Abstract: The present disclosure relates to identifying vehicles using wireless device identifiers. In accordance with aspects of the present disclosure, a system for identifying vehicles in a parking structure includes a camera configured to capture images of an area in the parking structure where the camera captures an image containing one or more vehicle(s), a detector configured to scan for wireless device identifiers in the area, and a processing system including an electronic storage. The processing system is configured to execute instructions to access the image containing the vehicle(s) in the area and access one or more wireless device identifier(s) scanned by the detector in the area, process the image containing the vehicle(s) to extract one or more license plate identifier(s) corresponding to the vehicle(s), and store in the electronic storage at least one record associating the license plate identifier(s) with the wireless device identifier(s).

Abstract: Techniques are described for generating reformatted views of a three-dimensional (3D) anatomy scan using deep-learning estimated scan prescription masks. According to an embodiment, a system is provided that comprises a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory. The computer executable components comprise a mask generation component that employs a pre-trained neural network model to generate masks for different anatomical landmarks depicted in one or more calibration images captured of an anatomical region of a patient. The computer executable components further comprise a reformatting component that reformats 3D image data captured of the anatomical region of the patient using the masks to generate different representations of the 3D image data that correspond to the different anatomical landmarks.

Abstract: A method of hybrid lane modeling, including, receiving a roadway image, extracting a set of lane points from the roadway image, fitting a polynomial line to the set of lane points, determining a fitted error of the fitted polynomial line, outputting the polynomial line if the fitted error is less than a predetermined threshold, selecting a set of clean lane points from the set of lane points if the fitted error is greater than the predetermined threshold and interpolating a cubic spline line to the set of clean lane points.

Abstract: Systems and methods are described herein for tracking an elongate instrument or other medical instrument in an image.

Abstract: A conversion device (20) is operable to perform a learning-based method of generating a synthetic electron density image (sCT) of an anatomical portion based on one or more magnetic resonance, MR, images. The method is processing-efficient and capable of producing highly accurate sCT images irrespective of misalignment in the underlying training set. The conversion device (20) receives and installs a machine-learning model (22) trained to predict coefficients of an image transfer function (24). The conversion device (20) then receives a current set of MR images (MRI) of the anatomical portion, computes current coefficients ([C]) of the image transfer function (24) by operating the machine-learning model (22) on the current set of MR images (MRI), and computes a current sCT image of the anatomical portion by operating the current coefficients ([C]), in accordance with the image transfer function (24), on the current set of MR images (MRI).

Abstract: The disclosure relates to system for processing an image of at least one camera. The camera has predetermined camera parameters including a lens distortion and a camera pose with respect to a predefined reference frame. The system comprises: a trained neural network with a predefined architecture, the neural network being configured to receive the image of the camera as input and to predict in response at least one characteristic, wherein the neural network architecture comprises at least one static feature map configured to encode the predetermined camera parameters including the lens distortion and/or the camera pose.

Abstract: A method for detecting image information includes: acquiring at least one sample of image pair to be processed; calculating a reconstruction loss function of the second feature extraction model based on the first image samples and the first reconstructed image feature information; calculating an adversarial loss function of the third feature extraction model based on the second reconstructed image feature information and the first image samples; optimizing the first model parameters in the first feature extraction model based on the reconstruction and the adversarial loss function to generate the optimized first feature extraction model; inputting the acquired image pair to be processed into the optimized first feature extraction model to generate the difference information. The method reduces the first feature extraction model's dependence on the labeled data and improves the model's recognition efficiency and accuracy by using the samples without the labeled difference information.

Abstract: The point cloud encoding method includes obtaining subgroup information of N frames of point clouds, where the subgroup information includes a quantity M of subgroups into which the N frames of point clouds are divided or a quantity of frames of point clouds included in each of one or more subgroups among the M subgroups, and writing the subgroup information of the N frames of point clouds into a bitstream. The point cloud decoding method includes receiving a bitstream, parsing the bitstream to obtain subgroup information, where the subgroup information includes a quantity M of subgroups into which N frames of point clouds are divided or a quantity of frames of point clouds included in each of one or more subgroups among the M subgroups, and decoding the N frames of point clouds based on the subgroup information.

Abstract: A task appropriateness determination apparatus includes a first learning unit causing artificial intelligence (AI) to learn image information of an index indicating a target object in a task appropriately completed state, an appropriate image provider providing an image possibly including the target object in the appropriately completed state and the index, a second learning unit causing the AI to detect an image where the index is present from the provided image after learning of the index, and learn image information of the target object in the image where the index is present, an image capturing unit capturing an image of a region including the target object and the index at least after the task, and a task appropriateness determiner determining that the task has been appropriately performed in response to detection by the AI of the target object roughly identical to the learned target object in the appropriately completed state.

Abstract: Gait, the walking pattern of individuals, is one of the important biometrics modalities. Most of the existing gait recognition methods take silhouettes or articulated body models as gait features. These methods suffer from degraded recognition performance when handling confounding variables, such as clothing, carrying and viewing angle. To remedy this issue, this disclosure proposes to explicitly disentangle appearance, canonical and pose features from RGB imagery. A long short-term memory integrates pose features over time as a dynamic gait feature while canonical features are averaged as a static gait feature. Both of them are utilized as classification features.

Abstract: A first binary image is generated by binarizing an input image based on a threshold, a second binary image is generated by changing a pixel that has predetermined high luminance in the input image into a black pixel, and whether a black pixel cluster in the second binary image is made to be an extraction target is determined based on a position of a character image identified based on a black pixel cluster in the first binary image, and a position of the black pixel cluster in the second binary image.

Abstract: A method and system by which a bounding box disposed around a segmented object in a camera (or other perception sensor) 2D image can be used to produce an estimate for both the location of the object—its position relative to the position of the camera that obtained the image (i.e., translation)—and the angle of rotation of the surface that the object is located on. The method and system may be used by an advanced driver assistance system (ADAS), an autonomous driving (AD) system, or the like. The input includes a simple camera (or other perception sensor) 2D image, with the ego vehicle generating 2D or 3D bounding boxes for objects detected at the scene. The output includes, for each object, its estimated distance from the ego vehicle camera/perception sensor and the angle of rotation of the surface underneath the object relative to the surface underneath the ego vehicle.

Abstract: The present invention relates to the field of inland vessel identification and ranging technology, and discloses a method, system, medium, equipment and terminal for identifying and ranging inland vessels. In the stage of vessel identification, based on the classical YOLO-V4 network model, the MobileNetV1 network is used to replace the feature extraction network CSPDarknet53 of the YOLO-V4 model; In the stage of vessel ranging, a binocular stereo vision ranging model is established, and the FSRCNN is used for super-resolution reconstruction of the original image pairs to enhance the vessel feature information; the ORB algorithm is used to achieve feature detection and matching at the sub-pixel level to obtain the parallax value between image pairs, and the depth information of the vessel target is obtained by triangulation principle and coordinate conversion.

Abstract: A method for assessing a camera calibration. In the method, a first quality measure is ascertained, a systematic error having to be assessed using the first quality measure, the assessment being carried out with respect to errors remaining after a calibration, an overall calibration object including at least one calibration object being virtually segmented into calibration objects, a detector noise being estimated for each calibration object, which are combined to form an overall estimate, which is compared with an estimate of the detector noise of the overall calibration object.

Abstract: Methods, systems, and apparatuses are described for interacting with images, segmenting the images, and determining one or more regions of interest within the images.

Abstract: A disclosed monitoring system includes infrared light sources that illuminate a subject in a sequenced manner and a camera that captures images of the subject during periods in which the subject is illuminated by one of the light sources. The system includes a processor that analyzes captured images to determine a brightness measure of the images, and a controller controls output power of the infrared light sources in response to the brightness measure. In response to the processor detecting a brightness measure below a predetermined brightness threshold, the controller is configured to switch off or reduce an output illumination intensity of one of the infrared light sources. A disclosed method further determines whether an emission source is occluded by modulating an intensity of an electromagnetic emission source, detecting whether the modulation pattern is present in captured images, and determining that the emission source is occluded based on the detected modulation.

Abstract: A calibration system includes: a storage unit that stores a reference trajectory of a mobile body in an image of a predetermined traffic environment photographed by an imaging sensor and a reference position in the image; an acquisition unit that acquires a plurality of the images of the traffic environment that are sequentially photographed; a generation unit that generates an estimated trajectory of the mobile body based on position information of the mobile body detected from the plurality of the images; a calculation unit that calculates an amount of positional deviation of the imaging sensor based on the reference trajectory and the estimated trajectory; a correction unit that corrects the reference position by using the amount of positional deviation; and an update unit that updates a position transformation model for transforming a two-dimensional position in the image into a three-dimensional position by using the corrected reference position.

Abstract: This application provides a method for measuring dimensions to reduce measurement time and improve production efficiency, including: obtaining a first image and a second image of a to-be-measured workpiece, where the first image and the second image are images captured by a first camera and a second camera at different positions respectively; extracting a first corner set of the to-be-measured workpiece from the first image and a second corner set of the to-be-measured workpiece from the second image separately; rectifying position coordinates of the first corner set and position coordinates of the second corner set to obtain a position coordinate value of the first corner set and a position coordinate value of the second corner set in a same coordinate system; and obtaining dimensions of the to-be-measured workpiece based on the position coordinate value of the first corner set and the position coordinate value of the second corner set.

Abstract: In the present disclosure, a candidate area is determined based on a pixel having a specific color included in an input image, and an area is determined to be a processing target from the candidate area based on a pixel having a predetermined color different from the specific color included in the candidate area. Further, a second binary image in which a pixel corresponding to the pixel having the specific color is converted into a white pixel is generated by converting, in a first binary image obtained by the input image being binarized, a pixel that is included in the area determined to be the processing target and corresponds to the pixel having the specific color, into a white pixel.

Abstract: An object included in a low-resolution image can be recognized with a high degree of precision. An acquisition unit acquires, from a query image, an increased-resolution image, which is acquired by increasing the resolution of the query image, by performing pre-learned acquisition processing for increasing the resolution of an image. A feature extraction unit, using the increased-resolution image as input, extracts a feature vector of the increased-resolution image by performing pre-learned extraction processing for extracting a feature vector of an image. A recognition unit recognizes an object captured on the increased-resolution image on the basis of the feature vector of the increased-resolution image and outputs the recognized object as the object captured on the query image.