Sony Corporation

Sony Semiconductor Solutions Corporation

Yoshikuni Nomura

Tomoo Mitsunaga

Shun Kaizu

Shigeyuki Baba

Norihiro Tanabe

Mitsuharu Ohki

Eiji Oba

Shigeki Nakamura

Masanori Kasai

Teppei Kurita

Markus Kamm

Masayuki Tachi

Kensei Jo

Hajime Hosaka

Seichi Otsuki

Satoru Takeuchi

Ryuhei Hata

Fabian Schaschek

Ohki Mitsuharu

Yoshiki Ando

Yusuke Shinmi

Shingo Iriyama

Yutaka Moriyama

To generate training data setting various sensor states. A method for generating data is a method for generating training data used for machine learning from a CG model using a processor. The method for generating data includes: generating, through simulation, a first image acquired under a first imaging condition and a second image acquired under a second imaging condition that is different from the first imaging condition, in the CG model, and acquiring at least the first image and the second image as input image data in the training data.

Data generation method, learning method, and estimation method

There is provided an imaging device including a pixel array unit () configured by arraying, in a row direction and a column direction, a plurality of pixels () of five or more types in which wavelength bands of detectable light are different in stages. The plurality of pixels are arrayed such that, at points having any spatial phases on the pixel array unit, mixed spectral characteristics obtained by mixing spectral characteristics of a predetermined number of pixels around the points are substantially same.

Imaging device and electronic equipment

Configuration, in which images output to a display unit are switched and displayed in accordance with the behavior of a driver, such as movements of the head of the driver, is achieved. Driver information indicating the behavior of the driver of a moving apparatus and images captured by a plurality of cameras that images a situation around the moving apparatus from different viewpoints are input. The images output to the display unit are switched in accordance with the driver information. The plurality of cameras is, for example, a plurality of rear cameras installed in the rear of the moving apparatus. For example, a direction of the face or line-of-sight of the driver is detected. An image in a direction corresponding to the detected direction of the face or line-of-sight of the driver is selected as an output image, and displayed on the display unit. Alternatively, an image in a direction indicated by a gesture of the driver is selected, and displayed on the display unit.

Image processing apparatus, moving apparatus, method, and program

Provided are an image processing apparatus, an image processing method, and an imaging apparatus. An image processing apparatus includes a demosaic processing unit configured to apply demosaic processing to a mosaic image having a first number of colors to generate a multispectral image having a second number of colors equal to or more than three but less than the first number of colors.

Image processing apparatus, image processing method, and imaging apparatus

The present technology relates to an image processing device, an image processing method, and an imaging device capable of correcting an image according to characteristics peculiar to each lens without executing an individual adjustment process. An image processing device according to a first aspect of the present technology includes a quantitative value calculating unit which calculates a quantitative value of a sample image based on an obtained image, an average value calculating unit which calculates an average value of the quantitative values calculated from a plurality of the sample images, a holding unit which holds the calculated average value of the quantitative values, and a correcting unit which corrects an imaged image on the basis of the held average value of the quantitative values. The present technology can be applied to a digital camera.

Image processing device, image processing method, and imaging device

There is provided a signal processing method including calculating, by a processor, a distortion correction parameter on a basis of a correlation between a chief ray angle (CRA) for an image height inside a pixel and a relative position of a lens in an optical axis direction to an imaging element, the relative position being changed by an actuator. In addition, there is provided an imaging device including an image calculation unit that converts an image by using a distortion correction parameter calculated on a basis of a correlation between a chief ray angle for an image height inside a pixel and a relative position of a lens in an optical axis direction to an imaging element, the relative position being changed by an actuator.

Signal processing method and imaging device

An electronic device including an optical system that combines a first lens and a second lens by means of a beam splitter.

Optical system, electronic device, camera, method and computer program

Provided are an apparatus and method for executing sensitivity difference correction processing of an image signal, which is generated by a single plate-type image sensor through a color filter. The sensitivity difference correction is executed for Gr and Gb signals included the image signal, for example, an RGB signal, which is generated by the single plate-type image sensor through the color filter. A pixel value of a color filter unit which has the same color as a correction target pixel and is present in surroundings of the correction target pixel is acquired. An additional value is calculated by adding a difference between weighted mean pixel values 'a' and 'b' of two kinds of pixel groups &#x201c;A&#x201d; and &#x201c;B&#x201d; classified according to positions of pixels to the pixel value of the correction target pixel in which the weighted mean values correspond to distances of the pixel groups from the correction target pixel. A mean value of the pixel value of the correction target pixel and the additional value is calculated as a corrected pixel value of the correction target pixel.

Image processing apparatus, image processing method, and program for executing sensitivity difference correction processing

Provided is an image processing apparatus including an infinite impulse response (IIR) mean value calculation section for calculating a mean value of signal values of reference pixels around a correction target pixel according to an IIR filter application process, an IIR variance value calculation section for calculating a variance value of the signal values of the reference pixels around the correction target pixel according to the IIR filter application process, an edge-preserving smoothing processing section for receiving the mean and variance values of the reference pixels and executing an edge-preserving smoothing process to which the mean and variance values are applied, and an IIR filter coefficient calculation section for updating an IIR filter coefficient to be applied to the IIR mean value calculation section and the IIR variance value calculation section according to a signal value of a pixel constituting an image.

Image processing apparatus, image processing method, and program

An image processing apparatus includes: a characteristic value calculation unit calculating a block luminance average value, which is an average value of luminance values in each of spatial blocks obtained by dividing an input image in a space direction, and a block luminance dispersion, which is a dispersion of the luminance values in each of the spatial blocks; and an edge-preserving smoothing unit calculating a general luminance value of pixels of the input image by setting a value obtained by approximately calculating a weighted average value of the luminance values of a noticed block containing noticed pixels of the input image, on the assumption that a distribution of the luminance values of each of the spatial blocks conforms to a Gaussian distribution based on the block luminance average value and the block luminance dispersion of each of the spatial blocks, as the general luminance value of the noticed pixels.

An image processing device includes an image correction unit which receives a synthesized image and pseudo color pixel information indicating a pseudo color pixel position included in the synthesized image and executes pixel value correction. The image correction unit selects non-pseudo color pixels as reference pixels from a reference region set in a surrounding region of the pixel to be corrected, sets a similarity weight coefficient in which a large weight is set as a pixel value of the reference pixel that is close to a pixel value of the pixel to be corrected and a pixel position weight coefficient in which a large weight is set as the pixel value of the reference pixel that is near a pixel position of the pixel to be corrected, with respect to the reference pixels, and determines a correction pixel value of the pixel to be corrected by a weighted summation process.

Image processing device, method, and computer-readable medium for executing pixel value correction in a synthesized image

An image processing apparatus includes: a first distribution calculation unit calculating a distribution of luminance gradient vectors in a first local area that includes a feature point on an image; a second distribution calculation unit calculating distributions of the luminance gradient vectors in second local areas close to the feature point on the image; a selection unit comparing the distribution of the luminance gradient vectors of the first local area with the distributions of the luminance gradient vectors of the second local areas to select the most different distribution of the luminance gradient vectors of the second local area; and a feature descriptor calculation unit calculating a feature descriptor at the feature point on the basis of the distribution of the luminance gradient vectors of the first local area and the distribution of the luminance gradient vectors of the second local area selected by the selection unit.

Image processing apparatus, image processing method and program

A method for manufacturing a color image pickup device including a pixel group in which a plurality of pixels each having a photoelectric conversion element and a color filter are arranged includes the steps of generating a random array pattern in which color filters of at least one color component are randomly arranged for an arbitrary pixel position, so that the occurrence frequency of color filters of a color component in a region having a predetermined size including the arbitrary pixel position is within a desired error range, generating a regular array pattern in which color filters of at least one color component are regularly arranged, and generating a color filter pattern by compositing in a regular manner the random array pattern generated in the random array generating step and the regular array pattern generated in the regular array generating step.

Method and apparatus for manufacturing color image pickup device including a random array pattern and a regular array pattern

A color filter array includes a plurality of filters, each having one of a plurality of types of spectral sensitivity and being disposed at the location of a corresponding one of a plurality of pixels. The filters of a predetermined type selected from among the plurality of types are arranged at the locations of the pixels in a checkered pattern, and the filters of some or all of the other types are randomly arranged at the pixel locations at which the filters of the predetermined type are not present.

Growing community of inventors

Tokyo, Japan

Yoshikuni Nomura