Systems and methods are disclosed for image signal processing. For example, methods may include determining an orientation setpoint for an image sensor; based on a sequence of orientation estimates for the image sensor and the orientation setpoint, invoking a mechanical stabilization system to adjust an orientation of the image sensor toward the orientation setpoint; receiving an image from the image sensor; determining an orientation error between the orientation of the image sensor and the orientation setpoint during capture of the image; based on the orientation error, invoking an electronic image stabilization module to correct the image for a rotation corresponding to the orientation error to obtain a stabilized image; and storing, displaying, or transmitting an output image based on the stabilized image.

An electronic device having a camera module for generating image data, a processor for receiving the image data and generating image data restored based on the image data. The electronic device also having a display module displaying the restored image data. The processor being configured to identify a class of the image data, select a filter corresponding to the class, and generate the restored image data by applying the selected filter to the image data.

Disclosed are techniques that provide a “best” picture taken within a few seconds of the moment when a capture command is received (e.g., when the “shutter” button is pressed). In some situations, several still images are automatically (that is, without the user's input) captured. These images are compared to find a “best” image that is presented to the photographer for consideration. Video is also captured automatically and analyzed to see if there is an action scene or other motion content around the time of the capture command. If the analysis reveals anything interesting, then the video clip is presented to the photographer. The video clip may be cropped to match the still-capture scene and to remove transitory parts. Higher-precision horizon detection may be provided based on motion analysis and on pixel-data analysis.

An image processing apparatus performs shake information processing of outputting output shake information for input image data constituting a movie, shake information normalization processing of obtaining normalization shake information by normalizing the output shake information on the basis of angle of view information, and shake change processing of changing a shake state of the input image data using the normalization shake information.

An apparatus includes a subject detection unit configured to detect a specific subject in an input image, an acquisition unit configured to acquire camera information, an estimation unit configured to estimate a target of interest in an image using the subject information and the camera information, a first motion detection unit configured to detect background motion and subject motion, a conversion unit configured to convert the detected background motion and the detected subject motion to a first blur correction amount for correcting background blur and a second blur correction amount for correcting subject blur, respectively, and a correction amount calculation unit configured to, based on the target of interest, combine the first blur correction amount and the second blur correction amount and generate a final blur correction amount.

A camera may use a multi-axis image sensor shifting system to implement both autofocus (AF) and optical image stabilization (OSI) functions. The multi-axis image sensor shifting system may include a flexure suspension arrangement and an actuator. The flexure suspension arrangement may include an inner frame, an intermediate frame, and an outer frame. The actuator may include one or more magnets, and two sets of one or more coils attached respectively to some of the frames of the flexure suspension arrangement. Current flowing through the coils may be regulated to interact with the magnetic field of the magnets to generate motive force to move an image sensor of the camera relative to a lens group in multiple directions.

An electronic device of an embodiment of the present document may include a camera including a lens assembly, at least one sensor configured to detect a movement of the camera or the lens assembly, and a processor electrically connected to the camera and the at least one sensor. The processor may determine an exposure value that will be applied when photographing using the camera, obtain image frames, based on the exposure value, obtain movement information on the camera or the lens assembly by using the at least one sensor while the image frames are being obtained, determine an image stabilization strength, based on the exposure value and the movement information, and perform video digital image stabilization (VDIS) for the image frames, based on the image stabilization strength.

A wearable camera with mobile device optical coupling provides hands-free point-of-view video-chat. The mobile device optical coupling is enabled by an optic transfer engine that comprises a communications bus, a video decoding module, a micro-display, and a housing. The communications bus initially receives optical sensor data from an optical sensing device (e.g., the wearable camera). Next, the video decoding module decodes the optical sensor data. The micro-display displays the decoded optical sensor data. The housing partially encloses the communications bus, the video decoding module, and the micro-display and has a mounting element that is configured to removably mount the optics couple to a computing device such that the micro-display is positioned in a field of view of another optical sensing device coupled to the computing device.

An anti-shake image processing method, apparatus, electronic device and storage medium are disclosed. The method includes the following steps. A current actual posture of an imaging device at a current shooting moment of capturing an original image of current frame and multiple reference actual postures of the imaging device at multiple shooting moments of capturing the original images of adjacent multiple frames of the original image of the current frame are obtained. A path smoothing process is performed to determine a current virtual posture after path smoothing at the current shooting moment. A coordinate transformation is performed on the original image of the current frame captured in the current actual posture to an estimated position of the original image of the current frame when captured in the current virtual posture in a pixel coordinate system to obtain a first correction image of the current frame.

An image pickup apparatus capable of eliminating a manual change of an image pickup direction and of easily obtaining an image while focusing attention on experience. A detection unit is worn on a body part other than a head of a user and detects an observation direction of the user. An image pickup unit is worn on the body part and picks up an image. A determination unit determines a recording direction in accordance with the observation direction. An image recording unit records an image corresponding to the recording direction from among a picked-up image. The detection unit and the image pickup unit are located on a user's median plane and under a user's jaw in a worn state where the user wears the image pickup apparatus. The detection unit is located at a nearer position to the jaw than the image pickup unit in the worn state.