Abstract: A signal processing device includes an approximate curved surface conversion unit that includes a first stacked autoencoder pretrained on the basis of learning input data constituted by coordinate data acquired for each of multiple elements of an object, and that obtains approximate curved surface data indicating an approximate curved surface of the object in an intermediate layer of the first stacked autoencoder, on the basis of input data constituted by the coordinate data acquired for each of the elements, and a geometric modulation processing unit that includes a second stacked autoencoder having learned by machine learning on the basis of learning input data constituted by the approximate curved surface data and on the basis of training data constituted by a result obtained by coordinate conversion for each of the elements in a geometric modulation process performed for the object, and performs the geometric modulation process.

Abstract: The present disclosure relates to systems and methods for image processing. The methods may include obtaining, by a first processor, a first image and a second image of a target region. The methods may further include generating, by the first processor, a fused image based on the first image and the second image. The methods may further include identifying, by a second processor, a region of interest (ROI) associated with a target object in the first image. And the method may also include generating, by the second processor, a target image based at least in part on information associated with the ROI in the first image and the fused image.

Abstract: An optical system (100), sequentially comprising from an object side to an image side: a first lens (L1) having positive refractive power, an object-side surface (S1) of the first lens (L1) being a convex surface at the circumference; a second lens (L2), a third lens (13), a fourth lens (L4), a fifth lens (L5), a sixth lens (L6), and a seventh lens (L7) having refractive power; and an eighth lens (L8) having negative refractive power. An image-side surface (S14) of the seventh lens (L7) is a concave surface at the optical axis. In addition, the optical system (100) satisfies 1<TTL/<2.5, wherein TTL is the distance between the object-side surface (S1) of the first lens (L1) and an imaging surface (S19) of the optical system (100) on the optical axis. The optical system (100) further comprises a diaphragm (STO), and L is the effective aperture diameter of the diaphragm (STO).

Abstract: An electronic device having a multi-camera, according to various embodiments of the present disclosure, includes: the multi-camera, a display, a memory, and a processor operatively connected to the camera, the display, and the memory. The processor may be configured to receive a first image being photographed at a first angle of view of the camera, receive a second image being photographed at a second angle of view of the camera, identify a subject in the first image according to predetermined criteria, generate a third image in which the identified subject is cropped according to a predetermined area of interest, and display the second image and the third image on at least a portion of an area in which the first image is displayed. Various other embodiments may be possible.

Abstract: An image capturing apparatus that is capable of accurately acquiring motion vectors according to a photographing environment and performing blur correction with high accuracy. The image capturing apparatus includes an image sensor, and a photometry unit that performs photometry of a photographing environment. A motion vector calculation section calculates motion vectors based on images acquired by the image sensor. A camera system controller calculates a reliability of the motion vectors. A photographing condition determination section determines photographing conditions for consecutively photographing a plurality of images by the image sensor, according to a photometry result and the calculated reliability.

Abstract: Solid-state imaging devices are disclosed. In one example, a solid-state imaging device includes a conversion circuit connected to a vertical signal line of a pixel array, a voltage generation circuit that outputs a predetermined voltage, and a reference voltage generation circuit that receives the predetermined voltage and outputs a reference voltage. The reference voltage generation circuit includes an operational amplifier that amplifies the predetermined voltage and outputs the reference voltage, a capacitive element having one end connected to an input of the operational amplifier that is different from an input that receives the predetermined voltage, a first switching circuit that connects the other end of the capacitive element to either the predetermined voltage output from the voltage generation circuit or a feedback loop of the operational amplifier, and a second switching circuit that selectively connects the one end of the capacitive element to the feedback loop of the operational amplifier.

Abstract: The present application discloses an anti-shake method, an anti-shake apparatus, and an electronic device. The method includes: acquiring, in a case that a camera of an electronic device captures a first picture in real time, a shaking parameter of the electronic device; and cropping a first region in the first picture according to a first cropping parameter corresponding to the shaking parameter, and displaying the cropped first picture, where the first picture includes the first region and a second region, the second region is a common region of the first picture and N frames of pictures, the N frames of pictures are pictures captured before the first picture is captured, and N is an integer greater than or equal to 1.

Abstract: The lens driving device includes: an AF movable part; an AF fixing part disposed spaced apart from the autofocus movable part; an AF driving section that moves the AF movable part in an optical-axis direction with respect to the AF fixing part; an OIS movable part that includes the AF movable part, the AF fixing part and the AF driving section; an OIS fixing part disposed spaced apart from the OIS movable part; and an OIS driving section that sways the OIS movable part in a plane orthogonal to the optical-axis direction with respect to the OIS fixing part. The AF movable part includes a first position detection magnet and the OIS fixing part includes a hall element provided facing the first position detection magnet in the optical-axis direction.

Abstract: Provided are an imaging device which can simultaneously capture images in different wavelength ranges and can improve a focusing accuracy of each image, an imaging optical system, and an imaging method.

Abstract: This disclosure provides systems, methods, and devices for image processing that supports high dynamic range (HDR) photography. In some aspects, a method of generating a full-resolution HDR photograph with in-sensor zoom includes receiving first and second image data corresponding to first and second exposure captures of a scene. First and second full-resolution image frames may be generated from the first and second image data, which are subsequently processed with HDR fusion to obtain an output image frame with higher dynamic range than either the first or second image data. The first full-resolution image frame may be determined from both the first and second image data by compensating the second image data for differences between the first and second exposures. Other aspects and features are also claimed and described.

Abstract: A target detection method based on fusion of vision, lidar and millimeter wave radar comprises: obtaining original data detected by a camera, a millimeter wave radar, and a lidar, and synchronizing the millimeter wave radar, the lidar, and the camera in time and space; performing a calculation on the original data detected by the millimeter wave radar according to a radar protocol; generating a region of interest by using a position, a speed, and a radar reflection area obtained from the calculation; extracting feature maps of a point cloud bird's-eye view and the original data detected by the camera; projecting the region of interest onto the feature maps of the point cloud bird's-eye view and the original data detected by the camera; fusing the feature maps of the point cloud bird's-eye view and the original data detected by the camera, and processing a fused image through a fully connected layer.

Abstract: A method of reduce the impact of noise on a depth image produced using a Time Of Flight (TOF) camera uses an infrared image produced from one or more phase-specific images captured by the TOF camera to determine whether to move pixels in the depth image from one phase section to another.

Abstract: The present embodiment relates to a camera module comprising a front body, a lens, a rear body, a first substrate, an image sensor, a second substrate, a connector and a cover, wherein the cover includes a bottom plate having a hole in which the connector is to be disposed, side plates extending from the bottom plate, and pressing unit disposed at the bottom plate and elastically supporting the connector, the connector includes a first surface facing the inner surface of the bottom plate of the cover, and a second surface extending from the first surface and disposed in the hole, and the pressing unit includes a first pressing part for pressing the first surface of the connector, and a second pressing part for pressing the second surface of the connector.

Abstract: For example, in order to enable an RCCB sensor or a specific optical system to perform an appropriate image correction process (distortion correction and the like), an imaging device includes an imaging element, an optical system configured to form an image on an imaging surface of the imaging element and has a characteristic in which an image formation magnification differs depending on a position in the imaging surface, a demosaic unit configured to generate color image data of at least two colors from the data output from the imaging element, and a distortion correction unit configured to correct distortion of the color image data of at least two colors generated by the demosaic unit.

Abstract: An image processing device is provided. The image processing devices includes an input part configured to input an input image; a cutout part configured to cut out a plurality of image regions from the input image input by the input part; and a luminance change part configured to execute luminance change of each of the image regions cut out by the cutout part.

Abstract: The present invention relates to a multi-band optical filtering method and apparatus and to a multi-band optical filtering method and apparatus capable of filtering wavelengths of two or more bands in order to create a multi-wavelength image of a subject. In the present invention, the optical filtering apparatus for creating a multi-wavelength image of a subject comprises a filter unit having a plurality of sub filter units comprising a first sub filter unit through which a first wavelength band passes and a second sub filter unit through which a second wavelength band, which is different from the first wavelength band, passes, wherein while the light generated in a light source passes through the filter unit, the filter unit filters the light such that an intensity of the first wavelength band is dominant in a first region, and an intensity of the second wavelength band is dominant in a second region.

Abstract: An image acquisition method, a camera assembly, and a mobile terminal are provided. The image acquisition method includes: acquiring a first color original image and a second color original image by exposing the pixel array, each piece of first color original image data in the first color original image being generated by at least one color photosensitive pixel in a sub-unit, and each piece of second color original image data in the second color original image being generated by at least one transparent photosensitive pixel and at least one color photosensitive pixel in the sub-unit; and fusing the first color original image and the second color original image to acquire a target image.

Abstract: An imaging device according to the embodiments of the present disclosure has a display including a wiring layer; a camera located at a back side of the display, the camera including an optical lens and an imaging sensor to sense the light through the display to create an image; an optical element between the display and the camera, wherein the optical element filters the light through the display and passes the filtered light to the camera, and the optical element reduces a diffraction due to the wiring layer.

Abstract: An image processing apparatus comprises a first processor that processes an image signal output from an image sensor; a second processor, connected in downstream of the first processor, that processes an image signal transferred from the first processor; and a controller that selects any of the first processor and the second processor to be used to perform a predetermined process on the image signal output from the image sensor based on a predetermined condition. The controller controls to stop an operation of the second processor in a case where the controller selects the first processor, the predetermined condition includes an instruction for live view display, and the controller selects the first processor in a case where the live view display is instructed.

Abstract: Examples are described for applying different settings for image capture to different portions of image data. For example, an image sensor can capture image data of a scene and can send the image data to an image signal processor (ISP) and a classification engine for processing. The classification engine can determine that a first object image region depicts a first category of object, and a second object image region depicts a second category of object. Different confidence regions of the image data can identify different degrees of confidence in the classifications. The ISP can generate an image by applying a different settings to the different portions of the image data. The different portions of the image data can be identified based on the object image regions and confidence regions.