231 results about "Pixel correlation" patented technology

Apparatus and method for object pose estimation are disclosed. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to receive a plurality of sets of echo data, wherein the plurality of sets of echo data is configured for generation of a plurality of echo depth maps, segment the plurality of echo depth maps, determine a depth datum related to pixels of an object of interest as a function of the plurality of segmented echo depth maps, generate a three dimensional (3D) point cloud related to the object of interest as a function of the depth datum and generate a pose datum of the object of interest as a function of the 3D point cloud.

A vehicle external environment recognition apparatus includes at least one processor, and at least one memory coupled to the at least one processor. The at least one processor is configured to operate in cooperation with at least one program stored in the at least one memory to execute processing. The processing includes generating a distance image from luminance images, specifying, by using semantic segmentation, a floating matter class in the luminance images, and invalidating parallax associated with floating pixels that are included in the distance image and belong to the floating matter class.

The invention relates to the technical field of image processing, and discloses an optical image noise reduction method and system of a composite imaging assembly. The method comprises the following steps: carrying out geometric correction on visible light, infrared and laser sensor data through a multi-sensor time synchronization mechanism to obtain a noise coupling matrix; generating annular and checkerboard type mask modes based on the noise coupling matrix; performing cross-band feature interaction through the conditional mask convolution block to obtain a multi-scale dense connection feature map; a double-blind-spot self-supervised learning algorithm is adopted to optimize cross-band coordination loss, and a noise reduction prediction result is obtained; and finally, edge protection processing is carried out through a block-based Wiener filter, and a final noise reduction image is obtained. The problem of noise reduction failure caused by multi-sensor noise coupling and pixel strong correlation in the composite imaging assembly is solved, and the imaging quality and target recognition precision of the composite imaging assembly in a complex environment are improved.

In accordance with some embodiments, systems, methods and media for single-photon imaging with improved energy efficiency are provided. In some embodiments, the system comprises: an image sensor comprising pixels comprising detectors in an array, configured to: generate image data representing a scene, and comprising pixel values based on a signal generated by the respective detector during a first period of time; and a processor configured to: determine, for each pixel, an inhibition value based on the pixel value; determine, based on the inhibition value, that a pixel is to be inhibited during a second period of time; inhibit the pixel such that a pixel value associated with the pixel in second image data is consistent with the pixel being inhibited during a second period of time.

The invention provides a super-resolution binocular image generation method and system based on geometric structure consistency, and the method comprises the steps: extracting the deep features of a low-resolution binocular image through employing a convolutional neural network or a Transform model, achieving the information interaction of a left image and a right image in combination with a cross attention module, and constructing a pixel incidence matrix of the left image and the right image; acquiring a pixel corresponding relation of the left image and the right image by using the pixel incidence matrix, and constructing a continuous parallax field; performing spatial warping on the deep features based on a continuous parallax field to obtain warping features, and aligning the deep features of the left and right images; and merging the deep features and the warping features after spatial alignment, inputting the merged features into a feature up-sampling module based on implicit two-dimensional expression, and outputting a high-resolution binocular image of the same scene. The invention provides a binocular image super-resolution technology comprising binocular image feature extraction, continuous parallax field construction based on implicit two-dimensional expression, left and right image feature space alignment and feature upsampling based on implicit two-dimensional expression.

Systems and methods are provided for vehicle navigation. In one implementation, at least one processing device may receive, from a camera of the host vehicle, at least one captured image representative of an environment of the host vehicle. The processing device may analyze one or more pixels of the at least one captured image to determine whether the one or more pixels represent at least a portion of a target vehicle. For pixels determined to represent at least a portion of the target vehicle, the processing device may determine one or more estimated distance values from the one or more pixels to at least one edge of a face of the target vehicle; and generate, based on the analysis of the one or more pixels, including the determined one or more distance values associated with the one or more pixels, at least a portion of a boundary relative to the target vehicle.

An event filter for an event based imaging sensor is provided by the present disclosure, the event filter comprising: input circuitry configured to receive an indication of a pixel position associated with a current event detected by the event based imaging sensor; event potential determining circuitry configured to determine an event potential associated with the current event; and filtering circuitry configured to determine whether to pass the current event based on the event potential; wherein the event potential determining circuitry is configured to determine the event potential for the current event based on combining contributions associated with pixels in a local region of pixels around the pixel position of the current event, where a given contribution associated with a given pixel in the local region is dependent on a time decay factor which causes the given contribution to decrease with increasing time difference between a time of detection of a previous event for the given pixel and a time of detection of the current event. A method of filtering and a computer program are also provided.

A macropixel is disclosed. The macropixel comprises a plurality of pixels, each pixel comprising a Single Photon Avalanche Diode (SPAD). The macropixel also comprises a memory configured to store: a plurality of counts, each count associated with a pixel of the plurality of pixels; and a plurality of saturation bits, each saturation bit associated with a count of the plurality of counts. The macropixel also comprises saturation detection circuitry configured to gate a recharge of each SPAD based on a state of the respective saturation bit.

In various examples, epipolar constraint-based cross-camera calibration validation is disclosed. For a pair of cameras that have partially overlapping fields of view, a shared region of their overlapping fields of view may be extracted and used as the basis to perform an epipolar constraint-guided feature descriptor matching process. A camera calibration metric may be computed based on the degree to which a feature descriptor appearing at a pixel of the first image aligns as expected in the second image with an epipolar line associated with the pixel of the first image, where the epipolar line is computed using extrinsic camera calibration parameters associated with the pair of cameras. Epipolar matching may be performed for a plurality of feature points and an aggregate validation score computed based on measuring the computed deviations for each feature. A sensitivity analysis may be applied to better assess the usefulness of the validation score.

The present disclosure provides methods and systems for fusing chroma intra prediction modes. An exemplary method includes: generating a plurality of predicted chroma samples associated with a pixel, by using a plurality of chroma intra prediction modes respectively; and determining a first predicted chroma sample, based on a weighted sum of the plurality of predicted chroma samples.

A method of training a machine learning model to identify image features including providing training image data including pixels, assigning a groundtruth annotation to each pixel relating to a respective pixel and each groundtruth annotation indicating whether or not that the pixel corresponds with an image feature, providing an ignore mask including a set of ignore flags relating to a respective pixel and each ignore flag providing an indication that the pixel should be ignored, for each pixel, receiving a prediction value from the machine learning model indicating a probability of the pixel corresponding with an image feature, for each pixel which has no ignore flag, determining a loss value based on the prediction value and groundtruth annotation for that pixel, and training the machine learning model based on the loss value, and for each pixel having an ignore flag, ignoring the prediction value for that pixel.

Semantic segmentation generally refers to a machine learning process that associates a label or category with every pixel in an image. This can be used to recognize a collection of pixels that form distinct categories of objects, which may have applications in autonomous driving for example where the vehicle needs to identify other vehicles, pedestrians, traffic signs, pavement, and other road features from captured images of a surrounding environment. While using pixel-level annotations may be ideal for fully-supervised training of the semantic segmentation model, collecting such annotations is time-consuming and expensive, and therefore limits the scalability and practicality of fully-supervised training methods. The present disclosure enables weakly supervised training of a semantic segmentation model aided by learned prompts embedded with semantic knowledge.

A method of computer-implemented synthesized view image generation and a synthesized view image generation system provide layered view synthesis. The method includes receiving an input image having a plurality of pixels having color values; generating a dilated depth map by dilating a depth map associated with the input image, the depth map with depth values respectively associated with each pixel in the input image; determining an inpainting mask using the dilated depth map; performing an inpainting operation based on the inpainting mask and the input image to generate a background image; and rendering a synthesized view image using the background image, the input image, and the dilated depth map.

Systems, methods, and software are disclosed herein that improve computer vision technology in general, and 4D scene reconstruction in particular. An artificial intelligence (Al) image processing system employs multiple dynamic neural radiance fields (NeRFs) to render two-dimensional (2D) images of a four-dimensional (4D) scene from different viewpoints and different instances of time. The Al image processing system collects viewing parameters for rendering a two-dimensional (2D) image of the 4D scene, such as from a desired viewing direction and at a desired instance of time. The system then executes the multiple dynamic NeRFs to obtain, based on the viewing parameters, color and volume density values for voxels associated with pixels in the 2D image. The system then renders the 2D image based on a combination of the color and the volume density values obtained from the multiple dynamic NeRFs.

Techniques for identifying lidar points associated with static objects, and using such lidar points to annotate objects within two-dimensional images are discussed herein. In some examples, an object manager may receive accumulations of lidar data captured from lidar devices of a vehicle while traversing within a driving environment. In some examples, the object manager may receive a plurality of annotated images. Such annotations may identify static objects within the driving environment. In some instances, the object manager may project a lidar point into an annotated image and determine that the lidar point is associated with an annotated pixel. Based on the pixel being associated with the annotated object, the object manager may determine that the lidar point is associated with object. In some examples, the object manager may determine a subset of lidar points that are associated with the object.

The present application relates to image processors and methods for processing images. A method of computing a warp result is disclosed that can include performing, for each target pixel in a set of target pixels, a warp computation process that includes receiving, by a first set of processing units in an array of processing units, a first weight and a second weight associated with the target pixel; receiving, by a second set of processing units in the array, values of neighboring source pixels associated with the target pixel; computing, by the second set, a warp result responsive to the values of the neighboring source pixels and the pair of weights; and providing the warp result to a memory module.

A robotic cleaning system may include a robotic cleaner configured to generate a map of an environment and a mobile device configured to communicatively couple to the robotic cleaner, the robotic cleaner configured to communicate the map to the mobile device. The mobile device may include a camera configured to generate an image of the environment, the image comprising a plurality of pixels, a display configured to display the image and to receive a user input while displaying the image, the user input being associated with one or more of the plurality of pixels, a depth sensor configured to generate depth data that is associated with each pixel of the image, an orientation sensor configured to generate orientation data that is associated with each pixel of the image, and a mobile controller configured to localize the mobile device within the map using the depth data and the orientation data.

The invention relates to a method (50) comprising the steps of: - using a sensor to acquire (110) an image of the sample composed of grains; - applying (120), to the image (1), a convolutional neural network in order to obtain a contour map (C) associating, with each pixel of the image, a value equal to one unit when that pixel belongs to a contour of a grain and otherwise equal to zero; - applying (130), to the contour map (C), a segmentation algorithm in order to obtain a segmented image (S) comprising a plurality of regions, one region being separated from a neighbouring region by a contour having a thickness of a single pixel; and - applying (140), to the segmented image (S), one or more geometric processing operations in order to calculate physical quantities for each grain so as to characterise the lithology of the sample (3).

Systems, methods, and software are disclosed herein that improve computer vision technology in general, and 4D scene reconstruction in particular. An artificial intelligence (AI) image processing system employs multiple dynamic neural radiance fields (NeRFs) to render two-dimensional (2D) images of a four-dimensional (4D) scene from different viewpoints and different instances of time. The AI image processing system collects viewing parameters for rendering a two-dimensional (2D) image of the 4D scene, such as from a desired viewing direction and at a desired instance of time. The system then executes the multiple dynamic NeRFs to obtain, based on the viewing parameters, color and volume density values for voxels associated with pixels in the 2D image. The system then renders the 2D image based on a combination of the color and the volume density values obtained from the multiple dynamic NeRFs.

A system for detecting one or more target materials in an un-calibrated multi-spectral data cube comprising a collection of pixels, the system comprising a processing circuitry configured to: obtain: (A) a machine learning model capable of receiving the un-calibrated multi-spectral data cube and determining for at least one pixel of the pixels at least one material indicator, indicative of existence of a given target material of the target materials at the location of the pixel, wherein the machine learning model is trained utilizing a labeled training-data set comprising of a plurality of training records, each training record comprising: (i) a training un-calibrated multi-spectral data cube, and (ii) at least one training material indicator associated with at least one pixel of the training un-calibrated multi-spectral data cube, indicative of existence of the target material at the location of the pixel, and (B) the un-calibrated multi-spectral data cube; and determine for at least one pixel of the pixels of the un-calibrated multi-spectral data cube, at least one material indicator, and a corresponding calibrated multi-spectral data cube, wherein the corresponding calibrated multi-spectral data cube is calculated by utilizing a calibration process and an atmospheric simulator that simulates a plurality of simulated un-calibrated multi-spectral data cubes by simulation of different atmospheric conditions over the calibrated multi-spectral cube.

A computer-implemented method includes encoding a radiance field of an object onto a machine learning model; conducting, based on a set of training images of the object, a training process on the machine learning model to obtain a trained machine learning model, wherein the training process includes a first training process using a plurality of first test sample points followed by a second training process using a plurality of second test sample points located within a threshold distance from a surface region of the object; obtaining target view parameters indicating a view direction of the object; obtaining a plurality of rays associated with a target image of the object; obtaining render sample points on the plurality of rays associated with the target image; and rendering, by inputting the render sample points to the trained machine learning model, colors associated with the pixels of the target image.

A system for detecting one or more target materials in an uncalibrated multispectral data cube comprising a collection of pixels, comprising: (A) a machine learning model capable of receiving the uncalibrated multispectral data cube and determining, for at least one of the pixels, at least one material indicator indicative of the presence of a given one of the target materials at the pixel location, the machine learning model being trained using a labeled training data set comprising a plurality of training records, each training record comprising: (i) the training uncalibrated multispectral data cube; and (ii) a target material indicator associated with at least one pixel of the training uncalibrated multispectral data cube at the pixel location. and (B) an uncalibrated multispectral data cube; and determining, for at least one pixel of the uncalibrated multispectral data cube, the at least one substance indicator and a corresponding calibrated multispectral data cube, wherein the corresponding calibrated multispectral data cube is calculated using a calibration process and an atmospheric simulator that simulates a plurality of simulated uncalibrated multispectral data cubes by simulating different atmospheric conditions for the calibrated multispectral cube.

The present invention provides a medical image segmentation device based on global information perception. A scanning head scans medical images; a memory stores medical images, a medical image sample set, and a medical image segmentation network model; a processing card uses the trained medical image segmentation network model to segment the medical images, obtaining a segmentation result map with clear boundaries. The medical image segmentation network model of the present invention models the per-pixel correlation between high- and low-dimensional feature maps through a CAB with low computational complexity, realizing seamless fusion of low-dimensional detailed information and high-dimensional semantic information during the feature encoding process; the CAB provides a semantic bridge during the encoding and decoding feature fusion to alleviate the semantic gap problem. In addition, the feature fusion module AAFM aligns the receptive fields of features at all levels through dilated convolution, and realizes calibration of significant regions of features at all levels in the spatial dimension through a feature fusion activation method. Therefore, the present invention can provide a more accurate segmentation result for medical images with complex boundary textures.

Techniques are provided for facilitating detection threshold determination for infrared imaging systems and methods. In one example, a method includes capturing, by an imaging device, a thermal image of a scene. The method further includes determining temperature difference data indicative of a difference between temperature data of the thermal image associated with a background of the scene and temperature data of the thermal image associated with gas detection. The method further includes determining detection threshold data based on sensitivity characteristics associated with the imaging device and the temperature difference data. The method further includes generating a detection threshold image based on the detection threshold data. Each pixel of the detection threshold image corresponds to a respective pixel of the thermal image and has a value indicative of a detection threshold associated with the respective pixel of the thermal image. Related devices and systems are also provided.

A method and device for coding and decoding a coded data stream representative of at least one image split into blocks. For a current block, a group of pixel values in the block is determined from previously decoded pixels, and for each pixel, a prediction residue is decoded. A prediction value for the pixel is determined according to a first prediction mode by predicting the pixel from at least one other previously decoded pixel belonging to the current block. Information is decoded from the stream indicating whether the pixel is predicted according to a second prediction mode using a prediction resulting from the group of pixel values in the block. When the pixel is predicted according the second mode, the prediction value for the pixel is replaced with a selected value of the group. The pixel is reconstructed using the prediction value associated with the pixel and the prediction residue.

The present disclosure relates to a computer-implemented method of classifying an object from a real-world environment in which an entity 32 operates, comprising: receiving a hyperspectral image 31 of the real-world scene from a hyperspectral camera mounted to the entity; obtaining a hyperspectral signature for each pixel of the hyperspectral image; identifying a material associated with each pixel based on the hyperspectral signature; clustering the pixels of the hyperspectral image into sub-objects based on the identified materials; comparing the sub-objects to sub-objects of known objects; and identifying the object (60, 62, 64, 66, 68 , Fig. 4) based on the comparison. Sub-objects may be classified into primary and secondary ones. The primary may have the largest size or highest prediction probability. The primary may be the sub-object whose material has the lowest occurrence frequency. Feasible search zones may be identified. Sub-objects may be weighted according to their prediction confidence. The entity may be a tank

Image sensors with improved memory effect are disclosed herein. In one embodiment, a method for reducing image lag associated with a pixel included in a plurality of pixels is described. The pixel includes a photodiode, a first floating diffusion coupled to the photodiode through a transfer transistor, a second floating diffusion coupled to the first floating diffusion through a dual floating diffusion transistor, and a lateral overflow integration capacitor coupled between the second floating diffusion and a bias voltage source. The lateral overflow integration capacitor is further coupled to a pixel reference voltage source through a reset transistor. Operation of the pixel comprises an idle period and an integration period after the idle period. The method also includes configuring the lateral overflow integration capacitor to be either zero-biased or forward-biased during the idle period.

A method for estimating distance to an object in a scene using an imaging system (400) comprising a camera array (410) with multiple imagers (540), an image processing pipeline module (420) and a controller (440). The image processing pipeline module (420) comprises an upstream pipeline processing module (510), an image pixel correlation module (514), and a parallax confirmation and measurement module (518). The method comprises: providing images (412), including a current image, captured by the multiple imagers (540) to the upstream pipeline processing module (510) for processing; aligning, by the image pixel correlation module (514), portions of images, including the current image, captured by different imagers of the multiple imagers to compensate for parallax; processing, by the parallax confirmation and measurement module (518), the current image to detect and measure the parallax by keeping track of various pair-wise measurements and calculating a parallax difference that is a best fit to a sample data; and determining distance to an object in the scene using the measured parallax.

A driving device includes a pulse intensity modulation module, a pulse width modulation module, a pulse density modulation module, and a driving module. The pulse intensity modulation module receives an image processing signal related to a pixel and generates a pulse intensity according to the image processing signal. The pulse width modulation module receives the image processing signal and generates a pulse width according to the image processing signal. The pulse density modulation module receives the image processing signal and generates a pulse density according to the image processing signal. The driving module receives the pulse intensity, the pulse width, and the pulse density and generates a driving signal to the pixel according to the pulse intensity, the pulse width, and the pulse density.

This information processing device can improve resolution of a taste that can be reproduced in the oral cavity of a person. The information processing device: causes a display unit to display an image which is indicated by image data indicating the image and in which taste data indicating one or more tastes is associated with each of at least some pixels; and outputs, on the basis of an operation received via the image displayed on the display unit, the taste data associated with the pixel designated by the operation.