Abstract: Methods, systems, computer-readable media, and apparatuses for generating an Augmented Reality (AR) object are presented. The apparatus can include memory and one or more processors coupled to the memory. The one or more processors can be configured to receive an image of at least a portion of a real-world scene including a target object. The one or more processors can also be configured to generate an AR object corresponding to the target object and including a plurality of parts. The one or more processors can further be configured to receive a user input associated with a designated part of the plurality of parts and manipulate the designated part based on the received user input.

Abstract: A method for obtaining a Fourier ptychography image using a smartphone comprises the steps of: (a) sequentially providing illumination of different angles to the sample by sequentially displaying, according to a first pattern composed of point light sources at different positions, the point light sources of the first pattern on a display of the smartphone; (b) obtaining an image for each illumination angle of the sample using a camera of the smartphone whenever illumination of different angles is provided by the point light sources of the first pattern; and (c) restoring a first Fourier ptychography image using a plurality of images for each illumination angle obtained using the camera of the smartphone.

Abstract: Techniques for auto-locating and positioning relative to an aircraft are disclosed. An example method can include a robot receiving a multi-dimensional representation of an enclosure that includes a candidate target aircraft. The robot can extract a geometric feature from the multi-dimensional representation associated with the candidate target aircraft. The robot can compare the geometric feature of the candidate target aircraft with a second geometric feature from a reference model of a target aircraft. The robot can determine whether the candidate target aircraft is the target aircraft based on the comparison. The robot can calculate a path from a location of the robot to the target aircraft based on the determination. The robot can traverse the path from the location to the target aircraft based on the calculation.

Abstract: Erroneous detection due to erroneous parallax measurement is suppressed to accurately detect a step present on a road. An in-vehicle environment recognition device 1 includes a processing device that processes a pair of images acquired by a stereo camera unit 100 mounted on a vehicle.

Abstract: In particular embodiments, a computing system of a device may determine a display peak power budget allocated for a display component of the device. The system may determine display information including display workload and display telemetry associated with the display component. The system may determine, in accordance with a display peak power management policy applied to the display peak power budget and the display information, one or more display-controlling parameters for maintaining the display component to operate within the display peak power budget. The system may determine, based on the one or more display-controlling parameters, a plurality of grayscales for a plurality of regions on a display screen of the device. The system may adjust a rendered frame based on the plurality of grayscales and output the adjusted rendered frame on the display screen of the device.

Abstract: The present disclosure is directed to providing a monitoring device that can improve the accuracy in tracking ships. A monitoring device (10) according to the present disclosure includes a position information acquiring unit (11) configured to acquire position information of an object to be tracked; an estimating unit (12) configured to estimate a position of the object to be tracked displayed in an image captured of a predetermined region; and an information generating unit (13) configured to generate path information of the object to be tracked by supplementing, based on an estimated position of the object to be tracked, the position of the object to be tracked held between the position indicated by the position information acquired at a first timing and the position indicated by the position information acquired at a second timing later than the first timing.

Abstract: A method for generating a monitoring image. The method includes: providing an image sequence of the surroundings to be monitored with the aid of an imaging system; determining at least one monitoring area and at least one periphery area of at least one image of the image sequence with the aid of a learning-based semantic segmentation method; compressing the monitoring area of the at least one image of the image sequence with a first compression quality; and compressing the periphery area of the at least one image of the image sequence with a second compression quality to generate the compressed monitoring image, the second compression quality being lower than the first compression quality.

Abstract: The present disclosure provides a visual perception method and apparatus, a perception network training method and apparatus, a device and a storage medium. The visual perception method recognizes the acquired image to be perceived with a perception network to determine a perceived target and a pose of the perceived target, and finally determines a control command according to a preset control algorithm and the pose, so as to enable an object to be controlled to determine a processing strategy for the perceived target according to the control command. According to the perception network training method, acquire image data and model data, then generate an edited image with a preset editing algorithm according to a 2D image and a 3D model, and finally train the perception network to be trained according to the edited image and the label.

Abstract: A checkout-payment device includes a table on which an item can be placed; a touch screen display; a camera for shooting the item on the table; and a controller configured to perform an operation for recognizing the item based on an image captured by the camera, display an item recognition result on the touch screen display, and start a confirmation waiting time during which the controller continues the item recognition operation and the user can confirm the item recognition result, followed by transitioning to a state in which the user's instructions for payment execution is acceptable.

Abstract: An apparatus comprising means for: capturing an audio scene using multiple microphones; determining that the captured audio scene has unacceptable detected noise; in dependence upon determining that the captured audio scene has unacceptable detected noise, searching both different sets of one or more microphones and different physical rotation angles of the microphones to find a combination of a first set of one or more microphones and a first physical rotation angle of the microphones that captures the audio scene with acceptable detected noise; and controlling the physical rotation angle of the microphones to be the first physical rotation angle of the microphones and capturing the audio scene using the combination of the first set of one or more microphones and the first physical rotation angle of the microphones.

Abstract: The present disclosure relates to a method of removing, by an imaging processing device, remanence artifacts from an image (fn) of a sequence of images captured by an infrared imaging device, the method comprising: generating a remanence measure for at least some pixels in the image (fn) based on a difference between the pixels values of the image (fn) and the pixel values a previous image (fn?1) of the sequence; and removing remanence artifacts from at least some pixels of the image (fn) based on a remanence estimation for each of the at least some pixels, each remanence estimation being generated based on the remanence measure and on one or more previous remanence estimations of the at least some pixels and on a model of the exponential decay of the remanence.

Abstract: An abnormality behind a shielding object is discovered. There is provided a monitoring system including a video acquirer, a detector, and a notifier. The video acquirer of the monitoring system acquires a video. The detector of the monitoring system detects entering of a target object into a blind spot generated by a shielding object in the video and appearance of the target object from the blind spot. If the target object does not appear from the blind spot even after a first time elapses since entering of the target object into the blind spot, the notifier of the monitoring system makes a notification.

Abstract: The disclosure provides a feature point position detection method and an electronic device. The method includes: obtaining a plurality of first relative positions of a plurality of feature points on a specific object relative to a first image capturing element; obtaining a plurality of second relative positions of the plurality of feature points on the specific object relative to a second image capturing element; and in response to determining that the first image capturing element is unreliable, estimating a current three-dimensional position of each feature point based on a historical three-dimensional position and the plurality of second relative positions of each feature point.

Abstract: Systems and methods are provided for detecting one or more anomalous events in video. Histogram-based noise cleansing, higher-order deep convolutional neural network-based feature extraction, instance segmentation, instance summation, difference calculation, and normalization can be used. Human-in-loop systems and methods can facilitate human decisions for anomaly detection. The decision of an anomaly event can be made by, for example, the instance difference value(s).

Abstract: Method of training an object detector for predicting centers of mass of objects projected onto a ground is provided. The method includes steps of: acquiring training images from training data set; inputting each of training images into the object detector to thereby instruct the object detector to perform object detection for the training images and thus generate object detection results including (i) information on predicted bounding boxes, corresponding to one or more ROIs, acquired by predicting each of locations of the objects in the training images and (ii) information on predicted projection points acquired by projecting the centers of mass of the objects onto the ground; and training the object detector by using object detection losses generated by referring to the object detection results and information on ground truths corresponding to the training images.

Abstract: Systems and methods for enrolling and authenticating a user in an authentication system via a user's camera of camera equipped mobile device include capturing and storing enrollment biometric information from at least one first image of the user taken via the camera of the mobile device, capturing authentication biometric information from at least one second image of the user, capturing, during imaging of the at least one second image, path parameters via at least one movement detecting sensor indicating an authentication movement of the mobile device, comparing the authentication biometric information to the stored enrollment biometric information, and comparing the authentication movement of the mobile device to an expected movement of the mobile device to determine whether the authentication movement sufficiently corresponds to the expected movement.

Abstract: In an illustrative system, a point-of-sale scanner is equipped to respond to multiple different symbologies printed on a single product. The scanner captures many frames per second, as products are swiped through a viewing volume. Each frame is decoded, yielding one or more payloads. A reconciliation module compares each newly-decoded payload against a list of payloads previously output by the module, to determine if the current payload is semantically-equivalent to a previously-output payload. If so, the previously-output payload is output again, in lieu of the just-decoded payload. If no equivalent is found, the current payload is output and added to the list for comparison against future payloads. A great number of other features and arrangements are also detailed.

Abstract: Disclosed systems and methods can include capturing the sequence of images of a monitored region that includes a sub-region of interest, processing the sequence of images using heuristics and rules of an artificial intelligence model to identify the plurality of discrete parts that are associated with a type of a unified entity, and processing the sequence of images using the heuristics and the rules of the artificial intelligence model to virtually link together a group of the plurality of discrete parts that correspond to a specific embodiment of the unified entity that is present in the sub-region of interest, wherein the heuristics and the rules of the artificial intelligence model can be developed from a training process that includes the artificial intelligence model receiving sample images delineating exemplary discrete parts on exemplary embodiments of the unified entity.

Abstract: Systems, methods and software are provided for aiding in positioning of objects in a surgical environment. A tracker is rigidly affixed to a surgical object. A camera has a field of view and senses positions of the tracker in the field of view. Controller(s) provide a zone positioned within the field of view at a location that is static relative to the field of view such that the zone is located independent of the sensed positions of the tracker. The zone defines a range of acceptable positions for the tracker relative to a position of the camera. Controller(s) acquire positions of the tracker as the surgical object is moved throughout a range of motion and enable evaluation of the positions of the tracker throughout the range of motion relative to the zone to aid in positioning of one or more of: the camera, the tracker, or the surgical object.

Abstract: A machine learning aerial wildlife survey and wounded game animal tracking process for completing accurate aerial wildlife surveys and tracking wounded game animals by machine learning and AI-supported filtering of non-relevant information is disclosed. The machine learning AI aerial wildlife survey and wounded game animal tracking process utilizes aerial vehicles, such as drones, to conduct wildlife surveys. Drones are quieter than helicopters and, therefore, have a diminished stress impact on the surrounding wildlife. In some embodiments, the machine learning AI aerial wildlife survey and wounded game animal tracking process utilizes machine learning AI filters to filter out trees and underbrush to accurately visualize wildlife and accurately count wild game.

Abstract: Systems and methods of detecting a traffic object outside of a vehicle and controlling the vehicle. The systems and methods receive perception data from a sensor system included in the vehicle, determine a focused Region Of Interest (ROI) in the perception data, scale the perception data of the at least one focused ROI, process the scaled perception data of the focused ROI using a neural network (NN)-based traffic object detection algorithm to provide traffic object detection data, and control at least one vehicle feature based, in part, on the traffic object detection data.

Abstract: A method for operating a 3D sensor system includes by an array of pixels of an imaging sensor of the 3D sensor system, generating first image data representative of reflected light from an environment, the image data having a first resolution. The method includes by processing circuitry of the 3D sensor system, generating second image data based on the first image data, the second image data having a second resolution less than the first resolution; and by the processing circuitry of the imaging sensor, determining that the second image data indicates that an object is present in the environment. The method includes responsive to the determining, providing the first image data from the 3D sensor system to one or more processors configured to generate a three-dimensional image of the environment based on the first image data.

Abstract: Provided are an object tracking system and an object tracking method.

Abstract: An early warning method and system for a regional public security management in a smart city based on the IoT are provided. The early warning method includes: sending, based on a sensing network sub-platform, a monitoring image of a target region to the management sub-platform; processing, based on a management sub-platform, the monitoring image to determine a risk index of the at least one target region; generating early warning information in response to the risk index of the target region greater than a first threshold, and sending the early warning information to the user platform through a general database of the management platform and the service platform; and obtaining a management instruction based on the user platform, and controlling, according to the management instruction, an unmanned aerial vehicle to go to the target region for monitoring.

Abstract: An apparatus for sign detection includes a point cloud analysis module, an image analysis module, a frustum comparison module, and a sign detector. The point cloud analysis module is configured to receive point cloud data associated with a geographic region and classify at least one point neighborhood in the point cloud data as planar and a sign position candidate. The image analysis module is configured to receive image data associated with the geographic region and calculate a sighting frustum from the image data. The frustum comparison module is configured to perform a comparison of the sighting frustum to the sign position candidate having at least one point neighborhood classified as planar. The sign detector is configured to provide a location for the sign detection in response to the comparison of the sighting frustum to the sign position candidate.

Abstract: An image processing apparatus 10 includes a learning model construction unit 11 that generates a divided space(s) obtained by dividing a target space into one or more spaces and constructs a learning model for recognizing an object(s) included in the divided space, a learning model management unit 12 that manages the learning model and a region forming the divided space including the object recognized by the learning model in association with each other, a space estimation unit 13 that estimates a region forming a camera recognition space captured by a camera provided in a UI device; and a detection unit 14 that selects, from among the managed learning models, a specific learning model associated with the region forming the divided space including the estimated region forming the camera recognition space, and to detect the object included in a space displayed on the UI device using the selected specific learning model.

Abstract: There is provided an imaging system. The imaging system comprising a multispectral camera configured to capture a multispectral image of an object, an RGB camera configured to capture a color image of the object, at least one storage device configured to store spectrum information for each of a plurality of labeled objects, and processing circuitry. The processing circuitry is configured to determine, based on the captured multispectral image, spectrum information associated with the object, associate, based at least in part, on the spectrum information associated with the object and the stored spectrum information for each of the plurality of objects, a label with the color image of the object, and store, on the at least one storage device, the color image and the associated label as training data.

Abstract: Various implementations disclosed herein include devices, systems, and methods that enable improved display of virtual content in computer generated reality (CGR) environments. In some implementations, the CGR environment is provided at an electronic device based on a field of view (FOV) of the device and a position of virtual content within the FOV. A display characteristic of the virtual object is adjusted to minimize or negate any adverse effects of the virtual object or a portion of the virtual object falling outside of the FOV of the electronic device.

Abstract: The present invention generally relates to a technology of detecting a stationary object in a static video, i.e., a video which is generated by a camera with a fixed view, such as a CCTV video. More specifically, the present invention relates to a technology of identifying a stationary object by use of inference information (Tensor, Activation Map) of Deep Learning object detector among objects which have been detected in a static video such as a CCTV video. According to the present invention, it is possible to lower the priority of stationary objects (e.g., parked vehicles) in processing a static video so that computing resource of the video analysis system can be effectively utilized in the process after object detection so as to enhance the performance of image analysis.

Abstract: Disclosed herein are embodiments for managing a task including one or more skills. A server stores a virtual environment, software agents configured to collect data generated when a user interacts with the virtual environment to perform the task, and a predictive machine learning model. The server generates virtual entities during the performance of the task, and executes the predictive machine learning model to configure the virtual entities based upon data generated when the user interacts with the virtual environment. The server generates the virtual environment and the virtual entities configured for interaction with the user during display by the client device, and receives the data collected by the software agents. The system displays a user interface at the client device to indicate a measurement of each of the skills during performance of the task. The server trains the predictive machine learning model using this measurement of skills during task performance.

Abstract: A method is provided for controlling a movable imaging assembly having a movable platform and an imaging device coupled to and movable relative to the movable platform. The method includes receiving user inputs that define an MIA position relative to a target and a frame position of the target within image frames captured by the imaging device. The user inputs include a horizontal distance, a circumferential position, and a horizontal distance that define the MIA position, and include a horizontal frame position and a vertical frame position that define the frame position. The method further includes predicting a future position of the target for a future time, and moving the MIA to be in the MIA position at the future time and moving the imaging device for the target to be in the frame position for an image frame captured at the future time.

Abstract: Methods and systems for touchless control of a device include receiving an image from a camera and applying a machine learning technique the image to determine a first map, the first map including a function that generates a correspondence between data associated with the image to a feature space. A second map including a representation of a user in the image can be determined based on the first map. Further, a pose of the user can be determined based on the second map. The pose of the user and a portion of a body of the user can be tracked to determine a mapping between the portion of the user's body and an input feature of a device. The input feature can be modified based on the mapping to enable a touchless interaction between the user and the device.

Abstract: An example device for retrieving media data, the device comprising: a memory configured to store scene data and image data; and one or more processors implemented in circuitry and configured to: receive data for a bitstream indicating that the bitstream includes one or more overlay images, the overlay images comprising either a single static image to be presented with scene data that remains constant while being presented frame-by-frame with frames of the scene data or an image sequence that repeats with a regular periodicity while being presented frame-by-frame with the frames of the scene data; receive the one or more overlay images from the bitstream; receive the scene data including one or more scene images; and present the scene images and the overlay images.

Abstract: A system for detecting and tracking an object that is exhibiting an anomalous behavior from a helicopter is disclosed. The system includes a search light connected to the helicopter; a camera; and a processor including an object detection module coupled to the search light and the camera, the object detection module being configured to receive a plurality of images from the camera, compare the plurality of images against a pattern database, determine the object is exhibiting the anomalous behavior and instruct the search light to point toward the object.

Abstract: Embodiments described herein provide a processing apparatus comprising compute logic to train a convolutional neural network (CNN) to perform autonomous re-localization for a service robot or mobile device. In one embodiment the apparatus comprises an image processor to process visual data received via a sensor and a general purpose graphics processing engine perform camera pose estimation for image data and generate a transformation matrix to transform positions of camera pose estimations to positions within a human readable map of the location. The images and transformed positions are uses to train the CNN to perform re-localization.

Abstract: Example apparatus disclosed herein are to process a first image of a first video segment from the image capture sensor with a machine learning algorithm to determine a first score for the first image, the machine learning algorithm to detect actions associated with images, the actions associated with labels. Disclosed example apparatus are also to determine a second score for the first video segment based on respective first scores for corresponding images in the first video segment. Disclosed example apparatus are further to determine, based on the second score, whether to retain the first video segment in the memory.

Abstract: Described are systems and methods to determine one or more body dimensions of a body based on a processing of one or more two-dimensional images that include a representation of the body. Body dimensions include any length, circumference, etc., of any part of a body, such as shoulder circumference, chest circumference, waist circumference, hip circumference, inseam length, bicep circumference, leg circumference, etc.

Abstract: A system and method of re-identifying players in a broadcast video feed are provided herein. A computing system retrieves a broadcast video feed for a sporting event. The broadcast video feed includes a plurality of video frames. The computing system generates a plurality of tracks based on the plurality of video frames. Each track includes a plurality of image patches associated with at least one player. Each image patch of the plurality of image patches is a subset of the corresponding frame of the plurality of video frames. For each track, the computing system generates a gallery of image patches. A jersey number of each player is visible in each image patch of the gallery. The computing system matches, via a convolutional autoencoder, tracks across galleries. The computing system measures, via a neural network, a similarity score for each matched track and associates two tracks based on the measured similarity.

Abstract: Various embodiments described herein provide for detection of a particular object within a scene depicted by image data by using a coarse-to-fine approach/strategy based on one or more relationships of objects depicted within the scene.

Abstract: The present disclosure provides a method for acquiring an item placing state, including: sending an acquisition request, wherein the acquisition request includes one or more association relationships, each of the association relationships includes an association relationship between a hot zone and a camera equipment, and one hot zone corresponds to one kind of item; and receiving a placing state of an item corresponding to at least one hot zone, wherein the placing state of the item corresponding to the at least one hot zone is determined according to a current image and a standard image of the at least one hot zone in response to the acquisition request. The present disclosure further provides a processing method, a system for acquiring an item placing state and a processing system.

Abstract: A system for shape dependent model identification in a point cloud includes a scanner device that captures a 3D point cloud that contains a representation of an object. The system further includes a computer that receives a sensor data, a capture time of the sensor data being substantially the same time as that of the 3D point cloud, the sensor data indicative of a position of a movable part of the object at the time of capture. The computer further computes an adjusted shape of the object from a baseline shape of the object by using the sensor data. The system further includes an object recognition module that searches for and identifies the adjusted shape of the object in the 3D point cloud.

Abstract: A vehicle drive assist apparatus includes an external environment recognizer, a traveling environment recognizer, and a processor. The traveling environment recognizer recognizes travel lane sides of dividing lines defining a travel lane as two approximate lines each in a linear form based on the image data on a traveling environment acquired by the external environment recognizer. When a static three-dimensional object has been continuously detected on or near one of dividing lines based on the image data, the processor sets a virtual approximate line by correcting the lateral position of the approximate line of the one of the dividing lines in a direction apart from the static three-dimensional object toward the middle of the travel lane by a predetermined correction amount, and sets a target travel course in the middle between the virtual approximate line and the approximate line of the other of the dividing lines.

Abstract: Provided are an electronic device for generating map data and an operating method of the electronic device. The operating method of the electronic device includes: obtaining image data of a first resolution and image data of a second resolution for each of a plurality of nodes generated while the electronic device moves; obtaining location information with respect to each of the generated nodes, by using the image data of the second resolution; generating and storing map data by matching the obtained location information with the image data of the first resolution for each node; and estimating a current location of the electronic device by using the generated map data and the image data of the first resolution.

Abstract: A head-mounted display device, including a display, one or more input devices including one or more image sensors, one or more communication devices, and a processor. The processor may output for display a mixed reality experience including one or more virtual objects. The processor may transmit imaging data to a server computing device. The processor may receive, from the server computing device, an identification of a virtual content item display opportunity, which may include a determination that the mixed reality experience and one or more physical features identified from the imaging data satisfy one or more spatial and/or temporal constraints. The processor may transmit a request for one or more virtual content items to the server computing device based on the identification. The processor may receive the one or more virtual content items from the server computing device and may output the one or more virtual content items for display.

Abstract: The present disclosure relates to a method, a device, and a program product for deploying a visual resource. In one method, a resource requirement of a vision application for the visual resource in a network system is acquired. Based on the resource requirement, the visual resource which will be called by the vision application is predicted. Based on processing capabilities of various edge devices and the visual resource in the network system, an edge device located near a terminal device in the network system is identified, wherein the terminal device is configured to run the vision application. Based on a time requirement in the resource requirement, the visual resource is deployed to the edge device. Further, a corresponding device and a corresponding program product are provided.

Abstract: This application describes a method of determining a position and orientation of an object having a plurality of fiducials attached thereto. The method includes the steps of forming images of the plurality of fiducials on a sensitive surface of a sensor and determining a 2D location of each of the images of the plurality of fiducials on the sensitive surface. Information comprising 3D positions of the plurality of fiducials in a coordinate system of the object is then retrieved and each of the 2D locations of the plurality of images is associated with the 3D position of the same fiducial. A position and orientation of the object with respect to the sensitive surface of the sensor is then determined based in part on the 2D locations of the images and the 3D positions of the fiducials.

Abstract: Macroblocking artifacts are assessed in an encoded video. Edges are detected and edge strengths are computed at macroblock boundaries in each decoded frame of the video. The detected edges are paired at horizontal or vertical sides of each macroblock to identify macroblock edge pairs. A macroblocking level of the frame is identified according to the macroblock edge pairs. For instance, for each of the macroblock edge pairs, the edges of the pair are identified as being macroblocking edges if edge strengths of both sides of the pair exceed a significance threshold, and the macroblocking level of the frame is determined by aggregating the macroblocking edges in the frame.

Abstract: An individual identification apparatus that identifies an individual product having a pattern of irregularities randomly formed on a surface thereof includes an imaging unit and an extracting unit. The imaging unit is configured to acquire an image obtained by capturing a date mark formed on the product. The extracting unit is configured to extract a feature value related to the pattern of the irregularities from the image as data identifying the individual product.

Abstract: Apparatuses, methods, and articles of manufacture are disclosed. An example apparatus includes processor circuitry to assign a location value hyperdimensional vector (HDV) to a location in an image of a first patch of one or more pixels, assign at least a first channel HDV to the first patch, determine at least one pixel intensity value HDV for each of the one or more pixels in the first patch, bind together each of the pixel intensity value HDVs into at least one patch intensity value HDV, bind together the at least first channel HDV and the at least one patch intensity value HDV to produce a patch consensus intensity HDV, and generate a first hyperdimensional representation patch value HDV of the first patch by binding together at least a combination of the patch consensus intensity HDV and the location value HDV.

Abstract: A system including a server arrangement and a programming interface in communication with external applications are provided.