1007 results about "Motion blur" patented technology

Systems and methods for providing a substantially de-blurred image of a scene from a motion blurred image of the scene are disclosed. An exemplary system includes a primary detector for sensing the motion blurred image and generating primary image information representing the blurred image, a secondary detector for sensing two or more secondary images of the scene and for generating secondary image information representing the two or more secondary images, and a processor for determining motion information from the secondary image information, estimating a point spread function for the motion blurred image from the motion information, and applying the estimated point spread function to the primary image information to generate information representing the substantially de-blurred image.

A method and apparatus for creating motion blur, depth of field, and screen door effects when rendering three-dimensional graphics data are disclosed. A graphics system configured with a graphics processor, a super-sampled sample buffer, and a sample-to-pixel calculation unit is disclosed. The graphics processor may be configured to use a sample mask to select different subsets of sample coordinates to be rendered for a particular frame. Each subset may be rendered applying a different set of attributes, and the resulting samples may then be stored together in the sample buffer. The sample-to-pixel calculation unit may be configured to filter the samples into output pixels that are provided to a display device. The attributes that may be changed from subset to subset include the viewpoint, the time at which objects in the data are rendered, which objects or geometric primitives in the data are rendered, the position of objects in the data, the color of objects in the data, the transparency of objects in the data, and the shape of objects in the data.

A digital image acquisition system includes a portable apparatus for capturing digital images and a digital processing component for detecting, analyzing and informing the photographer regarding motion blur, and for reducing camera motion blur in an image captured by the apparatus. The digital processing component operates by comparing the image with at least one other image, for example a preview image, of nominally the same scene taken outside the exposure period of the main image. In one embodiment the digital processing component identifies at least one feature in a single preview image which is relatively less blurred than the corresponding feature in the main image, calculates a point spread function (PSF) in respect of such feature, and de-convolves the main image using the PSF. In another embodiment, the digital processing component calculates a trajectory of at least one feature in a plurality of preview images, extrapolates such feature on to the main image, calculates a PSF in respect of the feature, and de-convolves the main image using the PSF. In another embodiment the digital processing unit after determining the degree of blur notifies the photographer of the existing blur or automatically invokes consecutive captures.

A sequence of images depicts a foreground object in motion. A base image is selected, and the other images in the sequence are co-registered with the base image in order to align the images to a common coordinate system. A background image and a binary foreground mask are generated from the sequence of aligned images. By applying the foreground mask to a chosen one of the aligned images, a representation of the moving object is extracted. After blurring the background image, the extracted representation may be superimposed onto the blurred background image to produce a new image.

A camera system is disclosed having the ability to overcome the effects of motion blur. The camera system includes an image sensor; a velocity detection means such as a MEMS accelerometer for determining any motion of the image relative to an external environment; a processor means interconnected to the image sensor and the velocity detection means and adapted to process the sensed image so as to deblurr the image and to output the deblurred image to a printer means.

The present invention relates to a display apparatus comprising a display panel; a controller to analyze input video data into frequency components, and create first and second video data different in the frequency component from each other on the basis of analyzed results; and a panel driver to drive the created first and second video data to be displayed in sequence as images on the display panel. Thus, the present invention provides a display apparatus and a control method thereof, in which first video data and second video data are created by analyzing a frequency component of input video data and output in sequence, thereby decreasing a motion blur through a simple operation without hardware change.

Samples of a scene are acquired in synchronization with finely interleaved varying conditions such as lighting, aperture, focal length, and so forth. A time-varying sample at each pixel for each condition is reconstructed. Time multiplexed interleaving allows for real-time, live applications, while handling motion blur naturally. Effects such as real-time video relighting of a scene is possible. Time interleaved exposures also allow segmentation of a scene, and allows for constrained special effects such as triangulation matting using a multi-color interleaved chroma key.

A method and system of identity masking to obscure identities corresponding to face regions in an image is disclosed. A face detector is applied to detect a set of possible face regions in the image. Then an identity masker is used to process the detected face regions by identity masking techniques in order to obscure identities corresponding to the regions. For example, a detected face region can be blurred as if it is in motion by a motion blur algorithm, such that the blurred region can not be recognized as the original identity. Or the detected face region can be replaced by a substitute facial image by a face replacement algorithm to obscure the corresponding identity.

An image displaying apparatus, for improving motion blur, in particular, on an image displaying apparatus of hold-type, such as, a liquid crystal display element, etc., comprising: sub-frame producing portions (5, 6) for producing a first sub-frame, a second sub-frame being lower in the gradation than the first sub-frame, from an image of one (1) frame of an image signal inputted; a histogram detection portion (2) for detecting brightness histogram of the image signal; an image determination portion (3) for determining on whether the image signal inputted is a high-gradation image or not, from that brightness histogram; and a level compensation portion (4) for lowering a gradation level of that image signal inputted. And, according to the present invention, lowering the gradation of the high-gradation image keeps the difference in brightness between the first and the second sub-frames, and thereby increasing an effect of improving the motion blur.

Provided are an apparatus and method for driving a 2-dimensional (2D)/3-dimensional (3D) switchable display for improving the quality of image. The apparatus for driving a 2D/3D switchable display includes: an image mode determination unit determining whether input image signals of continuous frames are in a 2D mode or 3D mode; and an over-driving control unit over-driving the input image signal of a current differently according to the determined image mode. According to the apparatus and method, the response time in each of the 2D mode and the 3D mode can be increased, while motion blur and cross-talk effects can be decreased, thereby improving the quality of image.

A digital image acquisition system includes a portable apparatus for capturing digital images and a digital processing component for detecting, analyzing, invoking subsequent image captures and informing the photographer regarding motion blur, and for reducing camera motion blur in an image captured by the apparatus. The digital processing component operates by comparing the image with at least one other image, for example a preview image, of nominally the same scene taken outside the exposure period of the main image. In one embodiment the digital processing component identifies at least one feature in a single preview image which is relatively less blurred than the corresponding feature in the main image, calculates a point spread function (PSF) in respect of such feature, and initiates a subsequent capture if determined that the motion blur exceeds a certain threshold. In another embodiment the digital processing determines the degree of blur by analyzing the motion blur in the captured image itself, and initiates a subsequent capture if determined that the motion blur exceeds a certain threshold. Such real time analysis may use the auto focusing mechanism to qualitatively determine the PSF.

The invention discloses a GAN based motion blur removing method of an image and a motion blur removing GAN model for the method. The method comprises that the GAN model is designed; the model is trained; and in an application phase, the GAN model comprises a generator and a discriminator, the generator optimizes parameters continuously so that a generated image approaches distribution of a clear image, the discriminator optimizes parameters continuously so that whether the image is from fuzziness removing image distribution or clear image distribution can be discriminated more effectively, thegenerator comprises a down-sampling device and an up-sampling device, the down-sampling device carries out convolution on the image and extract semantic information from the image, and the up-sampling device carries out deconvolution on the image by combining the obtained semantic information with structure information of the image. Thus, motion blur of the image can be removed effectively, and the clear image satisfying perception of humans is obtained.

Motion of an image of a scene being captured by a digital image acquisition device is detected and used to control parameters of illumination of the scene by a flash lamp that is typically built into the device. Parameters that may be controlled include the intensity, duration and timing of light emitted by the flash lamp. Such control of the flash illumination is preferably performed in conjunction with adjusting one or more exposure parameters used to capture an image. Such exposure parameters include duration, aperture and sensor gain. Motion blur caused by movement of the camera or by movement of an object within the scene being photographed is reduced by selecting appropriate exposure parameters and flash light characteristics.

Multiple images of a scene are acquired over a contemporaneous period of time. Most of the multiple images are lower resolution images acquired with a lower resolution than the other of the multiple images. A corrected set of images is formed at least by correcting for motion present between at least some of the lower resolution images. In addition, a synthesized image is formed at least by merging (a) at least a portion of at least one of the images in the corrected set of images, and (b) at least a portion of at least one of the other of the multiple images. The synthesized image is stored in a processor-accessible memory system. The synthesized image exhibits improved image quality including reduced motion blur, a higher signal-to-noise ratio, and higher resolution over conventional techniques.

A video system that performs TV signal decoding, deinterlacing, and de-motion-blurring for progressive scan flat panel display is introduced. The system embeds a frame buffer and a scaler for conducting format and resolution conversions for display panels of different sizes. The output of the scaler is sent to a de-motion-blur processor for reducing the blurriness due to the motion of image objects and the slow response time of flat panel display devices. The de-motion-blur processor gets the motion and noise indication signal from scaler or the pre-frame-buffer video processor. Based on the motion and noise information and the information of temporal difference, the de-motion-blur processor performs over driving for the display panel interface and improves the rising and falling response time of the flat panel display. The decoding, deinterlacing, and de-motion-blur processing share the same frame buffer controller so the entire system can be optimized in cost and performance.

A driving method and apparatus for a liquid crystal display for minimizing motion blur in a moving picture as well as displaying a fresh and dynamic image is disclosed. In the driving method, data inputted from the exterior are converted into brightness components to produce a histogram for each frame. A control value is extracted from various characteristics of the histogram. Turn-on times of a plurality of lamps positioned in such a manner to overlap with a liquid crystal display panel are controlled in correspondence with the control value.

A method, a circuit arrangement and a display device which suppresses motion blur due to motion integration carried out along a motion trajectory on the image data, which occurs in matrix type displays in which a motion trajectory is integrated by the viewer and/or the display, includes an inverse integration filtering of the video signal. To avoid de-blurring in image regions where motion cannot be detected, or image is low and to avoid noise modulation, motion estimation as well as further image characteristic are used.

Motion/Saturation detection system and method for synthesizing high dynamic range motion blur free images from multiple captures, the system and method utilizing photocurrent estimation to reduce read noise and enhance dynamic range at the low illumination end, saturation detection to enhance dynamic range at the high illumination end, and motion blur detection to ensure the photocurrent estimation is not corrupted by motion. Motion blur detection also makes it possible to extend exposure time and to capture more images, which can be used to further enhance dynamic range at the low illumination end. The present invention operates completely locally, making it well suited for single chip digital camera implementations.

Image light from an object is dispersed by a light dispersing device. When a plurality of image sensors are used for picking up images, an image in which a moving object is stopped is picked up with a high shutter speed, and at the same time, a motion-blurred image in which the moving object is picked up at a slow shutter speed. The obtained images are synthesized. The synthesized image has a slow synchronized flash effect. Accordingly, an image having a slow synchronized flash effect can be obtained without using a flash.

Systems and methods are provided for controlling texture sampling in connection with computer graphics in a computer system. In various embodiments, improved mechanisms for controlling texture sampling are provided that enable 3-D accelerator hardware to greatly increase the level of realism in rendering, including improved mechanisms for (1) motion blur; (2) generating anisotropic surface reflections (3) generating surface self-shadowing (4) ray-cast volumetric sampling (4) self-shadowed volumetric rendering and (5) self-shadowed volumetric ray-casting. In supplementing existing texture sampling techniques, parameters for texture sampling may be replaced and/or modified.