Techniques describe computing computer vision (CV) features based on sensor readings from a sensor and detecting macro-features based on the CV features. The sensor may include a sensor element array that includes a plurality of sensor elements. The sensor may also include in-pixel circuitry coupled to the sensor elements, peripheral circuitry and/or a dedicated microprocessor coupled to the sensor element array. The in-pixel circuitry, the peripheral circuitry or the dedicated microprocessor may include computation structures configured to perform analog or digital operations representative of a multi-pixel computation for a sensor element (or block of sensor elements), based on sensor readings generated by neighboring sensor elements in proximity to the sensor element, and to generate CV features. The dedicated microprocessor may process the CV features and detect macro-features. Furthermore, in certain embodiments, the dedicated microprocessor may be coupled to a second microprocessor through a wired or wireless interface.

An image processing device comprises an input unit, a characteristic amount calculation unit, a characteristic amount vector calculation unit, and a characteristic identification unit. The input unit receives an image. The characteristic amount calculation unit calculates an image characteristic amount characterizing a texture of a local area of the image received by the input unit. The characteristic amount vector calculation unit calculates a first characteristic amount vector corresponding to the local area from the image characteristic amount. The characteristic identification unit identifies a characteristic of the local area on the basis of the first characteristic amount vector and a second characteristic amount vector calculated by the same method as the first characteristic amount vector and calculated from an image whose characteristic has been determined in advance.

Embodiments of the present disclosure provide an image processing method and apparatus. The method includes detecting a human face region in each frame of an image in a to-be-processed video; locating a lip region in the human face region; extracting feature column pixels in the lip region from each frame of the image; building a lip change graph based on the feature column pixels; and recognizing a lip movement according to a pattern feature of the lip change graph.

Systems and methods suitable for capable of autonomous crack detection in surfaces by analyzing video of the surface. The systems and methods include the capability to produce a video of the surfaces, the capability to analyze individual frames of the video to obtain surface texture feature data for areas of the surfaces depicted in each of the individual frames, the capability to analyze the surface texture feature data to detect surface texture features in the areas of the surfaces depicted in each of the individual frames, the capability of tracking the motion of the detected surface texture features in the individual frames to produce tracking data, and the capability of using the tracking data to filter non-crack surface texture features from the detected surface texture features in the individual frames.

Various embodiments provide an apparatus, a method, and a computer program product. 1. An apparatus incudes at least one processor; and at least one non-transitory memory includes computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to: perform an overfitting operation, at an encoder side, to obtain an overfitted probability model, wherein overfitting comprises one or more training operations applied to a probability model, wherein one or more parameters of the probability model are trained; use the overfitted probability model to provide probability estimates to a lossless codec or a substantially lossless codec for encoding data or a portion of the data; and signal information to a decoder on whether to perform the overfitting operation at the decoder side.

A control method for a robot cleaner includes acquiring a plurality of images of surroundings during travel of the robot cleaner in a cleaning area, estimating a plurality of room-specific feature distributions according to a rule defined for each of a plurality of rooms, based on the images acquired while acquiring the plurality of images, acquiring an image of surroundings at a current position of the robot cleaner, obtaining a comparison reference group including a plurality of room feature distributions by applying the rule for each of the plurality of rooms to the image acquired while acquiring the image at the current position, comparing the obtained comparison reference group with the estimated room-specific feature distributions, and determining a room from the plurality of rooms having the robot cleaner currently located therein.

The present invention provides a method and a device for detecting interest points in an image. The method includes: acquiring an original input image; performing down-sampling processing on the original input image, so as to obtain a plurality of sampling images with different resolutions; dividing each sampling image into a plurality of small image blocks; performing filtering processing on the plurality of small image blocks in each sampling image in sequence by using Laplacian-of-Gaussian filters, so as to obtain filtered images of the plurality of small image blocks in each sampling image; and acquiring interest points in an image in filtered images of the plurality of small image blocks in each sampling image. The present invention is used for solving the problems of more memory consumption and a low detection speed in the prior art.

Techniques for direct local binary pattern (LBP) generation are presented. An image sensor for LBP generation includes a variable reference signal generator and a sensor pixel array that can generate events based on optical signals on the sensor pixel array and a reference level from the variable reference signal generator. The image sensor also includes an address encoder that can encode the addresses of the sensor pixels that generate events, and a binary image generator that can create a binary image based on the addresses of the sensor pixels that generate the events at the reference level. The image sensor may also include a local binary pattern generator configured to determine local binary pattern labels for image pixels whose binary value changes from a first binary image at a first reference level to a subsequent second binary image at a next reference level.

An improved system and method for digital image classification is provided. A host computer having a processor is coupled to a memory storing thereon reference feature data. A graphics processing unit (GPU) having a processor is coupled to the host computer and is configured to obtain, from the host computer, feature data corresponding to the digital image; to access, from the memory, the one or more reference feature data; and to determine a semi-metric distance based on a Poisson-Binomial distribution between the feature data and the one or more reference feature data. The host computer is configured to classify the digital image using the determined semimetric distance.

The present disclosure relates to a method and apparatus for searching an image, and to a computer-readable recording medium for executing the method. The apparatus for searching an image of the present disclosure obtains features of an input image; and obtains words that correspond to the features respectively and an adjacent word that is adjacent to the words corresponding to the features. When a word is assigned to a first word cell of a plurality of word cells that are included in a visual feature space, an adjacent word is assigned to at least one second word cell that is adjacent to the first word cell, where the plurality of word cells is assigned to different words, and at least one word being within a predetermined distance from a word is designated as the adjacent word. The apparatus is further configured to search for an image that is identical or similar to the input image based on information associated with a first group of images corresponding to the word and information associated with a second group of images corresponding to the adjacent word, the information on the first and second groups of images being stored in a database.