A method for creating a pair of stereoscopic images is described. The method includes using at least one lightfield camera which receives respective required camera parameters for a left view and a right view. The required camera parameters define a theoretical stereo image pair to acquire respective actual camera parameters for respective sub aperture images that are generated based on the captured image by the lightfield cameras, to determine a best matching sub aperture image for the left view by comparing the required camera parameter for the left view with the actual camera parameters for the respective sub aperture images, to determine a best matching sub aperture image for right view by comparing the required camera parameter for right view with the actual camera parameters for the respective sub aperture images, and to associate the best matching sub aperture image for left view and the best matching sub aperture image for right view as a pair of stereoscopic images.

One aspect of the present invention provides an image processing apparatus capable of tracking an image region to be tracked with high accuracy.

A distance distribution generation unit generates distance information indicating a distance of each of regions in first image data. An object likelihood distribution generation unit generates a likelihood distribution of an object in the first image data based on information indicating a position specified as the object in the first image data, the distance information, and reliability of the distance information. A feature amount extraction unit calculates a feature amount to be used to detect the object from second image data based on the likelihood distribution.

An adaptive image acquisition system and method that generates virtual view of a surveillance scene to a user (operator), in which, the user operates the system. Through viewing the virtual view, the user controls sensors that create the virtual view. The sensors comprise at least one first sensor having a higher resolution than at least one second sensor. Images from the second sensor are processed to create an image mosaic that is overlaid with images from the higher resolution first sensor. In one embodiment of the invention, the first sensor is moved using Saccade motion. In another embodiment of the invention, a user's intent is used to control the Saccade motion.

Provided is an electronic device, wherein the at least one processor is configured to execute the at least one instruction to obtain a first light field image including view images with a first number of views, obtain, from the first light field image, a second light field image including view images with a second number of views, obtain first location information corresponding to each of sub-pixels in the second light field image, obtain a first layer image by inputting the second light field image and the first location information to an artificial intelligence model configured to perform factorization, obtain a third light field image including view images with a third number of views by inputting the first layer image to a simulation model, and train the artificial intelligence model, based on a result of comparing the first light field image and the third light field image with each other.

An image processing device includes a processor including hardware, the processor being configured to calculate comparison result information through a comparison process performed on the results of a census transform process performed on a first image and the results of the census transform process performed on a second image, set weight information, calculate a cost using the comparison result information and the weight information, calculate the amount of disparity using the cost, set a first weight having as low degree of contribution to the cost on a neighboring pixel which is determined to be affected by noise to a large extent among a plurality of neighboring pixels, and set a second weight having a high degree of contribution to the cost on a neighboring pixel which is determined to be affected by noise to a small extent among the plurality of neighboring pixels.

An image processing apparatus includes a restrictive condition storage unit in which at least one restrictive condition, which is to be applied to an image to be output and acquired from a subject, is stored, an accepting unit that accepts an image that is obtained by shooting the subject and has at least one field, an image changing unit that applies the at least one restrictive condition to the at least one field of the image accepted by the accepting unit, changes the at least one field so that it satisfies the at least one restrictive condition, and acquires at least one new field, and an image output unit that outputs the at least one field acquired by the image changing unit, enabling an image having an overall balance to be output.

A miniaturized active dual pixel stereo system and method for close range depth extraction includes a projector adapted to project a locally distinct projected pattern onto an image of a scene and a dual pixel sensor including a dual pixel sensor array that generates respective displaced images of the scene. A three-dimensional image is generated from the displaced images of the scene by projecting the locally distinct projected pattern onto the image of the scene, capturing the respective displaced images of the scene using the dual pixel sensor, generating disparity images from the respective displaced images of the scene, determining depth to each pixel of the disparity images, and generating the three-dimensional image from the determined depth to each pixel. A three-dimensional image of a user's hands generated by the active dual pixel stereo system may be processed by gesture recognition software to provide an input to an electronic eyewear device.

In some examples, one or more processors may receive at least one first visible light image and a first thermal image. Further, the processor(s) may generate, from the at least one first visible light image, an edge image that identifies edge regions in the at least one first visible light image. At least one of a lane marker or road edge region may be determined based at least in part on information from the edge image. In addition, one or more first regions of interest in the first thermal image may be determined based on at least one of the lane marker or the road edge region. Furthermore, a gain of a thermal sensor may be adjusted based on the one or more first regions of interest in the first thermal image.

An electronic device that reprojects two-dimensional (2D) images to three-dimensional (3D) images includes a memory configured to store instructions, and a processor configured to execute the instructions to: propagate an intensity for at least one pixel of an image based on a depth guide of neighboring pixels of the at least one pixel, wherein the at least one pixel is considered a hole during 2D to 3D image reprojection; propagate a color for the at least one pixel based on an intensity guide of the neighboring pixels of the at least one pixel; and compute at least one weight for the at least one pixel based on the intensity and color propagation.

The disclosure relates to an image processing apparatus for determining a depth of a pixel of a reference image of a plurality of images representing a visual scene relative to a plurality of locations, wherein the plurality of locations define a two-dimensional grid with rows and columns and wherein the location of the reference image is associated with a reference row and a reference column of the grid. The image processing apparatus comprises a depth determiner configured to determine a first depth estimate on the basis of the reference image and a first subset of the plurality of images for determining the depth of the pixel of the reference image, wherein the images of the first subset are associated with locations being associated with a row of the grid different than the reference row and with a column of the grid different than the reference column.