting a common feature point from a number of video frames corresponding to a correction window size; extracting a trace of the feature point from the video frames; calculating an average value of the trace in the video frames; extracting a stabilized trace from a circular queue circular queue buffer using the trace and the average value; and applying a repositioning operation and a perspective warping operation to the video frames based on the stabilized trace to generate a stabilized video.

A method for image capture control may include computing an electronic image stabilization (EIS) compensation based on image data from an image capture device, the image data having a first region of interest (ROI). A jitter or panning shift is computed based on the EIS compensation. The first ROI is adjusted for use in at least one of the group consisting of an automatic white balance process and an automatic exposure process of the image capture device based on the jitter or panning shift.

A signal processing device includes an approximate curved surface conversion unit that includes a first stacked autoencoder pretrained on the basis of learning input data constituted by coordinate data acquired for each of multiple elements of an object, and that obtains approximate curved surface data indicating an approximate curved surface of the object in an intermediate layer of the first stacked autoencoder, on the basis of input data constituted by the coordinate data acquired for each of the elements, and a geometric modulation processing unit that includes a second stacked autoencoder having learned by machine learning on the basis of learning input data constituted by the approximate curved surface data and on the basis of training data constituted by a result obtained by coordinate conversion for each of the elements in a geometric modulation process performed for the object, and performs the geometric modulation process.

An electric camera includes an image sensing device with a light receiving surface having N vertically arranged pixels and an arbitrary number of pixels arranged horizontally, N being equal to or more than three times the number of effective scanning lines M of a display screen of a television system, a driver to drive the image sensing device to vertically mix or cull signal charges accumulated in individual pixels of K pixels to produce, during a vertical effective scanning period of the television system, a number of lines of output signals which corresponds to 1/K the number of vertically arranged pixels N of the image sensing device, K being an integer equal to or less than an integral part of a quotient of N divided by M, and a signal processing unit having a function of generating image signals by using the output signals of the image sensing device.

A device and method to provide the user of a video recording device, like a smartphone, on-screen feedback to control the stability of the output video. The demarcation of a shape on the screen indicates the bounds of the material to be included in the resultant output video. The shape moves, as required, on the screen in the direction intended to stabilize the video. Device embodiments may also comprise facilitations for maintaining the shape's location relative to the screen, in the event that the shape hits one of the screen's edges; in that way, the video recording can accommodate scene movements. Other embodiments provide capability for locking onto a physical location in space, regardless of camera position or orientation.

To facilitate conversion of a frame rate of moving image data in an imaging element that images the moving image data. A pixel array unit is divided into a plurality of divided regions each including a plurality of partial regions. A scanning circuit sequentially performs control of exposing a predetermined number of regions of the plurality of partial regions as first partial regions to output first pixel data in each of the plurality of divided regions, and control of exposing a region different from the first partial regions of the plurality of partial regions as a second partial region to output second pixel data in each of the plurality of divided regions. An image processing unit sequentially performs processing of arraying the first pixel data to generate a first frame and processing of arraying the second pixel data to generate a second frame.

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.

An imaging unit of an embodiment of the present technology includes: a detector that detects temperature or remaining battery capacity; an imaging device that obtains a captured image; and a first correction section that changes, on a basis of a detection result of the detector, electronic hand shake correction accuracy with respect to the captured image obtained by the imaging device when an electronic hand shake correction function is enabled.