Abstract: Motion estimation systems and methods are disclosed. An apparatus may include a processing unit to acquire video images and to arrange the video images into a plurality of sequential video frames, and a motion estimation unit that receives the sequential video frames and determines a set of repetitive pattern neighbor candidate vectors for repetitive pattern content in a first frame. The set of repetitive pattern neighbor candidate vectors may be reduced by sorting the set to eliminate spurious repetitive pattern neighbor candidate vectors. The reduced set may be provided to a second adjacent frame. A method may include acquiring a plurality of sequential video frames having a repetitive pattern content, and determining a set of repetitive pattern neighbor candidate vectors for the repetitive pattern content in a first frame of the sequential video frames. The set of repetitive pattern neighbor candidate vectors may be sorted by determining at least one spurious repetitive pattern neighbor candidate vector.

Abstract: A weighting coefficient sequence defining unit generates an array in which weighting coefficients are held at positions defined by the directional components of blur vectors, and adjusts the weighting coefficients to increase the sum of the frequency components of the array or reduce variations of the frequency components. A weighting unit multiplies respective captured images by corresponding weighting coefficients, generating L weighted captured images. The weighting unit then generates the synthesized image of the L weighted captured images. A corrected image generation unit performs deconvolution processing using the frequency component of the array in which the weighting coefficients are held at positions defined by the directional components of blur vectors, and the frequency component of the synthesized image. The corrected image generation unit performs an inverse frequency transform for the deconvolution processing result, generating an output image.

Abstract: Apparatus and method for electronically estimating focusing distance between a camera (still and/or video camera) and a subject. Images at different focal positions of a calibration target are collected to arrive at a focus matching model for a given imaging apparatus. In operation, at least two images are captured and convolutions performed which approximate the modeling of blur change as a point spread function. Wavelet transforms are applied to the images after each convolution and images are compared based on the wavelet variance differences to provide a motion robust blur difference determination. Applying the blur differences to the focus matching model provides an estimate of focusing distance, which can be utilized such as for controlling camera focus.

Abstract: An image processing apparatus characterized by including; an area sensor unit that reads from an original document image a plurality of frames of image data having a shift of less than one pixel, an output resolution acquisition unit that obtains an output image resolution at which resolution the original document image read by the area sensor unit is output, an acquisition frame number control unit that controls a number of frames read by the area sensor unit according to a result of the output resolution acquisition unit, a correction unit that corrects an inclination of the frames of image data controlled by the acquisition frame number control unit, and a high resolution conversion unit that performs an interpolation processing using the plurality of frames of image data whose inclination is corrected by the correction unit to obtain image data in a resolution higher than a resolution during reading.

Abstract: Super-resolution time delay and integrate (TDI) imaging processing and systems for providing same utilize imaging geometry configured such that a predictable sub-pixel component of the frame-to-frame image motion can be used to construct a high-resolution output image from multiple under-sampled low-resolution input images.

Abstract: A super-resolution image is generated from a sequence of low resolution images. In one embodiment, the image shift information is measured for each of the low resolution images using an image stabilization component of an imaging device. The shift information is used to generate the super-resolution image. In another embodiment, the blurs are calculated for each of the low resolution images and are used to generate the super-resolution image.

Abstract: A control unit controls an image capture unit to perform a plurality of image captures of an object and acquires a plurality of mutually different image data based on a positional change of an image capturing device. Then, the control unit extracts a specified object image common to each of the acquired plurality of image data. The control unit synthesizes the acquired plurality of image data using the extracted specified object image as a reference, and thereby creates synthesized image data. The synthesized image data is an image equivalent to a captured image having a shallow depth of field such that only the specified object image is clearly photographed and the other portions are blurred.

Abstract: An image acquisition sensor of a digital image acquisition apparatus is coupled to imaging optics for acquiring a sequence of images. Images acquired by the sensor are stored. A motion detector causes the sensor to cease capture of an image when the degree of movement in acquiring the image exceeds a threshold. A controller selectively transfers acquired images for storage. A motion extractor determines motion parameters of a selected, stored image. An image re-constructor corrects the selected image with associated motion parameters. A selected plurality of images nominally of the same scene are merged and corrected by the image re-constructor to produce a high quality image of the scene.

Abstract: A camera-shake correction apparatus includes an image capturing unit configured to capture an object image, a camera-shake detection unit configured to detect a camera-shake applied to the camera-shake correction apparatus, a correction unit configured to correct the camera-shake of the object image by moving a correction member based on a camera-shake signal detected by the camera-shake detection unit, and a control unit configured to measure an amplitude of the camera-shake or a frequency of the camera-shake, or both the amplitude of the camera-shake and the frequency of the camera-shake, based on the camera-shake signal supplied from the camera-shake detection unit, and the control unit further configured to control to hold the correction member at a latest position if it is determined that the measured amplitude is smaller than a predetermined amplitude or if it is determined that the measured frequency is lower than a predetermined frequency, or if it is determined that the measured amplitude is smaller

Abstract: An optical system comprising an aberration control optical system is disclosed. An aberration control optical system is operable to produce an image aberration, and an aperture stop is operable to limit a light beam passing through the aberration control optical system. An image pickup device is operable to capture an object image passing through the aberration control optical system, and the aberration control optical system provides inflection points within a diameter of the aperture stop to obtain a depth extending effect.

Abstract: An image capture device includes: an optical system for producing a subject image; an imager, which receives the subject image and outputs a signal representing an image including the subject image; a sensor for detecting the shake of the device itself by the movement of the device; and an image processing section, which receives the signal representing the image and crops and outputs a part of the image and which changes the cropping range of the image, thereby reducing the shakiness of the subject image in the image that has been caused by the shake of the device itself. The image processing section determines whether the cropping range of the image needs to be changed based on the shake of the device itself that has been detected by the sensor or based on the motion of the subject image.

Abstract: Among pickup image data items of multiple frames picked up at different time instants, an image of a certain frame is regarded as a synthesizing base image. The synthesizing base image and an image of another frame are used to perform synthesizing processing. Specifically, an object-of-synthesis area is designated in the frame image regarded as the synthesizing base image, and processing of replacing pixel data in the object-of-synthesis area with pixel data in another frame is carried out. For example, if a person having his/her eyes closed appears in the synthesizing base image that is a group-photograph image, the part of the person's face is regarded as the object-of-synthesis area. As another frame, an image in which the person has his/her eyes left open is searched. Pixel data in the facial image part showing the open eyes is fetched and synthesized with the synthesizing base image. Thus, a group photograph in which all people have their eyes left open is produced.

Abstract: An image-processing method is an image-processing method for detecting motion between plural images, including a searching operation of searching for a local motion vector from each of blocks in the plural images on the basis of feature quantity of the plural images, and a calculating operation of calculating evaluation values of the local motion vector found, in which one of the evaluation values is accuracy of position adjustment which is obtained when the search source block of said local motion vector is position-adjusted on a trial basis by using the local motion vector in order to provide an image-processing method, an image-processing program, an image-processing apparatus, and an imaging apparatus which can properly evaluate local motion vectors which are found by searching blocks of images upon detecting motion of plural images.

Abstract: An imaging device (1) includes: an imaging element (33) which outputs a signal expressing an optical image of an imaging object upon an imaging process; a particular object detection unit (14) which successively acquires a frame image based on an output signal of the imaging element and detects the position of the particular object contained in the imaging object on the frame image according to the image signal of the frame image; a cut-out unit (15) which sets in the frame image, a cut-out region smaller than the entire region of the frame image according to the detected position and extracts the image in the cut-out region as a cut-out image; and an image quality compensation unit (16) which improves the resolution of the cut-out image.

Abstract: To provide an image generation apparatus that generates a visually-favorable target video sequence in color using input video sequences of color components and that is least likely to have an insufficient transfer rate when obtaining the input video sequences. The image generation apparatus includes: an image receiving unit (101) that receives, as the plurality of input video sequences, a plurality of video sequences that are obtained by shooting the same subject with a phase difference being set between frame exposure periods of the different color components; and a color image integration unit (103) that generates the target video sequence whose frame cycle is shorter than each of the frame exposure periods of the input video sequences, by reducing a difference between a frame image of the input video sequence of each color component and a sum of a plurality of frame images of the target video sequence which are included in a period that corresponds to the frame image of the input video sequence.

Abstract: A motion vector calculation unit calculates inter-frame movement amounts. A masked region specification unit separates the entire edge image of frame feature data into (i) an edge image showing relatively large movement amounts and (ii) an edge image showing relatively small movement amounts. The masked region specification unit then specifies the edge image showing relatively large movement amounts as a region to be masked. This way, a correction parameter is detected from a region other than the masked region. When the correction parameter is a slang angle, a slant correction unit performs slant correction on a frame picture obtained by an image sensor.

Abstract: Disclosed is an apparatus and method for obtaining a motion adaptive high dynamic range image, in which a motion degree of a first image and a second taken using different exposure times is calculated. The motion calculation intensity is adjusted based on the calculated motion degree. The motion compensation intensity involves a global motion compensation and/or a location motion compensation. Images subjected to compensation are synthesized and output, so that an image having high dynamic range is obtained.

Abstract: An image processing apparatus includes a region extracting section that extracts a first predetermined region including a target pixel in a current frame and a second predetermined region including a pixel located at the same position as the target pixel in a previous frame, a motion vector calculating section that calculates a motion vector of the first predetermined region with respect to the previous frame based on part or all of the pixels in the first predetermined region and part of the pixels in the second predetermined region, a filter coefficient determining section that determines a filter coefficient for a plurality of pixels in the second predetermined region based on the motion vector, and a noise reducing section that reduces noise in the target pixel based on the plurality of pixels in the second predetermined region and the filter coefficient.

Abstract: Image processing herein reduces the computational complexity required to estimate a disparity map of a scene from a plurality of monoscopic images. Image processing includes calculating a disparity and associated matching cost for at least one pixel block in a reference image, and then predicting, based on this disparity and associated matching cost, a disparity and associated matching cost for a pixel block that neighbors the at least one pixel block. Image processing continues with calculating a tentative disparity and associated matching cost for the neighboring pixel block, by searching for a corresponding pixel block in a different monoscopic image over a reduced range of candidate pixel blocks focused around the disparity predicted. Searching over a reduced range avoids significant computational complexity. Image processing concludes with determining the disparity for the neighboring pixel block based on comparing the matching costs associated with the tentative disparity and the disparity predicted.

Abstract: An image sensing apparatus that includes an image sensing portion outputting the image data of an image by shooting and that generates an output image based on the output data of the image sensing portion obtained in response to a predetermined shooting command has: a first correction portion which, based on the image data of a first image shot by the image sensing portion and the image data of a second image shot by the image sensing portion with an exposure time longer than the exposure time of the first image, performs position adjustment between the first and second images and then synthesizes the first and second images to generate the output image; a second correction portion which generates the output image by reducing noise in the first image without using the second image; and a correction control portion which executes selection processing to alternatively select one of the first and second correction portions based on a shooting condition set for shooting of the second image or based on the output

Abstract: An imaging apparatus with adjustable imaging plane, the apparatus having mechanical, electronic or optical devices to adjust the position and the orientation of the imaging plane, which successively captures a plurality of images while adjusting the imaging plane, and a method to integrate the captured images to a single high-resolution image by exploration of the mutual information not available in a single image, such as the sub-pixel observations due to the spatial misalignment, thus achieving an image resolution higher than the sensor resolution.

Abstract: The present invention discloses a super-resolution method for image display. The method comprises: receiving a low resolution image; dividing the low resolution image into a plurality of regions; finding high resolution patches in a pre-trained database; pasting the high resolution patches back to the plurality of regions by puzzle-form process or oblique-form process and computing the compatibility utilizing a two-dimensional hidden Markov model process; and generating a super-resolution image.

Abstract: Disclosed are an apparatus and a method of preventing image degradation due to shaking of an image photographing device. An apparatus for preventing image degradation due to shaking of an image photographing device according to an aspect of the present invention includes an image acquiring unit to acquire a plurality of images of a predetermined subject using a second exposure time shorter than a first exposure time, a scale adjusting unit to adjust scales of the plurality of acquired images, and an image restoring unit to restore images of the subject using the plurality of images whose scales are adjusted.

Abstract: To provide a processing method for reducing motion blur while increasing resolution. By performing a super-resolution process, a resolution-increased image is obtained from an input image in multiple frames. By performing an enlargement process, an enlarged image is obtained from the input image in one frame. A high-frequency image is obtained by subtracting the enlarged image from the resolution-increased image. A high spatial frequency-emphasized image is obtained by adding the high-frequency image to the resolution-increased image. The enlarged image and high spatial frequency-emphasized image are displayed alternately every half frame.

Abstract: An image processing device (200) according to the present invention includes: a shooting period obtaining unit (205) configured to obtain a shooting period; an imaging unit (202) which includes a plurality of pixels each converting light into an electrical signal, and which has a first mode in which a low-resolution image signal is outputted and a second mode in which a high-resolution image signal is outputted, the low-resolution image signal including electrical signals converted by a first number of pixels among the plurality of pixels, the high-resolution image signal including electrical signals converted by a second number of pixels among the plurality of pixels, and the second number being greater than the first number; a control unit (210) configured to cause the imaging unit (202) to operate in the first mode during the shooting period, and to operate in the second mode during a period other than the shooting period; and a super-resolution unit (203) configured to generate a super-resolution image si

Abstract: An imaging apparatus includes an image pickup device, a device that obtains an image from the image pickup device, a sensor that detects a roll angle of the sensor, wherein the sensor detects a reference roll angle of the sensor when the imaging apparatus is disposed at a predetermined roll angle, a device that calculates a reference roll angle of the image pickup device by using a reference image from the image pickup device when the imaging apparatus is disposed at the predetermined roll angle and a device that corrects a roll angle of the sensor by calculating a relative roll angle from the reference roll angle of the image pickup device and the reference roll angle of the sensor.

Abstract: Embodiments of the invention describe a method for reducing a blur in an image of a scene. First, we acquire a set of images of the scene, wherein each image in the set of images includes an object having a blur associated with a point spread function (PSF) forming a set of point spread functions (PSFs), wherein the set of PSFs is suitable for null-filling operation. Next, we invert jointly the set of images and the set of PSFs to produce an output image having a reduced blur.

Abstract: A plurality of input image signals are synthesized to generate a synthesis signal on the basis of synthesis information indicating an area where input image signals which are image signals of an image composed of at least one of input moving images and still images are respectively synthesized, a motion vector of the synthesis signal is detected, a synthesis interpolation exclusion area is decided where the interpolation in the synthesis signal is not performed on the basis of the synthesis information and interpolation control information indicating an input interpolation exclusion area where the interpolation in the respective input image signals is not performed, and a synthesis signal in-between signal is interpolated and output which is an image signal at an arbitrary time between the synthesis signal and a previous synthesis signal on the basis of the motion vector in an area other than the synthesis interpolation exclusion area.

Abstract: An image shake correction apparatus of a camera in which an object image is formed on an image sensor that is driven to move in first and second directions, which are orthogonal to each other, in a plane orthogonal to an optical axis to compensate for camera shake. The image shake correction apparatus includes a first table provided in a camera body to be movable in the first direction, and a second table which supports the image sensor and is movable in the second direction on the first table. At least one of the first table and the second table is supported by one guide bar and supported by a linear actuator which moves the one of the first table and the second table along the one guide bar, the one guide bar extending in a corresponding one of the first direction and the second direction.

Abstract: In an image acquisition apparatus, RAW data obtained in image acquisition with an imager in which a color filter is disposed in a front face is divided into each identical color by a RAW data dividing unit, a compression coding processing unit produces coded data of each color by compressing the RAW data at a compression rate controlled for each color, and the coded data of each color is recorded in a recording unit. A motion compensation unit compensates a relative positional relationship between frames by estimating a motion of a subject between frames of plural images, using specific color division coded data which is decoded by the compression coding processing unit and a RAW format data reproducing unit, the specific color division coded data being coded data of a color close to a peak of spectral sensitivity of human vision in the coded data of each color.

Abstract: An image processing device that performs registration processing between a plurality of images using an image transformation defined by at least one inter-frame motion vector, is provided with a lens characteristic acquisition unit for obtaining a lens characteristic of an imaging lens that photographs the plurality of images; a motion vector measurement region setting unit for setting, on the basis of the lens characteristic, a plurality of motion vector measurement regions in each of which a motion vector is to be measured; a motion vector reliability calculation unit for calculating a reliability of each of calculated motion vectors; and a motion vector integration processing unit for calculating the at least one inter-frame motion vector by integrating the motion vectors of the plurality of motion vector measurement regions in accordance with the reliability of the motion vectors.

Abstract: A photography mode selecting section allows a photographer to select continuous photographing. An imaging section captures an image of a subject. An area setting section detects a photographic subject based on a photographic image captured by the imaging section for every photographing in the continuous photographing, and sets the size and position of a photographic subject area including the detected photographic subject, when the continuous photographing is selected by the photography mode selecting section. A memory section stores an image inside the photographic subject area as a photographic subject image. Consequently, in continuous photographing of a moving body, the size of the photographic subject area for every photographing in the continuous photographing can be changed according to change in the size of the image of the moving body with respect to an image screen of the imaging section, thereby preventing wasteful usage of a memory area of the memory section.

Abstract: A motion estimation method is provided for processing successive images in an image sequence, with a motion vector being associated with each of the processed images. For a current image, motion vectors associated with images that precede the current image in the sequence are selected. Candidate motion vectors are generated from the motion vectors that are selected. A motion vector is elected from among the candidate motion vectors. Information that associates the elected motion vector with the current image is stored in memory. At least one of candidate motion vectors is an acceleration vector generated from the acceleration between first and second motion vectors averaged relative to a first and second images, with the first and second images being distinct and preceding the current image in the image sequence. A motion vector averaged relative to a given image is obtained from selected motion vectors associated with images preceding the given image.

Abstract: A method for producing an improved high resolution image is disclosed including capturing low resolution images and a high resolution image; combining the low resolution images to provide an aggregate low resolution image; reducing the resolution of the high resolution image and then interpolated to produce a blurred high resolution image; calculating an image difference map using the aggregate high resolution image and blurred high resolution image; and using the image difference map along with the aggregate high resolution image and the high resolution image to produce an improved high resolution image.

Abstract: An image acquisition sensor of a digital image acquisition apparatus is coupled to imaging optics for acquiring a sequence of images. Images acquired by the sensor are stored. A motion detector causes the sensor to cease capture of an image when the degree of movement in acquiring the image exceeds a threshold. A controller selectively transfers acquired images for storage. A motion extractor determines motion parameters of a selected, stored image. An image re-constructor corrects the selected image with associated motion parameters. A selected plurality of images nominally of the same scene are merged and corrected by the image re-constructor to produce a high quality image of the scene.

Abstract: A processing device (D) is dedicated to image frame stabilization of digital video sequences in an electronic equipment (E1), such as a digital camera, for instance. This processing device (D) comprises processing means (PM) arranged, for each current image frame of a video sequence, for determining a type of motion present in the video sequence from global motion parameters of the current image frame and the ones of at least one preceding image frame of this video sequence. These parameters are determined from a motion estimation between the current image frame and the preceding one of the video sequence. The motion determination is followed by a selection of a jitter extraction technique amongst at least two jitter extraction techniques depending on this determined motion type. The jitter extraction technique thus chosen is used to determine a jitter intended to be removed from the determined global motion parameter(s) in order to remove unwanted motion(s) present into the current image frame.

Abstract: A method for increasing resolution of a focal plane array having a plurality of pixels dispersed across a total pixel area is described. The method includes providing an active pixel area for the focal plane array that is less than the total pixel area, acquiring image data utilizing the reduced active pixel area, and storing the image data in a portion of a memory, the memory having a capacity corresponding to the total pixel area of the focal plane array.

Abstract: 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.

Abstract: A camera system in normal mode and hand jitter reduction (hjr) mode may comprise generating a first exposure time-gain product by multiplying the normal mode exposure time with the normal mode gain. It may further comprise modifying the normal mode exposure time and gain and multiplying these modified parameters to generate a second exposure time-gain product for a hjr mode that reduces the difference between the first exposure time-gain product and the second exposure time-gain product. To reduce the difference the normal mode frame rate may also be modified. Operation of a camera in normal mode may be in response to a sensed light level being above a threshold. The hjr mode may be selected by the user while the camera is operating. The hjr mode may be used in response to a sensed light level being lower than the threshold.

Abstract: To handle static text and logos in stabilized images without destabilizing the static text and logos, a method of handling overlay subpictures in stabilized images includes detecting an overlay subpicture in an input image, separating the overlay subpicture from the input image, stabilizing the input image to form a stabilized image, and merging the overlay subpicture with the stabilized image to obtain an output image.

Abstract: An imaging device and its image processing for creating an image with less blur from a small number of images under different exposure conditions in a shortened processing time. The imaging device 10 captures an image by means of an optical system 11 and an imaging element 12 in a short exposure time with a high resolution and much noise and images in a long exposure time with low resolution and less noise. After signal processing by signal processing section 13, a CPU 14 detects the position variation between captured images and blurs, separates the edges blur and the noise by using the threshold from the two difference images, combines the two images at a varied combination ratio, and thereby creates an image with no blur and reduced noise.

Abstract: An apparatus takes in a plurality of still image frames, to generate an interpolated image frame. Next, moving addition of the still image frame and an interpolated image frame is performed in time-axis direction, to generate a superimposed image frame. At this time, high spatial frequency components in the superimposed image frame are suppressed strongly as alienation of motion between the still image frames becomes larger. Movie is reproduced by sandwiching these superimposed image frames between the still image frames. As a result of this, the movie reproduction with smooth motion is made possible even from a group of the still images photographed by an electronics still camera and the like.

Abstract: An imaging apparatus includes an imaging part that images a subject to generate image data, an image storage part that temporarily stores original image data that was imaged by the imaging part, an image data size reducing part that forms image data for display by reducing the size of image data stored in the image storage part, and an image display part that displays image data for display that was formed by the image data size reducing part; the imaging apparatus further comprising a camera shake state detection part that detects a camera shake occurrence state of the imaging part, a camera shake decision part that decides whether or not camera shake occurred for image data for display that was reduced by the image data size reducing part based on a camera shake state that was detected by the camera shake state detection part, and a camera shake correction part that, when a result decided by the camera shake decision part is that a camera shake occurrence state exists, subjects the image data for display to

Abstract: Exposed images from a CCD are each captured to Surfaces A, B and C in an SDRAM in a repeated sequence from A, B to C, and the latest image among the images thus captured is displayed. While an image on Surface B is being transferred, an image on Surface A is used as the image to be displayed. The next exposure is started, and images to be displayed are switched, at the same timing as the transfer is started. An image to be displayed on an LCD monitor is stopped from being updated when camera shake compensating device starts to be released from the mechanical holding. The next switching of images and the transfer of an exposed image from the CCD to the SDRAM are prohibited. When the release of the mechanical holding is completed, the next exposed image is transferred from the CCD to the SDARM. Updating is permitted for displaying the image which is transferred to the SDRAM on a display device.

Abstract: A method for simulating an image captured at a long exposure time (“simulated image”), includes (1) capturing each of first, second, and third images at a short exposure time, (2) determining a first relative motion between the first and the second images, (3) transforming the first image to remove the first relative motion, (4) determining a second relative motion between the third and the second images, (5) transforming the third image to remove the second relative motion, and (6) combining the first, the second, and the third images to form the simulated image. Relative motions between images are determined by matching blocks at multiple resolutions to determine corresponding points between the images. Transformation to remove relative motion is determined by fitting corresponding points between the images using a minimum square error (MSE) algorithm in a random sample consensus (RANSAC) framework.

Abstract: A digital camera 100 is provided with an optical unit 1, CCD 3, a CCD holder 27 for holding CCD 3, actuator 10 for connecting the CCD holder 27 with the optical unit 1, wherein the actuator changes in shape when a voltage is applied across a front surface and rear surface thereof, and flexible printed circuits 8, 9 for applying voltages to driving members 10a, 10b, 10c and 10d in response to detection of camera shake to move the CCD holder 27 such that an optical axis Z of the optical unit 1 passes through the center of the image capturing plane 300 of CCD 3.

Abstract: An optical system, imaging device and high-resolution processing method precisely generate a high-resolution image by using image data with few pixels. The optical system images an optical image in an imaging unit, the imaged image is spatially discretized so as to be sampled and converted into an image signal, thereby being recorded in a recording unit. A timing at which the image is imaged by the imaging unit is recorded in an imaging timing recording unit. A weight coefficient for the image is calculated by a weight calculating unit by utilizing the timing information obtained by the imaging timing recording unit. A high-resolution processing unit generates a high-resolution image by using the weighted information of the image generated by the weight calculating unit.

Abstract: A method of auto-photographing for an image capturing device is disclosed. A predetermined time for auto-photographing is counted down. Consecutive preview images of a scene to be photographed are acquired after the predetermined time begins to be counted. Whether a moving object bursts into the scene to be photographed is detected by comparing the consecutive preview images. If the moving object bursts into the scene to be photographed, the predetermined time for auto-photographing is recounted down again.

Abstract: A multi-eye imaging apparatus comprises a plurality of imaging systems (106a, 106b) each including an optical system (107a, 107b) and an imaging element (108a, 108b) and having a different optical axis. The plurality of imaging systems (106a, 106b) include a first imaging system (106b) having a pixel shift means (101) for changing a relative positional relationship between an image formed on the imaging element (108b), and the imaging element (108b), and a second imaging system (106a) in which a relative positional relationship between an image formed on the imaging element (108a), and the imaging element (108a), is fixed during time-series image capture.

Abstract: Some embodiments allow a video editor to remove unwanted camera motion from a sequence of video images (e.g., video frames). Some embodiments are implemented in a video editing application. Some of these embodiments distinguish unwanted camera motion from the intended underlying motion of a camera (e.g., panning and zooming) and/or motion of objects within the video sequence.