Abstract: The present disclosure relates to an artificial intelligence (AI) system that utilizes a machine learning algorithm, and applications therefore. Disclosed is an electronic device. The electronic device comprises: a storage unit which stores therein an artificial intelligence model trained to determine parameters for a plurality of filters used for image processing on the basis of a deep neural network (DNN); and a processor for determining, through the artificial intelligence mode, parameters for each of the plurality of filters used for image processing for an input image, and performing, through the plurality of filters, filtering of the input image on the basis of the determined parameters so as to perform image processing for the input image.

Abstract: Video coding schemes may include one or more filters to reduce coding artifacts and improve video quality. These filters may be applied to decode video data in a predetermined sequence. The output from one or more of these filters may be selected for different images, blocks, or sets of video data and then copied and/or routed to a display or a buffer storing reference data that is used to decode other video data in a data stream. Providing the ability to select which filter output is used for display and as a reference may result in better video quality for multiple types of video data. The filters that are selected for display and for reference may be different and may vary for different images, blocks, and data sets.

Abstract: A method related to adaptive usage of pixel-based and block-based affine motion compensation and includes performing sub-block-based affine transform prediction on an affine block with a first sub-block size if the first sub-block size is greater than or equal to a first sub-block size threshold. If the first sub-block size is less than the first sub-block size threshold, it is determined whether a pixel-based motion vector field is not applied for performing motion compensation for the affine block. If the motion vector field is not applied, a sub-block-based affine motion prediction is performed with a second sub-block size that is based on the first sub-block size. If the pixel-based motion vector field is applied, motion compensation is performed for a sub-block of the affine block using the pixel-based motion vector field.

Abstract: An image adjustment device includes: an illumination component derivation unit that derives an illumination component of a grayscale image; a reflectance component derivation unit that derives a reflectance component image that is a resulting image in which the illumination component is removed from the grayscale image; a contrast component derivation unit that derives a contrast component based on a contrast value between a pixel of the reflectance component image and a peripheral area of the pixel; a histogram derivation unit that derives a luminance histogram of the grayscale image weighted according to the contrast value for each pixel of the contrast component; a conversion function derivation unit that derives a luminance conversion function for converting a luminance such that a luminance histogram of a converted grayscale image in which the grayscale image is converted by the luminance conversion function and a predetermined histogram are matched with or similar to each other; and a luminance conversi

Abstract: An encoder includes circuitry and memory connected to the circuitry. The circuitry, in operation: derives, as a first parameter, a total sum of absolute values of sums of horizontal gradient values respectively for pairs of relative pixel positions; derives, as a second parameter, a total sum of absolute values of sums of vertical gradient values respectively for the pairs of relative pixel positions; derives, as a third parameter, a total sum of horizontal-related pixel difference values respectively for the pairs of relative pixel positions; derives, as a fourth parameter, a total sum of vertical-related pixel difference values respectively for the pairs of relative pixel positions; derives, as a fifth parameter, a total sum of vertical-related sums of horizontal gradient values respectively for the pairs of relative pixel positions; and generates a prediction image to be used to encode the current block using the first, second, third, fourth, and fifth parameters.

Abstract: An encoder includes circuitry and memory connected to the circuitry. The circuitry, in operation: derives, as a first parameter, a total sum of absolute values of sums of horizontal gradient values respectively for pairs of relative pixel positions; derives, as a second parameter, a total sum of absolute values of sums of vertical gradient values respectively for the pairs of relative pixel positions; derives, as a third parameter, a total sum of horizontal-related pixel difference values respectively for the pairs of relative pixel positions; derives, as a fourth parameter, a total sum of vertical-related pixel difference values respectively for the pairs of relative pixel positions; derives, as a fifth parameter, a total sum of vertical-related sums of horizontal gradient values respectively for the pairs of relative pixel positions; and generates a prediction image to be used to encode the current block using the first, second, third, fourth, and fifth parameters.

Abstract: Video coding schemes may include one or more filters to reduce coding artifacts and improve video quality. These filters may be applied to decode video data in a predetermined sequence. The output from one or more of these filters may be selected for different images, blocks, or sets of video data and then copied and/or routed to a display or a buffer storing reference data that is used to decode other video data in a data stream. Providing the ability to select which filter output is used for display and as a reference may result in better video quality for multiple types of video data. The filters that are selected for display and for reference may be different and may vary for different images, blocks, and data sets.

Abstract: In a data driven object recognition system and object recognition method, a connection relationship between an object feature extraction unit and a plurality of task-specific identification units is stored in a connection switch according to a type of task. The connection relationship is changed based on the connection information to suppress the amount of labeling in constructing a learning data set.

Abstract: Methods, apparatuses and systems directed to pattern learning, recognition, and metrology. In some particular implementations, the invention provides a flexible pattern recognition platform including pattern recognition engines that can be dynamically adjusted to implement specific pattern recognition configurations for individual pattern recognition applications. In certain implementations, the present invention provides for methods and systems suitable for analyzing and recognizing patterns in biological signals such as multi-electrode array waveform data. In other implementations, the present invention also provides for a partition configuration where knowledge elements can be grouped and pattern recognition operations can be individually configured and arranged to allow for multi-level pattern recognition schemes. In other implementations, the present invention provides methods and systems for dynamic learning of patterns in supervised and unsupervised manners.

Abstract: A method of determining a longitudinal position of a vehicle (100) relative to a digital map is disclosed in which real time scan data (200, 202) is determined by scanning a lateral environment around the vehicle using at least one range-finder sensor, said real time scan data comprising one or more depth maps, each depth map representing the measured lateral distance to surfaces in the lateral environment for a plurality of longitudinal positions and elevations. Localization reference data associated with the digital map for a deemed current longitudinal position of the vehicle (100) in relation to the digital map is retrieved, and compared to the real time scan data (200, 202) by calculating a cross-correlation to determine a longitudinal offset. The deemed current longitudinal position is adjusted based on said longitudinal offset to determine the longitudinal position of the vehicle (100) relative to the digital map.

Abstract: Image enhancement is achieved by separating image signals, e.g. YCbCr image signals, into a series of frequency bands and performing locally-adaptive noise reduction on bands below a given frequency but not on bands above that frequency. The bands are summed to develop the image enhanced signals. The YCbCr, multi-band locally-adaptive approach to denoising is able to operate independently—and in an optimized fashion—on both luma and chroma channels. Noise reduction is done based on models developed for both luma and chroma channels by measurements taken for multiple frequency bands, in multiple patches on the ColorChecker chart, and at multiple gain levels, in order to develop a simple yet robust set of models that may be tuned off-line a single time for each camera and then applied to images taken by such cameras in real-time without excessive processing requirements and with satisfactory results across illuminant types and lighting conditions.

Abstract: Image enhancement is achieved by separating image signals, e.g. YCbCr image signals, into a series of frequency bands and performing noise reduction on bands below a given frequency but not on bands above that frequency. The bands are summed to develop the image enhanced signals. The YCbCr, multi-band approach to denoising is able to operate independently—and in an optimized fashion—on both luma and chroma channels. Noise reduction is done based on models developed for both luma and chroma channels by measurements taken for multiple frequency bands, in multiple patches on the ColorChecker chart, and at multiple gain levels, in order to develop a simple yet robust set of models that may be tuned off-line a single time for each camera and then applied to images taken by such cameras in real-time without excessive processing requirements and with satisfactory results across illuminant types and lighting conditions.