Described herein is an image processing apparatus (701) comprising one or more processors (704) configured to: receive (601) a plurality of input images (301, 302, 303); for each input image, form (602) a set of decomposed data by decomposing the input image (301, 302, 303) or a filtered version thereof (307, 308, 309) into a plurality of frequency-specific components (313) each representing the occurrence of features of a respective frequency interval in the input image or the filtered version thereof; process (603) each set of decomposed data using one or more convolutional neural networks to form a combined image dataset (327); and subject (604) the combined image dataset (327) to a construction operation that is adapted for image construction from a plurality of frequency-specific components to thereby form an output image (333) representing a combination of the input images. The resulting HDR output image may have fewer artifacts and provide a better quality result. The apparatus is also computationally efficient, having a good balance between accuracy and efficiency.

Provided are an image capturing method and apparatus, a device and a storage medium. The method includes: at a new acquisition moment, predicting a predicted projection area position of a target object in a current captured image on an image sensor and estimated exposure brightness information of the target object in the predicted projection area position; adjusting, according to a type of the target object and the estimated exposure brightness information, an exposure parameter of the target object in the predicted projection area position when the new acquisition moment arrives; and acquiring a new captured image at the new acquisition moment according to the adjusted exposure parameter, where both the new captured image and the current captured image include the target object.

This application provides an image sensor (702) and image light sensing method. The image sensor (702) includes a red pixel (R), a green pixel (G), a blue pixel (B), and an invisible light pixel, where the red pixel (R), the green pixel (G), and the blue pixel (B) are large pixels, the invisible light pixel is a small pixel, and a light sensing area of the large pixel is greater than that of the small pixel. The red pixel (R), the green pixel (G), and the blue pixel (B) are arranged in a Bayer format. In this application, when color information is sufficient, light crosstalk caused by the small pixel to the large pixel can be reduced, and therefore a signal-to-noise ratio of the large pixel can be improved.

Provided is an imaging apparatus capable of continuously imaging a natural video even though brightness is changed. In an imaging apparatus in which an exposure condition is set based on a characteristic of a transmittance control element, a first exposure condition range is calculated based on photometry of the imaging apparatus. Determination is made whether or not the calculated first exposure condition range is included in a second exposure condition range where a control range acquired by the transmittance control element is applicable. In a case where the calculated first exposure condition range is not included in the second exposure condition range, the exposure condition of the imaging apparatus is changed such that the first exposure condition range is included in the second exposure condition range.

A scanning system and method for controlling an aiming light source (7), comprising: an image sensor (4), which sequentially exposes a pixel array through a rolling shutter to acquire an image of the target, the pixel array includes effective pixels (5) and non-imaging pixels (6), the effective pixels (5) are pixels that are actually used for image decoding, and the non-imaging pixels (6) are pixels that are not actually used for image decoding; an aiming light source (7) for projecting an aiming pattern (8) to aim at a target; a control unit (12) for controlling the image sensor (4) and the aiming light source (7), so that the aiming light source (7) is in turned off state during the exposure time of the effective pixel (5), and the aiming light source (7) is turned on during at least part of the exposure time of the non-imaging pixels (6).

Devices, methods, and computer-readable media are disclosed, describing an adaptive, subject-aware approach for image bracket selection and fusion, e.g., to generate high quality images in a wide variety of capturing conditions, including low light conditions. An incoming image stream may be obtained from an image capture device, comprising images captured using differing default exposure values, e.g., according to a predetermined pattern. When a capture request is received, it may be detected whether one or more human or animal subjects are present in the incoming image stream. If a subject is detected, an exposure time of one or more images selected from the incoming image stream may be reduced relative to its default exposure time. Prior to the fusion operation, one of the selected images may be designated a reference image for the fusion operation based, at least in part, on a sharpness score and/or a blink score of the image.

A device includes an offset subtraction unit; an image sensor which receives, for each of a plurality of bright frames, a respective image signal obtained during a respective exposure time of the image sensor, and transmits the same to the offset subtraction unit, and receives, for a dark frame, a respective image signal obtained during a respective exposure time of the image sensor, and transmits the same to the offset subtraction unit; and a control unit which ensures that the image sensor alternately transmits a number of bright frames and one dark frame to the offset subtraction unit. An amount of light by which the respective image signal for each of the bright frames is generated is larger than an amount of light by which the respective image signal for the dark frame is generated; and the offset subtraction unit obtains an offset and subtracts the offset from a signal.

An image recognition device (image recognition system 100) according to the present disclosure includes an imaging unit (10) and a recognition unit (14). The imaging unit (10) captures a plurality of images at the same exposure start timing in one frame period by using imaging pixels having different sensitivities to generate image data. The recognition unit (14) recognizes a subject from each of the image data. The imaging unit (10) includes a pixel array in which a plurality of imaging pixels having different exposure times, different light transmittances of color filters, or different light receiving areas are two-dimensionally arranged.

A method includes obtaining multiple images of a scene using at least one red-green-blue-white (RGBW) image sensor. The method also includes generating multi-channel frames at different exposure levels from the images. The method further includes estimating motion across exposure differences between the different exposure levels using a white channel of the multi-channel frames as a guidance signal to generate multiple motion maps. The method also includes estimating saturation across the exposure differences between the different exposure levels to generate multiple saturation maps. The method further includes using the generated motion maps and saturation maps to recover saturations from the different exposure levels and generate a saturation-free RGBW frame. In addition, the method includes processing the saturation-free RGBW frame to generate a final image of the scene.

An electronic device includes a UDC and a UDC controller configured to determine an optimal number of frames required to be captured for a scene to compensate at least one parameter to optimize an output media using the UDC, obtain a multi-frame fusion media by performing at least one multi-frame fusion on the determined optimal number of frames, perform a light source spread correction on the multi-frame fusion media, and optimize the output media based on the light source spread correction on the multi-frame fusion media.