Abstract: The disclosed technology includes techniques for providing improved video stabilization on a mobile device. Using gyroscope data of the mobile device, the physical camera orientation of the mobile device may be estimated over time. Using the physical camera orientation and historical data, corresponding virtual camera orientations representing a camera orientation with undesired rotational movement removed may be modeled using a non-linear filter to provide for mapping of a real image to a stabilized virtual image. The virtual camera orientation may be modified to prevent undefined pixels from appearing in the output image.

Abstract: The disclosed technology includes techniques for providing improved video stabilization on a mobile device. Using gyroscope data of the mobile device, the physical camera orientation of the mobile device may be estimated over time. Using the physical camera orientation and historical data, corresponding virtual camera orientations representing a camera orientation with undesired rotational movement removed may be modeled using a non-linear filter to provide for mapping of a real image to a stabilized virtual image. The virtual camera orientation may be modified to prevent undefined pixels from appearing in the output image.

Abstract: The disclosed technology includes techniques for providing improved video stabilization on a mobile device. Using gyroscope data of the mobile device, the physical camera orientation of the mobile device may be estimated over time. Using the physical camera orientation and historical data, corresponding virtual camera orientations representing a camera orientation with undesired rotational movement removed may be modeled using a non-linear filter to provide for mapping of a real image to a stabilized virtual image. The virtual camera orientation may be modified to prevent undefined pixels from appearing in the output image.

Abstract: A zooming control method is disclosed to perform following operations. A graphical user interface is displayed, and the graphical user interface includes a preview image corresponding to the zooming scale of the camera. A user input is received to assign the zooming scale for zooming in or zooming out the camera. The camera is natively capable of adopting the zooming scale within a scalable range between a wide bound and a telephoto bound. In response to a determination that the zooming scale assigned by the user input is wider than the wide bound of the scalable range, a panorama view mode is launched on the graphical user interface. The preview image during the panorama view mode is generated by the camera adopting the zooming scale at the wide bound, displayed within a central part on the graphical user interface and surrounded by a blank area on the graphical user interface.

Abstract: Image processing methods and systems in accordance with depth information are provided. At least one image with depth information is obtained. The image is displayed on a display unit of an electronic device. A selection of an ROI (Region Of Interest) in the image is received via a user interface. A first depth value corresponding to the selected ROI is obtained from the depth information, and the first depth value is mapped to a first effect level of an image effect, wherein the image effect has a plurality of effect levels. The image effect is applied to the image according to the depth information of the image, wherein the selected ROI is applied with the image effect in the first effect level.

Abstract: A method, an electronic apparatus, and a computer readable medium for processing reflection in an image are proposed. In the method, a first image and a second image are obtained. A plurality of objects in the first image and the second image are recognized and a plurality of lighting regions having a brightness higher than a first threshold in the first image and the second image are detected. Then, a plurality of displacements between corresponding objects and corresponding lighting regions in the first image and the second image are calculated. It is determined whether a ratio of the displacement of the object nearby one of the lighting regions to the displacement of the lighting region is over a second threshold. Finally, the lighting region is determined as a reflection if the ratio is over the second threshold.

Abstract: A method, an electronic apparatus, and a computer readable medium for processing reflection in an image are proposed. In the method, a first image and a second image are obtained. A plurality of objects in the first image and the second image are recognized and a plurality of lighting regions having a brightness higher than a first threshold in the first image and the second image are detected. Then, a plurality of displacements between corresponding objects and corresponding lighting regions in the first image and the second image are calculated. It is determined whether a ratio of the displacement of the object nearby one of the lighting regions to the displacement of the lighting region is over a second threshold. Finally, the lighting region is determined as a reflection if the ratio is over the second threshold.

Abstract: A handheld device, a panoramic image forming method and a non-transitory machine readable medium thereof are provided. The present invention discloses a handheld electronic device for generating a panoramic image formed by a plurality of sub images, the handheld electronic device comprise an input unit, a display unit, an image sensor and a processor. The input unit senses a control action to generate a panorama signal. The image sensor captures a specific sub image of the plurality of sub images according to the panorama signal. The processor determines that the specific sub image is fuzzy so that the processor executes an image re-capturing program to: enable the display unit to display an image re-capturing interface; enable the image sensor to capture a first auxiliary image corresponding to the specific sub image; and replace the specific sub image by the first auxiliary image.

Abstract: A method for adjusting a stereo image and an image processing device using the same are provided. The stereo image is displayed on a screen. The method includes following steps. A plurality of depth values of the stereo image are obtained, where a plurality of first depth values correspond to a boundary region of the screen. It is determined whether one of the first depth values is negative parallax. If one of the first depth values is negative parallax, the depth values are adjusted such that the first depth values are not negative parallax. In this way, stereoscopic window violation is avoided.

Abstract: Image processing methods and systems in accordance with depth information are provided. At least one image with depth information is obtained. The image is displayed on a display unit of an electronic device. A selection of an ROI (Region Of Interest) in the image is received via a user interface. A first depth value corresponding to the selected ROI is obtained from the depth information, and the first depth value is mapped to a first effect level of an image effect, wherein the image effect has a plurality of effect levels. The image effect is applied to the image according to the depth information of the image, wherein the selected ROI is applied with the image effect in the first effect level.

Abstract: An automatic image adjusting method for use in an electronic device is provided. The electronic device has a processor and a display screen. The automatic image adjusting method has the following steps of: analyzing an image to determine multiple target objects in the image; estimating corresponding depth distances of the target objects; and displaying the image on the display screen by switching focus between the target objects according to the corresponding depth distances in a display order.

Abstract: A stereoscopic imaging method for a stereoscopic imaging system is provided. The stereoscopic imaging method comprises using a processor to perform the following steps of: rendering a three-dimensional scene with at least one object and a manipulating area comprising a corresponding plane of the object; generating and displaying at least one stereoscopic image comprising the three-dimensional scene and the updated object; receiving a plurality of touch-control commands; manipulating the corresponding plane of the object according to the touch-control commands; updating the object in the three-dimensional scene with the manipulated corresponding plane; and updating the stereoscopic image with the updated object.