A focus detection apparatus comprising: a focus detection unit that detects an in-focus position using an image signal obtained by an image sensor photoelectrically converting light that has entered via an imaging optical system; a first acquisition unit that acquires aberration information of the imaging optical system; a generating unit that generates a recording image using the image signal; a calculation unit that calculates, on the basis of the aberration information, a correction value for correcting a difference between the in-focus position detected by the focus detection unit and a position to be focused on in the recording image; and a correction unit that corrects the in-focus position using the correction value. The calculation unit calculates the correction value on the basis of information of a display unit that displays an image based on the image signal.

An electronic device includes an image sensor that generates first image data upon receiving external light, generates second image data based on the first image data, and outputs the first image data and the second image data, and an application processor that increases resolution of at least a region of an image that corresponds to the first image data using a machine learning algorithm and outputs third image data that includes at least a portion of the first image data with increased resolution and at least a portion of the second image data.

An electronic device includes an image sensor that generates first image data upon receiving external light, generates second image data based on the first image data, and outputs the first image data and the second image data, and an application processor that increases resolution of at least a region of an image that corresponds to the first image data using a machine learning algorithm and outputs third image data that includes at least a portion of the first image data with increased resolution and at least a portion of the second image data.

The technology relates to a refuse collection system including: a camera configured to capture image data; a sensor configured to capture spatial data; and a processing module in communication with the camera and the sensor, the processing module configured to: process the image data to assist in identifying an object; and process the spatial data in a region associated with the object in order to determine one or more characteristics associated therewith, wherein in response to confirming that the object is a bin based on the one or more characteristics associated with the object, the processing module is configured to provide information to assist in retrieving the bin with a bin-collecting device.

The present disclosure relates to a solid-state image pickup device and an electronic apparatus by which a phase-difference detection pixel that avoids defects such as lowering of sensitivity to incident light and lowering of phase-difference detection accuracy can be realized. A solid-state image pickup device as a first aspect of the present disclosure is a solid-state image pickup device in which a normal pixel that generates a pixel signal of an image and a phase-difference detection pixel that generates a pixel signal used in calculation of a phase-difference signal for controlling an image-surface phase difference AF function are arranged in a mixed manner, in which, in the phase-difference detection pixel, a shared on-chip lens for condensing incident light to a photoelectric converter that generates a pixel signal used in calculation of the phase-difference signal is formed for every plurality of adjacent phase-difference detection pixels. The present disclosure is applicable to a backside illumination CMOS image sensor and an electronic apparatus equipped with the same.

A dual sensor imaging system and a privacy protection imaging method thereof are provided. The system is configured to control at least one color sensor and at least one IR sensor to respectively capture multiple color images and multiple IR images by adopting multiple exposure conditions adapted for an imaging scene, adaptively select a combination of the color image and the IR image that can reveal details of the imaging scene, detect a feature area with features of a target of interest in the color image, and fuse the color image and the IR image to generate a fusion image with the details of the imaging scene, and crop an image of the feature area of the fusion image to be replaced with an image not belonging to the IR image, so as to generate a scene image.

A dual sensor imaging system and a privacy protection imaging method thereof are provided. The system is configured to control at least one color sensor and at least one IR sensor to respectively capture multiple color images and multiple IR images by adopting multiple exposure conditions adapted for an imaging scene, adaptively select a combination of the color image and the IR image that can reveal details of the imaging scene, detect a feature area with features of a target of interest in the color image, and fuse the color image and the IR image to generate a fusion image with the details of the imaging scene, and crop an image of the feature area of the fusion image to be replaced with an image not belonging to the IR image, so as to generate a scene image.

A pixel may include an inner sub-pixel group and an outer sub-pixel group. The inner sub-pixel group may have a smaller light collecting area than the outer sub-pixel group and therefore be less sensitive to light than the outer sub-pixel group. This may enable the pixel to be used to generate high dynamic range images, even with the sub-pixel groups using the same length integration time. The inner sub-pixel group may be nested within the outer sub-pixel group. Additionally, one or both of the inner sub-pixel group and the outer sub-pixel group can be split into at least two sub-pixels so that the sub-pixel group can be used to gather phase detection data. Adjacent pixels may have sub-pixel groups split in different directions to enable detection of vertical and horizontal edges in a scene.

There is provided an information processing apparatus capable of determining an object area with high accuracy. An object area determination unit of the information processing apparatus acquires defocus information of positions in a captured image and information of a position specified as an object in the captured image, and determines, based on a difference between a defocus value at each of the positions and a defocus value at the specified position, an estimated area of the object specified in the captured image. Further, the object area determination unit determines an object area from the captured image based on an evaluation value calculated from each of a plurality of evaluation areas set for the specified position.

An encoder is disclosed that uses hyperspectral data to produce a unified three-dimensional (“3D”) scan that incorporates depth for various points, surfaces, and features within a scene. The encoder may scan a particular point of the scene using frequencies from different electromagnetic spectrum bands, may determine spectral properties of the particular point based on returns measured across a first set of bands, may measure a distance of the particular point using frequencies of another band that does not interfere with the spectral properties at each of the first set of bands, and may encode the spectral properties and the distance of the particular point in a single hyperspectral dataset. The spectral signature encoded within the dataset may be used to classify the particular point or generate a point cloud or other visualization that accurately represents the spectral properties and distances of the scanned points.