Abstract: In various examples, multimodal image data may be used to generate a set of top-down tile images, which are applied to a deep neural network generator architecture model to produce lane marking-specific heatmap images corresponding to the set of top-down tile images. The multimodal sensor data may include LIDAR-captured intensity channel data, LIDAR-captured feature height channel data, and optical color image channel data. The set of top-down tile images may be processed by the generator model to automatically detect lane boundaries and navigation boundaries to generate pixel-level heatmap images that may classify lane markings by marking characteristics such as line type and/or color. The generator model may comprise an encoder-decoder architecture, with multiscale feature extraction and/or context extraction functional layers intervening between the encoder model and the decoder model.

Abstract: Approaches presented herein provide for the ability to process, store, index, and search geospatial information such as maps with flexible granularity. A set of observations, such as may include sensor data captured for a region of an environment, can be fed as input to a language model. The language model can generate a tokenized description of the region, as may include a text string of tokens encapsulating semantics, topology, geometry, and/or other aspects of the region. A feature vector or embeddings for the region can be generated based on the tokenized description, and a similarity search performed against a vector database, for example, to identify similar feature vectors corresponding to similar regions or domains. Labels or other information associated with these similar feature vectors can be automatically applied to the example region. Clustering of feature vectors or other embeddings can also be performed based in part on the similarity.

Abstract: Approaches presented herein provide for the automated, end-to-end generation of map data based at least in part on sensor data captured for an environment. At least one language model can be used to generate a text-based, tokenized description of the environment that includes semantics, topology, geometry, and/or other information for the environment. A generation pipeline can use one or more language models in one or more stages, and the data passed between stages can be in a determined tokenized representation format, as may correspond to a tokenized text string in a specific structured language.

Abstract: Approaches presented herein provide for the performance of quality assurance-related tasks with respect to a representation of an environment, such as a set of generated map data. In particular, a language model can be used to generate a tokenized representation of a map using information such as the semantics, topology, and/or geometry determinable from the map data. A language model-generated representation can comply with real-world rules and constructs, and can account for omissions or errors in the input data based upon known relationships and semantics for various objects in the environment. One or more language models can be used to not only identify potential issues in the map data, but also to make recommendations for modifications and/or to generate plaintext descriptions of the issues, modifications, or recommendations to assist a human reviewer in addressing the issues.

Abstract: Methods and systems for detecting defects on a specimen are provided. One method includes generating first and second mode test, reference, and difference images of a specimen for first and second modes of an inspection subsystem, respectively. The method also includes combining the first and second mode test images, the first and second mode reference images, and the first and second mode difference images as an input for defect detection. In addition, the method includes detecting defects on the specimen based on at least the first and second mode difference images.

Abstract: Methods and systems for detecting defects on a specimen are provided. One system includes one or more computer systems and one or more components executed by the one or more computer systems. The component(s) include a deep learning model configured for, for a location on a specimen, generating a gray scale simulated design data image from a high resolution image generated at the location by a high resolution imaging system. The computer system(s) are configured for generating a simulated binary design data image for the location from the gray scale simulated design data image. The computer system(s) are also configured for detecting defects at the location on the specimen by subtracting design data for the location from the simulated binary design data image.

Abstract: Methods and systems for setting up inspection of a specimen are provided. One system includes one or more computer subsystems configured for acquiring a reference image for a specimen and modifying the reference image to fit the reference image to a design grid thereby generating a golden grid image. The one or more computer subsystems are also configured for storing the golden grid image for use in inspection of the specimen. The inspection includes aligning a test image of the specimen generated from output of an inspection subsystem to the golden grid image.

Abstract: A system includes a processing unit communicatively coupled to a detector array of an optical wafer characterization system. The processing unit is configured to perform one or more steps of a method or process including the steps of acquiring one or more target images of a target location on a wafer from the detector array, applying a de-noising filter to at least the one or more target images, determining one or more difference images from one or more reference images and the one or more target images, and up-sampling the one or more difference images to generate one or more up-sampled images. One or more wafer defects are detectable in the one or more difference images or the up-sampled images.

Abstract: Methods and systems for aligning images of a specimen are provided. One method includes reducing noise in a test image generated for a specimen by an imaging subsystem thereby generating a denoised test image. The method also includes detecting one or more patterned features in the denoised test image extending in at least a horizontal or vertical direction. In addition, the method includes designating an area of the denoised test image in which the detected one or more patterned features are located as a region of interest in the denoised test image. The method further includes aligning the denoised test image to a reference image for the specimen using only the region of interest in the denoised test image and a corresponding area in the reference image.

Abstract: A system for characterizing a specimen is disclosed. In one embodiment, the system includes a controller configured to: receive training images of one or more defects of the specimen; generate a machine learning classifier based on the training images; receive product images of one or more defects of a specimen; determine one or more defect type classifications of one or more defects with the machine learning classifier; filter the product images with one or more smoothing filters; perform binarization processes to generate binarized product images; perform morphological image processing operations on the binarized product images; determine one or more algorithm-estimated defect sizes of the one or more defects based on the binarized product images; and determine one or more refined estimates of one or more defect sizes of the one or more defects based on the one or more algorithm-estimated defect sizes and the one or more defect type classifications.

Abstract: A rendered image is aligned with a scanning electron microscope (SEM) image to produce an aligned rendered image. A reference image is aligned with the SEM image to produce an aligned reference image. A threshold probability map also is generated. Dynamic compensation of the SEM image and aligned reference image can produce a corrected SEM image and corrected reference image. A thresholded defect map can be generated and the defects of the thresholded probability map and the signal-to-noise-ratio defects of the thresholded defect map are filtered using a broadband-plasma-based property to produce defect-of-interest clusters.

Abstract: Methods and systems for setting up inspection of a specimen are provided. One system includes one or more computer subsystems configured for acquiring a reference image for a specimen and modifying the reference image to fit the reference image to a design grid thereby generating a golden grid image. The one or more computer subsystems are also configured for storing the golden grid image for use in inspection of the specimen. The inspection includes aligning a test image of the specimen generated from output of an inspection subsystem to the golden grid image.

Abstract: Methods and systems for detecting defects on a specimen are provided. One system includes one or more computer systems and one or more components executed by the one or more computer systems. The component(s) include a deep learning model configured for, for a location on a specimen, generating a gray scale simulated design data image from a high resolution image generated at the location by a high resolution imaging system. The computer system(s) are configured for generating a simulated binary design data image for the location from the gray scale simulated design data image. The computer system(s) are also configured for detecting defects at the location on the specimen by subtracting design data for the location from the simulated binary design data image.

Abstract: Methods and systems for aligning images of a specimen are provided. One method includes reducing noise in a test image generated for a specimen by an imaging subsystem thereby generating a denoised test image. The method also includes detecting one or more patterned features in the denoised test image extending in at least a horizontal or vertical direction. In addition, the method includes designating an area of the denoised test image in which the detected one or more patterned features are located as a region of interest in the denoised test image. The method further includes aligning the denoised test image to a reference image for the specimen using only the region of interest in the denoised test image and a corresponding area in the reference image.

Abstract: A rendered image is aligned with a scanning electron microscope (SEM) image to produce an aligned rendered image. A reference image is aligned with the SEM image to produce an aligned reference image. A threshold probability map also is generated. Dynamic compensation of the SEM image and aligned reference image can produce a corrected SEM image and corrected reference image. A thresholded defect map can be generated and the defects of the thresholded probability map and the signal-to-noise-ratio defects of the thresholded defect map are filtered using a broadband-plasma-based property to produce defect-of-interest clusters.

Abstract: A system for characterizing a specimen is disclosed. In one embodiment, the system includes a controller configured to: receive training images of one or more defects of the specimen; generate a machine learning classifier based on the training images; receive product images of one or more defects of a specimen; determine one or more defect type classifications of one or more defects with the machine learning classifier; filter the product images with one or more smoothing filters; perform binarization processes to generate binarized product images; perform morphological image processing operations on the binarized product images; determine one or more algorithm-estimated defect sizes of the one or more defects based on the binarized product images; and determine one or more refined estimates of one or more defect sizes of the one or more defects based on the one or more algorithm-estimated defect sizes and the one or more defect type classifications.

Abstract: Techniques for fast and accurate measuring test strip intensities are disclosed herein. A cassette attachment device for detecting intensity of a test strip cassette includes a strip chamber configured to accommodate at least a portion of a test strip, a light source configured to provide illumination to the test strip cassette via indirect lighting, an attaching mechanism configured to attach the device to a mobile device, and a camera window configured to transmit light signal reflected from the test strip cassette such that the mobile device can capture an image of the test strip cassette illuminated by the light source.

Abstract: Techniques for fast and accurate measuring test strip intensities are disclosed herein. A cassette attachment device for detecting intensity of a test strip cassette includes a strip chamber configured to accommodate at least a portion of a test strip, a light source configured to provide illumination to the test strip cassette via indirect lighting, an attaching mechanism configured to attach the device to a mobile device, and a camera window configured to transmit light signal reflected from the test strip cassette such that the mobile device can capture an image of the test strip cassette illuminated by the light source.

Abstract: Techniques for fast and accurate measuring test strip intensities are disclosed herein. A method for measuring a test strip intensity comprising steps of obtaining an image of a sample line in a test strip and a plurality of reference lines, wherein the reference lines have known intensities; determining grayscale values of the sample line and the reference lines from the image; constructing a standard curve based on the grayscale values versus the known intensities of the reference lines; and determining the intensity of the sample line by fitting the grayscale value of the sample line on the standard curve.

Abstract: Techniques for fast and accurate measuring test strip intensities are disclosed herein. A method for measuring a test strip intensity comprising steps of obtaining an image of a sample line in a test strip and a plurality of reference lines, wherein the reference lines have known intensities; determining grayscale values of the sample line and the reference lines from the image; constructing a standard curve based on the grayscale values versus the known intensities of the reference lines; and determining the intensity of the sample line by fitting the grayscale value of the sample line on the standard curve.