Abstract: An image processing method is configured to split a deconvolution kernel according to a preset splitting mode to obtain a sub-convolution kernel. And then, determining an original sub-matrix corresponding to the sub-convolution kernel, according to parameters of the sub-convolution kernel and an image feature matrix, and performing a convolution operation on the original sub-matrix corresponding to the sub-convolution kernel by using the sub-convolution kernel to obtain a deconvolution sub-matrix corresponding to each sub-convolution kernel; determining a target feature matrix according to the deconvolution sub-matrix corresponding to the sub-convolution kernel.

Abstract: Disclosed are an image classification and conversion method, apparatus, image processor and training method thereof, and medium. The image classification method includes receiving a first input image and a second input image; performing image encoding on the first input image by utilizing n stages of encoding units connected in cascades to produce a first output image, wherein n is an integer greater than 1, and wherein as for 1?i<n, the output of the i-th stage of encoding unit is an input of an (i+1)-th stage of encoding unit, wherein m is an integer greater than 1; outputting a first output image, the first output image comprising mn output sub-images, and each of the mn output sub-images is corresponding to an image category.

Abstract: System/method identifying a defined object (e.g., hazard): a sensor detecting and defining a digital representation of an object; a processor (connected to the sensor) which executes two techniques to identify a signature of the defined object; a memory (connected to the processor) storing reference data relating to two signatures derived, respectively, by the two techniques; responsive to the processor receiving the digital representation from the sensor, the processor executes the two techniques, each technique assessing the digital representation to identify any signature candidate defined by the object, derive feature data from each identified signature candidate, compare the feature data to the reference data, and derive a likelihood value of the signature candidate corresponding with the respective signature; combining likelihood values to derive a composite likelihood value and thus determine whether the object in the digital representation is the defined object.

Abstract: A Convolution Multiply and Accumulate (CMAC) system for performing a convolution operation is disclosed. The CMAC system receives image data pertaining to an image. The image data comprises a set of feature matrix, a kernel size and depth information. Further, the CMAC system generates a convoluted data based on convolution operation for each feature matrix. The CMAC system performs an accumulation of the convoluted data to generate accumulated data, when the convolution operation for each feature matrix is performed. The CMAC system further performs an addition of a predefined value to the accumulated data to generate added data. Further, the CMAC system filters the added data to provide a convolution result for the image, thereby performing the convolution operation of the image.

Abstract: Depth perception has become of increased interest in the image community due to the increasing usage of deep neural networks for the generation of dense depth maps. The applications of depth perception estimation, however, may still be limited due to the needs of a large amount of dense ground-truth depth for training. It is contemplated that a self-supervised control strategy may be developed for estimating depth maps using color images and data provided by a sensor system (e.g., sparse LiDAR data). Such a self-supervised control strategy may leverage superpixels (i.e., group of pixels that share common characteristics, for instance, pixel intensity) as local planar regions to regularize surface normal derivatives from estimated depth together with the photometric loss. The control strategy may be operable to produce a dense depth map that does not require a dense ground-truth supervision.

Abstract: The present invention relates to a method for acquiring an object information, the method comprising: obtaining an input image acquired by capturing a sea; obtaining a noise level of the input image; when the noise level indicates a noise lower than a predetermined level, acquiring an object information related to an obstacle included in the input image from the input image by using a first artificial neural network, and when the noise level indicates a noise higher than the predetermined level, obtaining a noise-reduced image of which the environmental noise is reduced from the input image by using a second artificial neural network, and acquiring an object information related to an obstacle included in the sea from the noise-reduced image by using the first artificial neural network.

Abstract: The present disclosure relates to a color classification system that accurately classifies objects in digital images based on color. In particular, in one or more embodiments, the color classification system utilizes a multidimensional color space and one or more color mappings to match objects to colors. Indeed, the color classification system can accurately and efficiently detect the color of an object utilizing one or more color similarity regions generated in the multidimensional color space.

Abstract: An example apparatus for processing images includes a hybrid infinite impulse response-finite impulse response (IIR-FIR) convolution block to receive an image and generate processed image information. The hybrid IIR-FIR convolution block includes a vertical infinite impulse response (IIR) component to approximate a vertical convolution when processing the image.

Abstract: A method of performing tone mapping in a stream of images (Fr1 . . . N) includes, for each image (FrN) in the stream: sparsely reading image data values (IDN) corresponding to the image (FrN) to provide sparse image data from a plurality of sparsely distributed positions (Pos1 . . . k) in the image (FrN); generating, based on the sparse image data, tone mapping parameters of a tone mapping algorithm (TMA) for each position in the image (FrN); each position in the image (FrN) including the sparsely distributed positions (Pos1 . . . k) and a plurality of further positions (PosF1 . . . j) in the image (FrN); reading the image data values (IDN) corresponding to the image (FrN) to provide image data from each position in the image (FrN); and tone mapping the image by mapping the image data from each position in the image (FrN) to adjusted image data using the generated tone mapping parameters.

Abstract: A system for patient positioning is provided. The system may acquire image data relating to a patient holding a posture and a plurality of patient models. Each patient model may represent a reference patient holding a reference posture, and include at least one reference interest point of the referent patient and a reference representation of the reference posture. The system may also identify at least one interest point of the patient from the image data using an interest point detection model. The system may further determine a representation of the posture of the patient based on a comparison between the at least one interest point of the patient and the at least one reference interest point in each of the plurality of patient models.

Abstract: A non-local means method is insufficient in its noise reduction effect or edge retainability due to a perfect match between blocks in a case where a reference pixel matches a target pixel. Therefore, information on a target region and plural reference regions is obtained for the target pixel. Whether the target region matches any one of the reference regions is determined from the obtained information. Switching between weight derivation methods based on similarity between the target region and the reference region is performed according to a determined result.

Abstract: The present invention relates to a diagnosis assistance system for assisting diagnosis for a plurality of diseases based on a fundus image, the diagnosis assistance system including: a fundus image obtaining unit configured to obtain a fundus image; a first processing unit configured to, for the fundus image, obtain a first result related to a first finding of a patient using a first neural network model, a second processing unit configured to, for the fundus image, obtain a second result related to a second finding of the patient using a second neural network model, a third processing unit configured to determine, on the basis of the first result and the second result, diagnostic information on the patient, and a diagnostic information output unit configured to provide the determined diagnostic information to a user.

Abstract: In some examples, a computing device can define a marked area of an image of analog imagery captured by the computing device, separate the analog imagery of the image from a background of the image, and generate a small vector image that includes the analog imagery of the image.

Abstract: A device for interpolating a color includes at least one processor to implement: a directions interpolation candidate values calculator configured to calculate third horizontal/vertical directions interpolation candidate values with respect to a pixel in a red (R) channel or a blue (B) channel on a Bayer color filter array pattern, based on a local gradient similarity between the R channel and a green (G) channel or a local gradient similarity between the B channel and the G channel; a directions interpolation weights calculator configured to calculate third horizontal/vertical directions interpolation weights based on the first horizontal/vertical directions interpolation candidate values by using a local complexity; and a G value interpolation execution unit configured to interpolate a G value of the pixel in the R channel or the B channel based on the calculated third horizontal/vertical directions interpolation candidate values and the third calculated horizontal/vertical directions interpolation weights.

Abstract: The various implementations described herein include systems and methods for recognizing persons in video streams. In one aspect, a method includes: obtaining images collected by video cameras in a smart home environment, each image including a detected person; for each image, obtaining first information that identifies an attribute of the detected person, the first information generated from analysis of the image; grouping the images into a first group of a plurality of groups based on the first information, each group of the plurality of groups representing a unique person; receiving a request to remove a first image from the first group; removing the first image from the first group; and disassociating the first information from the first group.

Abstract: A method and apparatus for creating an adaptive mosaic pixel-wise virtual Bayer pattern. The method may include receiving a plurality of monochromatic images from an array of imaging elements, creating a reference ordered set at infinity from the plurality of monochromatic images, running a demosaicing process on the reference ordered set, and creating a color image from the demosaiced ordered set. One or more offset artifacts resulting from the demosaicing process may be computed at a distance other than infinity, the ordered set may be modified in accordance with the computed offsets.

Abstract: Embodiments of the present application provide a method, apparatus, and electronic device for eliminating distortion of a distorted image. Side information components of a distorted image are generated. The distorted image is resulted from image processing on an original image. Side information components represent distortion features of the distorted image with respect to original image. Distorted image color components of the distorted image and the side information components are input into a pre-established convolutional neural network model for convolution filtering to obtain distortion-eliminated image color components. The convolutional neural network model is obtained through training based on a preset training set. The training set comprises original sample images, distorted image color components of multiple distorted images corresponding to each of the original sample images, and side information components of each of the distorted images.

Abstract: An image processing apparatus includes a correction unit configured to correct first image data acquired via an image pickup optical system and to generate second image data using a filter generated based on a characteristic of the image pickup optical system, a decomposition unit configured to decompose each of the first image data and the second image data into a first frequency component and a second frequency component, a combination unit configured to combine the first frequency component of the first image data and the first frequency component of the second image data with each other, and a generation unit configured to generate third image data based on a frequency component including the first frequency component combined by the combination unit and the second frequency component of the second image data.

Abstract: The present disclosure relates to imaging processing devices, aerial refueling aircraft, and methods relating to the processing of images. An example imaging processing device includes a programmable circuit, such as a field-programmable gate array (FPGA), that is reprogrammed based on selected circuit data so as to construct a circuit configured to provide image processing on at least one image. The image processing includes receiving the at least one image. The image processing also includes adjusting the at least one image, to provide at least one adjusted image. Adjusting the at least one image includes applying: a local adaptive histogram equalization filter, a global gamma correction filter, and a local contrast filter.

Abstract: The disclosure describes various embodiments of validating data synchronization between an active sensor and a passive sensor. According to an exemplary method of validating sensor synchronization between an active sensor and a passive sensor, a synchronization device receives a first signal from the active sensor, the first signal indicating that the active sensor has transmitted laser points to a measure board. In response to the first signal, the synchronization device transmits a second signal to the passive sensor to trigger the passive sensor to capture an image of the measure board. A synchronization validation application can perform an analysis of the image of the measure board in view of timing of the first signal and second signal to determine whether the passive sensor and the active sensor are synchronized with each other.