Abstract: An information processing apparatus comprising a division processing unit configured to divide each of input depth data and image data corresponding to the input depth data and having a higher resolution than the input depth data into a plurality of divided regions; an inference processing unit configured to infer depth data by complementing input depth data with image data for each of the divided regions; and a combining processing unit configured to combine depth data having a higher resolution than that of input depth data by combining inferred depth data, wherein the division processing unit performs division such that each divided region has an overlap region partially overlapping with an adjacent divided region.

Abstract: The present disclosure provides a method for predicting a target object, including performing a first voxelization on a plurality of first points included in a point cloud to obtain a plurality of first voxels; predicting a plurality of second points from the plurality of first voxels, wherein each of the plurality of second points represents a prediction of a center of the target object by a first point; performing a second voxelization on a plurality of first points and a plurality of second points to obtain one or more second voxels and one or more third voxels; and predicting the target object from the one or more third voxels. In addition, the present disclosure also provides an apparatus and non-transitory computer-readable storage medium that can perform the methods described above.

Abstract: A system for monitoring a moving element within a monitored system, comprising: an illumination device configured to periodically provide instantaneous light to a longitudinal moving element; an image sensor configured to capture at least one image of at least a portion of the moving element; and one or more processors configured to: obtain one or more images of the moving element during motion under illumination emitted by the illumination device; analyze an image to determine whether one or more failure modes are present within the captured portion of the moving element; and register the image with one or more other images to obtain further information about the at least one failure mode.

Abstract: Methods and systems are provided herein for maximum contrast projection (MCP). In one example, a method includes dividing image data into a plurality of tiles and a plurality of sub-z-stacks, wherein the image data includes a plurality of z-plane images; determining a tile of a plurality of the plurality of sub-z-stacks with a highest local contrast via calculation of a Brenner gradient value for each tile and generation of a Brenner gradient distribution for each of the plurality of the plurality of sub-z-stacks; and projecting pixels of the tile with the highest local contrast for each of the plurality of the plurality of sub-z-stacks to an MCP image.

Abstract: In one embodiment, a method includes recording, by a camera of a client device, a video of a region of a first user's skin and estimating, from the recorded video, a current ratio of ratios (RoR) for the first user corresponding to the first user's current blood-oxygen saturation. The method further includes converting the first user's determined RoR to a transformed RoR for the first user based at least in part on a baseline user's RoR determined while generating a trained SpO2 prediction model. The trained SpO2 prediction model is trained to estimate the baseline user's SpO2 value based on an input RoR value from the baseline user. The method further includes determining, by the trained SpO2 prediction model and based on the transformed RoR for the first user, the first user's current estimated blood-oxygen saturation.

Abstract: A method for preparing data for identifying analytes by coloring one or more analytes with markers in multiple coloring rounds, the markers in each case being specific for a certain set of analytes, detecting multiple markers using a camera, which for each coloring round generates at least one image that contains multiple pixels and includes colored signals and uncolored signals, a colored signal being a pixel containing color information of a marker, and an uncolored signal being a pixel containing color information that is not based on a marker, and storing the images of the particular coloring rounds for evaluating the color information, a data point in each case including one or more contiguous pixels in the images of the multiple coloring rounds, which are assigned to the same location in a sample.

Abstract: A method for generating a sports game highlight video based on winning probability includes receiving video of the sports game from at least one image capture device; performing object tracking analysis on the video to generate tracking data providing ball trajectory and player position information; identifying a shot event in the video of the sports game based on said tracking data; extracting video segments of the identified shot events from the video of the sports game; generating shot event metadata for indexing the video segments; computing a winning probability matrix including winning probabilities at point level by winning probability model of the sports game, based on said shot event metadata; and generating a sports game highlight video based on said winning probability matrix.

Abstract: One embodiment provides a system and method for generating vectorized maps. During operation, the system can obtain labeled training samples comprising images and vectorized ground truth information associated with the images. The system can generate, based on a machine learning model, a prediction output for each training sample, the prediction output comprising a vectorized map. The system can apply a differentiable rasterization technique to a vectorized map element within the vectorized map to obtain a segmentation mask, apply the differentiable rasterization technique to the vectorized ground truth information associated with the vectorized map element to obtain a ground truth segmentation mask, compute a segmentation loss function based on the segmentation mask and the ground truth mask, and update the machine learning model based on the segmentation loss function, thereby facilitating optimized generation of vectorized maps.

Abstract: Disclosed are methods, systems, and computer-implemented method for detecting foreign objects on a landing surface. For instance, the method may include capturing an image from one or more cameras associated with a vehicle, detecting the landing surface present in the captured image, retrieving a reference image for the detected landing surface, and extracting a plurality of feature points present in both the captured image and the reference image. The method may further include determining a transformation between the captured image and the reference image by correlating the plurality of feature points between the captured image and the reference image, creating a virtual image by applying the transformation to one of the captured image or the reference image, and comparing the virtual image to the other one of the captured image or the reference image that was not transformed to detect one or more foreign objects.

Abstract: An information processing apparatus acquires a first image obtained by capturing an image of a structure and first damage information of the structure extracted from the first image; acquires a second image obtained by capturing an image of the structure at a time point different from a time point at which the first image is captured and second damage information of the structure extracted from the second image; extracts feature points from the first image; extracts feature points from the second image; searches for corresponding feature points between the first image and the second image; performs coarse registration followed by fine registration on the first damage information and the second damage information based on information on the corresponding feature points to perform registration between the first damage information and the second damage information; and calculates a difference between the first damage information and the second damage information after the registration.

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: In some examples, a computing system accesses a field of view (FOV) image that has a field of view less than 360 degrees and has low dynamic range (LDR) values. The computing system estimates lighting parameters from a scene depicted in the FOV image and generates a lighting image based on the lighting parameters. The computing system further generates lighting features generated the lighting image and image features generated from the FOV image. These features are aggregated into aggregated features and a machine learning model is applied to the image features and the aggregated features to generate a panorama image having high dynamic range (HDR) values.

Abstract: An image processing device 100 of the present invention includes a region extraction unit 121 that extracts, from a captured image, a mobile body region that is a region having a possibility that a mobile body exists, a matching unit 122 that performs template matching on the mobile body region by using a template corresponding to a mobile body that is a detection object, and a detection unit 123 that detects each mobile body from the mobile body region separately, on the basis of the template matching.

Abstract: An image acquisition method. N images of an object to be shot are acquired. The N images are shot by N shooting devices. Shooting fields of view of the N shooting devices are different from each other. The N images are in one-to-one correspondence with the N shooting devices. Feature extraction is performed on the N images to obtain M features of the N images. M is an integer multiple of N. The M features include M/N types of features.

Abstract: A computer-implemented method for the ordinal classification of at least one microscope image calculates a classification into one of a plurality of classes which form an order with respect to an image property. The microscope image is input into a machine-learned model for ordinal classification. The model comprises binary classifiers which calculate estimates regarding whether the microscope image belongs to cumulative auxiliary classes, which combine different numbers of the classes which follow each other in the order. The estimates can be combined so as to form a total score, wherein the classification occurs by comparing the total score with threshold values which can be defined in a variable manner depending on the application, or interval limits of the classes can be defined so that the classes form intervals of different widths. The model for ordinal classification can also comprise further binary classifiers for inverse auxiliary classes.

Abstract: One example method includes receiving a digital image, receiving an input list that includes a respective hash for each frame in a group of frames, creating new frames on a particular area of the digital image, and the new frames are created and located based on the information in the input list, obtaining a respective hash for content included within each of the new frames, comparing one of the hashes generated for one of the new frames with a hash from the input list and, when the hashes match, continue the comparing for all frames of the particular area, and when all hashes from the input list have been checked, determining whether or not the digital image is an illegal image.

Abstract: A system and method for extracting a full range hyperspectral data from one or more RGB images. The method encompasses pre-processing, the one or more RGB images. Further the method encompasses estimating, an illumination component associated with each pre-processed RGB image. The method thereafter comprises removing, the illumination component from the each pre-processed RGB image. Further the method encompasses tracking, a trajectory of pixel(s) over frame(s) associated with the each pre-processed RGB image. The method then leads to identifying, a position of the pixel(s) in one or more adjacent frames of the frame(s) based on a patch defined around said one or more pixels. Thereafter the method encompasses extracting, the full range hyperspectral data from the each pre-processed RGB image based on at least one of the removal of the illumination component, the trajectory of the pixel(s) and the position of the pixel(s).

Abstract: A method for enhancing images for metrological applications. A first set of first images is provided, wherein the first set comprises at least one first image, the first set representing a scene of interest, and a second set of second images is provided, wherein the second set comprises at least one second image, the second set representing at least a part of the scene of interest. The method comprises the following steps: 1) jointly processing the first set and the second set by a neural network, and 2) outputting a third set of images by the neural network, the third set comprising at least one processed image, from which is determinable the position and/or orientation of the at least one object with a processed precision, wherein the processed precision is equal to or higher than the initial precision.

Abstract: A portion of a polygon is appropriately extracted from an image.

Abstract: A driving assistance device that recognizes a lane marking around an own vehicle with at least one sensor includes a lane marking detection unit that detects lane marking information from data acquired by the sensor, a lane marking type candidate estimation unit that recognizes a lane marking type from the detected lane marking information and calculates a likelihood of each lane marking type, a lane marking type branch point estimation unit that detects a lane marking type branch point that is a point at which a likelihood of the lane marking type changes with respect to an advancing direction of the own vehicle, and distinguishes regions before and after the lane marking type branch point as a first region and a second region, and a lane marking information integration unit that, in a case where a lane marking of the first region and a lane marking of the second region have the same lane marking type, integrates the lane marking of the first region and the lane marking of the second region into a continuous