90 results about "Binocular disparity" patented technology

An image processing apparatus and method may estimate binocular disparity maps of middle views from among a plurality of views through use of images of the plurality of views. The image processing apparatus may detect a moving object from the middle views based on the binocular disparity maps of the frames. Pixels in the middle views may be separated into dynamic pixels and static pixels through detection of the moving object. The image processing apparatus may apply bundle optimization and a local three-dimensional (3D) line model-based temporal optimization to the middle views so as to enhance binocular disparity values of the static pixels and dynamic pixels.

A binocular display deals with an optical contrast imbalance problem between display screens manifest over a range of interpupillary distances by orienting contrast asymmetries between the display screens in opposite directions.

An augmented reality system in which video imagery of a physical environment is combined with video images output by a game engine by the use of a traveling matte which identifies portions of the visible physical environment by techniques such as Computer vision or chroma keying and replaces them with the video images output by the video game engine. The composited imagery of the physical environment and the video game imagery is supplied to a trainee through a headmounted display screen. Additionally, peripheral vision is preserved either by providing complete binocular display to the limits of peripheral vision, or by providing a visual path to the peripheral vision which is matched in luminance to higher resolution augmented reality images provided by the binocular displays. A software / hardware element comprised of a server control station and a controller onboard the trainee performs the modeling, scenario generation, communications, tracking, and metric generation.

The invention provides a binocular disparity estimation method based on a cascaded geometric context neural network. The invention designs a new cascaded convolution neural network Cascaded GCNet (CGCNet). The network mainly adopts the improved GCNet and combines the 3d convolution and the original 2d convolution operation to obtain a better disparity map characteristic expression, which is beneficial to the subsequent network training. RefineNet is used to optimize the rough parallax map of GCnet network, and the precision of parallax map is improved by iterative refinement. In the process ofRefineNet optimization, difficult mining is used to make the network model focus on learning rare samples, so as to improve the disparity estimation accuracy of the network for image pairs with different complexity.

The invention discloses a method and device for converting a two-dimensional image into a three-dimensional image, and a three-dimensional imaging system. The method for converting the two-dimensionalimage into the three-dimensional image comprises the following steps: obtaining a two-dimensional image to be processed; performing perspective transformation on the two-dimensional image to be processed to obtain a left eye image and a right eye image separately; adjusting the distance between the left eye image and the right eye image according to the result of the perspective transformation; and synthesizing the left eye image and the right eye image after distance adjusting. According to the embodiment of the invention, a binocular parallax image is created through performing perspectivetransformation on the two-dimensional image to be processed; and the distance adjusting is performed on the left eye image and the right eye image after perspective transformation to form the binocular parallax and create a convergence angle, so that the image observed by naked eyes lies at different depths and different stereoscopic effects can be seen. The image transformation is performed through the two-dimensional image, which does not relate to the resolution and clarity of the image; therefore, the image quality of the image of 3D imaging is the same as that of the original two-dimensional image, and the effect of 3D imaging is not affected.

A mobile terminal and a method of controlling the operation of the mobile terminal are provided. The method includes dividing each of first and second images into a plurality of blocks, the first and second images capable of realizing a three-dimensional (3D) image using binocular disparity; searching the first and second images for pairs of matching blocks and calculating depth information of each of the pairs of matching blocks based on a difference in position between each of the pairs of matching blocks; and calculating stereoscopic information of the 3D image based on the depth information of each of the pairs of matching blocks. Therefore, it is possible to effectively provide stereoscopic information of a 3D image for various purposes.

An image processing apparatus and method may estimate binocular disparity maps of middle views from among a plurality of views through use of images of the plurality of views. The image processing apparatus may detect a moving object from the middle views based on the binocular disparity maps of the frames. Pixels in the middle views may be separated into dynamic pixels and static pixels through detection of the moving object. The image processing apparatus may apply bundle optimization and a local three-dimensional (3D) line model-based temporal optimization to the middle views so as to enhance binocular disparity values of the static pixels and dynamic pixels.

A depth estimating apparatus operated by at least one processor includes: a database which stores a photographed first color image, a training thermal image geometrically aligned with the first color image, and a second color image simultaneously photographed with the first color image as a training image set; and a training apparatus which trains a neural network in an unsupervised manner to output a chromaticity image and a binocular disparity image from the training thermal image. The training apparatus generates an estimated first color image from the second color image, the chromaticity image, and the binocular disparity image, and trains the neural network to minimize a difference between the estimated first color image and the photographed first color image.