Abstract: A relative position of an object in the surroundings of a vehicle is estimated based on a two-dimensional camera image. A control unit determines an object contour of the object from the camera image and determines at least one digital object template that represents the object based on the object contour. The control unit forward projects the at least one object template from respective different positions onto an image plane of the camera image. Each forward-projected object template yields a respective two-dimensional contour proposal, and the control unit compares the contour proposals with the object contour of the object.

Abstract: A surface data acquisition, storage, and assessment system for detecting and quantifying similarities or differences between scanned surface data before and after the surface has been acted upon by a surface altering element.

Abstract: The disclosure herein enables tracking of multiple objects in a real-time video stream. For each individual frame received from the video stream, a frame type of the frame is determined. Based on the individual frame being an object detection frame type, a set of object proposals is detected in the individual frame, associations between the set of object proposals and a set of object tracks are assigned, and statuses of the set of object tracks are updated based on the assigned associations. Based on the individual frame being an object tracking frame type, single-object tracking is performed on the frame based on each object track of the set of object tracks and the set of object tracks is updated based on the performed single-object tracking. For each frame received, a real-time object location data stream is provided based on the set of object tracks.

Abstract: The present disclosure provides devices, systems and methods for mapping of traffic boundaries.

Abstract: A computer-implemented method for training an artificial neural network using training data, which include features and identifiers, the features characterizing term candidates from a corpus, the corpus including a text from a domain, the identifier characterizing a degree of association to at least three classes for term candidates that differ from one another, different classes indicating different degrees of association of the term candidates to the domain, the training data including an assignment of features to identifiers. An artificial neural network, method for classifying term candidates, and computer-implemented method for generating training data, are also described.

Abstract: A board damage classification system includes a Convolutional Neural Network (CNN) sub-engine and a Graph Convolutional Network (GCN) sub-engine that were trained based on digital images of structures that have experienced natural disasters. The CNN sub-engine receives a board digital image of a board, analyzes the board digital image to identify board features, and determines a board feature damage classification for the board features. The CGN sub-engine receives a board feature graph that was generated using the board digital image and that includes nodes that correspond to the board features in the board digital image, and defines relationships between the nodes included in the board feature graph. The board feature damage classification determined by the CNN sub-engine and the relationships defined by the GCN sub-engine are then used to generate a board damage classification that includes a damage probability for board features in the board digital image.

Abstract: A method and device for generating a composite group image from subgroup images is provided. Subgroup images, each having a common background, are accessed. The boundaries of a subgroup area within each of the subgroup images is determined. At least one horizontal and at least one vertical shift factor is determined using the determined boundaries. An arrangement for the subgroup images based on the at least one horizontal and the at least one vertical shift factor is generated. The composite group image is generated by blending the subgroup images arranged in the arrangement.

Abstract: Systems and methods for determining a concordance between results of medical assessments are provided. Results of a medical assessment of a first type for an anatomical object of a patient and results of a medical assessment of a second type for the anatomical object are received. The results of the medical assessment of the first type are converted to a hemodynamic measure. A concordance analysis between the results of the medical assessment of the first type and the results of the medical assessment of the second type based on the hemodynamic measure is performed. Results of the concordance analysis are output.

Abstract: Techniques are provided for processing video frames in a process flow that includes first and second computation engines. In an example, the first engine is an artificial intelligence based computation engine, and the second engine is a heuristics-based computation engine. A sequence of frames of a video includes a first and second frames that are two consecutive frames in the sequence. An analyzer determines whether the second frame has non-redundant information relative to the first frame. In response to the determination, the analyzer selects one of the first or second engine for processing at least a section of the second frame. For example, if the second frame has non-redundant information relative to the first frame, at least the section of the second frame is processed by the first engine. If the second frame does not include non-redundant information, the second frame is processed by the second engine.

Abstract: A method for training a deep learning model of a patterning process. The method includes obtaining (i) training data comprising an input image of at least a part of a substrate having a plurality of features and a truth image, (ii) a set of classes, each class corresponding to a feature of the plurality of features of the substrate within the input image, and (iii) a deep learning model configured to receive the training data and the set of classes, generating a predicted image, by modeling and/or simulation of the deep learning model using the input image, assigning a class of the set of classes to a feature within the predicted image based on matching of the feature with a corresponding feature within the truth image, and generating, by modeling and/or simulation, a trained deep learning model by iteratively assigning weights using a loss function.

Abstract: A method for predicting brain disease state change is disclosed. The method includes acquiring test images obtained by capturing a portion of a human brain at a time interval, performing a pre-processing procedure of converting the test images into test voxels configured to be processed for image analysis, wherein a respective test voxel of the test voxels is composed of three-dimensional voxel units, mapping first and second test voxels selected from the test voxels acquired from a patient, with each other on a three-dimensional voxel unit, wherein the first test voxel is acquired at a first time-point and the second test voxel is acquired at a second time-point, generating a voxel-based data-set based on the mapped first and second test voxels, extracting a change in the test voxels using a deep neural network, and generating a state change probability model based on the change in the test voxels.

Abstract: A system comprises a processor and a memory storing instructions. The processor receives an image for processing using a reinforcement learning based agent comprising a neural network trained using a reward function. The image includes N lane lines of a roadway, where N is a positive integer. The instructions configure the processor to traverse the image using the agent at least N times from a first end of the image to a second end of the image by: incrementally moving the agent from a first side of the image to a second side of the image after each traversal; and maximizing rewards for the agent using the reward function during each traversal of the image using the agent. The instructions configure the processor to identify the N lane lines of the roadway as a single cluster of lane lines after traversing the image using the agent at least N times.

Abstract: An image processing apparatus according to the present invention calculates, even in a case where a region of a part as an observation target included in an image capturing range is different between a plurality of medical images in different time phases, a degree of slippage of the region of the part as the observation target with high accuracy.

Abstract: A person re-identification method and apparatus, a device, and a readable storage medium. A homogeneous training network of an initial person re-identification network is trained by means of an objective function such as a knowledge synergy for dynamic classification probability loss function to obtain a final person re-identification network carrying more accurate final weight parameters, and a person re-identification task is performed by means of the final person re-identification network. In this way, the accuracy and performance of the person re-identification network to process the person re-identification task may be improved, the storage space in a device may be reduced, more beneficial to the storage and deployment of the portable device, and the amount of calculation of performing the person re-identification task may be reduced, thereby increasing the processing rate of the person re-identification task.

Abstract: The technology described herein is directed to a media indexer framework including a character recognition engine that automatically detects and groups instances (or occurrences) of characters in a multi-frame animated media file. More specifically, the character recognition engine automatically detects and groups the instances (or occurrences) of the characters in the multi-frame animated media file such that each group contains images associated with a single character. The character groups are then labeled and used to train an image classification model. Once trained, the image classification model can be applied to subsequent multi-frame animated media files to automatically classifying the animated characters included therein.

Abstract: A method includes receiving a first time series of video frames depicting a first area of interest that includes a display area in a retail environment, and using classification by a convolutional neural network to detect instances of people picking up inventory items from the display area. The method also includes receiving a second time series of video frames depicting a second area of interest in the retail environment, and determining, based upon one or more portions of the second time series of video frames, that at least one inventory item picked up at the display area was not, or will not likely be, checked out. The method also includes causing one or more alert messages to be displayed, including causing an alert message to be displayed based on the determining.

Abstract: Systems and methods for detecting/identifying novel material samples are provided. A test sample image is processed with a trained transformation function to obtain a transformed matrix. A measure of similarity of the test image based on the transformed matrix is compared to a threshold to determine whether the test sample is novel to a batch of material samples that are provided to train the transformation function.

Abstract: A first processing unit detects each of a plurality of patterns included in the image as one of families by subjecting the image to a neural network process. An extraction unit extracts a plurality of parts that include families from the image, based on a position of the families detected. A second processing unit acquires intermediate data for an intermediate layer unique to each family, by subjecting the plurality of parts extracted to a neural network process. A clustering unit subjects the intermediate data acquired to clustering in accordance with the number of types of pattern. A calculation unit calculates a number of patterns included in each cluster that results from clustering.

Abstract: A motion classification model learning apparatus that learns a model for early recognizing a motion is provided. A training data acquisition part acquiring training data configured with pairs of video information about a motion that can be classified into any of a plurality of categories according to characteristics of the motion and category information that is a correct label corresponding to the video information; a motion history image generation part generation a motion history image of the video information; and a model learning part learning a model that outputs a label that is the category information, with the motion history image as an input are included.

Abstract: Simultaneous learning of a plurality of different tasks and domains, with low costs and high precision, is enabled. A learning unit 160, on the basis of learning data, uses a target encoder that takes data of a target domain as input and outputs a target feature expression, a source encoder that takes data of a source domain as input and outputs a source feature expression, a common encoder that takes data of the target domain or the source domain as input and outputs a common feature expression, a target decoder that takes output of the target encoder and the common encoder as input and outputs a result of executing a task with regard to data of the target domain, and a source decoder that takes output of the source encoder and the common encoder as input and outputs a result of executing a task with regard to data of the source domain, to learn so that the output of the target decoder matches training data, and the output of the source decoder matches training data.