Abstract: Disclosed herein are embodiments of systems, methods, and products comprise an analytic server, which provides a terrain segmentation and classification tool for synthetic aperture radar (SAR) imagery. The server accurately segments and classifies terrain types in SAR imagery and automatically adapts to new radar sensors data. The server receives a first SAR imagery and trains an autoencoder based on the first SAR imagery to generate learned representations of the first SAR imagery. The server trains a classifier based on labeled data of the first SAR imagery data to recognize terrain types from the learned representations of the first SAR imagery. The server receives a terrain query for a second SAR imagery. The server translates the second imagery data into the first imagery data and classifies the second SAR imagery terrain types using the classifier trained for the first SAR imagery. By reusing the original classifier, the server improves system efficiency.

Abstract: Data for training a machine learning algorithm to detect airborne objects is generated by capturing background images using a camera aboard an aerial vehicle, and generating a trajectory of a synthetic object, such another aerial vehicle, in three-dimensional space. The trajectory is projected into an image plane of the camera, determined from a pose of the camera calculated using inertial measurement unit data captured by the aerial vehicle. Images of the synthetic object may be rendered based on locations of the trajectory in the image plane at specific times. Pixel-accurate locations for the rendered images may be determined by calculating a homography from consecutive images captured using the camera, and adjusting locations of the trajectory using the homography. The rendered images may be blended into the images captured by the camera at such locations, and used to train a machine learning algorithm.

Abstract: An autonomous personal companion utilizing a method of object identification that relies on a hierarchy of object classifiers for categorizing one or more objects in a scene. The classifier hierarchy is composed of a set of root classifiers trained to recognize objects based on separate generic classes. Each root acts as the parent of a tree of child nodes, where each child node contains a more specific variant of its parent object classifier. The method covers walking the tree in order to classify an object based on more and more specific object features. The system is further comprised of an algorithm designed to minimize the number of object comparisons while allowing the system to concurrently categorize multiple objects in a scene.

Abstract: A method and system for improving damage assessment by automatic measurement of virtual objects within an augmented reality (AR) representation of a physical environment are disclosed. A user interacts with a mobile computing device to position and resize virtual objects within a virtual space corresponding to a physical environment, which is presented to the user as an AR environment generated by the mobile computing device. The virtual objects are positioned and sized to match damaged physical objects within the physical environment. The sizes of the physical objects are automatically determined using the virtual sizes of the virtual objects, which physical sizes are further used to determine the extent of damage.

Abstract: Example implementations include a method, apparatus and computer-readable medium for controlling a camera, comprising receiving a video sequence of a scene. The method includes determining one or more scene description metadata in the scene from the video sequence. The method includes identifying one or more scene object types in the scene based on the one or more scene description metadata. The method includes determining one or more rules based on one or both of the scene description metadata or the scene object types, each rule configured to generate an event based on a detected object following a rule-specific pattern of behavior. The method includes applying the one or more rules to operation of the camera.

Abstract: Systems and techniques are generally described for semantically segmenting videos. In various examples, a selection of a first video may be received. A first query to segment the first video into segments related to a first category of content may be received. A first plurality of segments related to the first category may be determined. In some examples, time code data representing the first plurality of segments may be sent to a remote computing device, wherein a video player of the remote computing device is effective to play the first plurality of segments based at least in part on the time code data.

Abstract: An apparatus including an interface and a processor. The interface may be configured to receive pixel data generated by a capture device. The processor may be configured to generate video frames in response to the pixel data, perform computer vision operations on the video frames to detect objects, perform a classification of the objects detected based on characteristics of the objects, determine whether the classification of the objects corresponds to a user-defined event and a user-defined identity and generate encoded video frames from the video frames. The encoded video frames may comprise a first sample of the video frames selected at a first rate when the user-defined event is not detected and a second sample of the video frames selected at a second rate while the user-defined event is detected. The video frames comprising the user-defined identity without a second person may be excluded from the encoded video frames.

Abstract: Systems and methods are provided herein for recording a portion of content of a sports game. A request to record the portion of the content, which specifies game clock time criteria, is received by user equipment. During transmission of the content, frames of the content including a game progress graphic are analyzed to determine time values representing progress points of the sports game. In response to determining that a first time value representing a first progress point of the sports game matches the game clock time criteria of the request, the user equipment begins to record the portion of the content. In response to determining that a second time value does not match the game clock time criteria of the request, the user equipment stops the recording of the portion of the content and stores the recorded portion of the content.

Abstract: The invention relates to a method for detecting the heating activity in objects or materials, based on thermal only or thermal and visual data images. The method is based on a physics-based model of the underlying heating phenomena within materials or objects, while taking into account disturbing factors of natural phenomena such as weather conditions and day and night cycle. The invention also relates to a corresponding system for detecting the heating activity in objects or materials.

Abstract: The present invention provides a processing apparatus (10) including: a detection unit (11) that detects that a notification apparatus is operated; an acquisition unit (12) that acquires, when it is detected that the notification apparatus is operated, at least one of an image generated by a camera and a sound collected by a microphone; a decision unit (13) that decides whether at least one of the image and the sound satisfies a notification condition; and an output unit (14) that outputs, when it is decided that the notification condition is satisfied, notification information indicating that the notification apparatus is operated.

Abstract: The invention relates to a monitoring device (10) for recognizing persons in a monitoring region (2), the monitoring region (2) being video-monitored by means of at least one camera (6) and the camera (6) being designed to provide monitoring images (7) to the monitoring device (10) as video data, the monitoring device comprising: —a feature determination apparatus (13), the feature determination apparatus (13) being designed to determine a feature vector (19) for each object in at least one of the monitoring images (7); —a person recognition apparatus (16), the person recognition apparatus (16) being designed to detect in the monitoring images (7) a person to be recognized (11), on the basis of the determined feature vector and/or the determined feature vectors (19) of the feature determination apparatus (13) and/or a combined feature vector (18); —an association apparatus (14), the association apparatus (14) being designed to determine a feature vector (19) for each person to be recognized (11) and each asso

Abstract: An approach is disclosed for detecting cornering spots capable of facilitating crowd control by limiting a mobility of a crowd. The approach involves, for example, collecting satellite, aerial, and/or street-level imagery associated with one or more geographic features of a geographic area. The approach also involves determining at least one cornering spot along with one or more attributes of the cornering spot characterizing the effectiveness of the cornering spot to assist in crowd control. Cornering spot data can be stored in a geographic database and/or displayed in an application on user equipment.

Abstract: The present disclosure discloses a perception data detection method and apparatus. The specific implementation scheme is: acquiring labeled data and perception data, where the labeled data includes a labeled position and a labeled type of at least one first obstacle, and the perception data includes a perception position and a perception type of at least one second obstacle; performing, according to a negative sample in the labeled data, rough filtering on the second obstacle in the perception data to obtain a third obstacle remaining after the rough filtering, where the negative sample is a non-physical obstacle; determining a matching relationship between the third obstacle and the negative sample, and determining the negative sample having the matching relationship with the third obstacle as a target obstacle; and determining, according to the number of the target obstacle and the number of the first obstacle, a detection result of the perception data.

Abstract: An object recognition device of the present disclosure divides a reflection intensity image and a background light image acquired from a light sensor into the same number of subregions. The object recognition device calculates a feature amount for partial image data of each of the subregions of the reflection intensity image and partial image data of each of the subregions of the background light image that have been divided. The object recognition device compares the feature amounts calculated for the partial image data of the reflection intensity image and the partial image data of the background light image in the same one of the subregions and selects the feature amount with which an object is more easily recognized as the selected partial image data. The object recognition device recognizes the object based on overall image data configured by the selected partial image data pieces that have been selected.

Abstract: The present disclosure provides a system, a method and an apparatus for object identification, capable of solving the problem in the related art that a system for centralized control and management of unmanned vehicles may not be able to identify an object effectively. The system for object identification includes a sensing device, a control device and one or more unmanned vehicles.

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 driving support method including: detecting a first boundary point group including boundary points forming a lane boundary line, using a sensor mounted on a vehicle; converting a coordinate system of the first boundary point group to the same coordinate system as a coordinate system of map data; and performing matching between a first point group constituted by boundary points not close to each other in either one of a second boundary point group including boundary points forming a lane boundary line in the map data and the first boundary point group and the other of the first boundary point group and the second boundary point group.

Abstract: A method and apparatus used for extracting a feature point of an environmental target, which relate to the field of vehicles. The method comprises: acquiring the position of each corner point of an environmental target; and determining a feature point of the environmental target according to the position of each corner point of the environmental target. Thus, the problem wherein target identification is not precise may be solved, which is particularly suitable for the identification of a large target.

Abstract: System and techniques for vehicle environment modeling with a camera are described herein. A device for modeling an environment comprises: a hardware sensor interface to obtain a sequence of unrectified images representative of a road environment, the sequence of unrectified images including a first unrectified image, a previous unrectified image, and a previous-previous unrectified image; and processing circuitry to: provide the first unrectified image, the previous unrectified image, and the previous-previous unrectified image to an artificial neural network (ANN) to produce a three-dimensional structure of a scene; determine a selected homography; and apply the selected homography to the three-dimensional structure of the scene to create a model of the road environment.

Abstract: A method and apparatus to recognize transported passengers and goods are disclosed herein. One example includes an apparatus comprising a processor unit on a vehicular entity, a communication component coupled to the processor unit, and a memory portion associated to the processor unit and structured to store information and data received through the communication component about at least one of passengers, luggage and/or goods on the vehicular entity, with the communication component being activated by a presence of the at least one of the passengers, luggage and/or goods on the vehicular entity.

Abstract: An anti-counterfeiting face detection method, device and multi-lens camera are disclosed. The anti-counterfeiting face detection method comprises: acquiring a depth image, an infrared image and an RGB image by using a TOF camera and an RGB camera; analyzing the RGB image through a preset face detection algorithm to determine an RGB face region of a face in the RGB image and position information of the RGB face region; determining a depth face region of the face in the depth image and an infrared face region of the face in the infrared image based on the position information of the RGB face region; determining that the face passes the detection when the depth face region, the infrared face region and the RGB face region meet corresponding preset rules respectively.

Abstract: Methods, systems, and programs are presented for simultaneous recognition of objects within a detection space utilizing three-dimensional (3D) cameras configured for capturing 3D images of the detection space. One system includes the 3D cameras, calibrated based on a pattern in a surface of the detection space, a memory, and a processor. The processor combines data of the 3D images to obtain pixel data and removes, from the pixel data, background pixels of the detection space to obtain object pixel data associated with objects in the detection space. Further, the processor creates a geometric model of the object pixel data, the geometric model including surface information of the objects in the detection space, generates one or more cuts in the geometric model to separate objects and obtain respective object geometric models, and performs object recognition to identify each object in the detection space based on the respective object geometric models.

Abstract: A method for detecting and labeling a target object in a 2D image includes receiving a plurality of 2D images from a visual sensor, manually marking points of the target object on each of the 2D images, generating from the 2D images a 3D world coordinate system of the environment surrounding the target object, mapping each of the marked points on the 2D images to the 3D world coordinate system using a simultaneous localization and mapping (SLAM) engine, automatically generating a 3D bounding box covering all the marked points mapped to the 3D world coordinate system, mapping the 3D bounding box to each of the 2D images, generating a label for the target object on each of the 2D images using a machine learning object detection model, and training the machine learning object detection model based on the generated label for the target object.

Abstract: An image is acquired by a camera. The image has a first set of characters and a second set of characters. The first set of characters are classified as an identifier. The second set of characters are classified as data associated with the identifier. The image is divided to create an image segment. The image segment includes the first set of characters and not the second set of characters. The first set of characters are decoded in the image segment to generate a first character string. The second set of characters are decoded to generate a second character string. The first character string is linked to the second character string based on classifying the first set of characters as the identifier and the second set of characters as the data associated with the identifier.

Abstract: A method for splitting text line images includes receiving a text line image and identifying that the text line image comprises a plurality of zones, wherein each zone includes text whose font differs from the text of adjacent zones. The method further includes selecting a splitting position between multiple zones and splitting the text line image at the splitting position into a plurality of image segments, wherein each image segment contains at least one zone of the text line image and performing optical character recognition on each image segment to recognize a text segment of the image segment. In certain implementations, the method further includes generating one or more confidence measurements and selecting a splitting position that corresponds to a large gradient in the confidence measurement.

Abstract: A series of steps may be performed to automatically extract structured data from an image. First, anchor points may be extracted from the image, representing areas of the image that potentially contain information of interest. The arrangement of anchor points may be used to identify a template. A transform may be generated, to facilitate mapping between particular points in the selected template and corresponding points in the image. The transform may then be used to automatically read visual information from the image and extract structured data from the visual information.

Abstract: Audio distortion compensation methods to improve accuracy and efficiency of audio content identification are described. The method is also applicable to speech recognition. Methods to detect the interference from speakers and sources, and distortion to audio from environment and devices, are discussed. Additional methods to detect distortion to the content after performing search and correlation are illustrated. The causes of actual distortion at each client are measured and registered and learnt to generate rules for determining likely distortion and interference sources. The learnt rules are applied at the client, and likely distortions that are detected are compensated or heavily distorted sections are ignored at audio level or signature and feature level based on compute resources available. Further methods to subtract the likely distortions in the query at both audio level and after processing at signature and feature level are described.

Abstract: An image is processed to determine semantic data about what is depicted in that image. The semantic data provides information about location in the image and semantic category of an object depicted within the image. The semantic categories may include “background”, “face”, “text”, “clothing”, “exercise”, and so forth. The semantic data may then be used to facilitate distribution of image data while limiting the information shared. For example, the semantic data may indicate the placement and position of a user exercising in first video data. Using the semantic data, second video data may be produced that obscures or replaces parts of the image that do not depict the user exercising. The second video data may then be used for providing feedback to the user, while preventing disclosure of other people, background, and so forth that are depicted in the first video data.

Abstract: A computer-implemented tool for automated classification and interpretation of documents, such as life science documents supporting clinical trials, is configured to perform a combination of raw text, document construct, and image analyses to enhance classification accuracy by enabling a more comprehensive machine-based understanding of document content. The combination of analyses provides context for classification by leveraging relative spatial relationships among text and image elements, identifying characteristics and formatting of elements, and extracting additional metadata from the documents as compared to conventional automated classification tools.

Abstract: Provided are a computer program product, system, and method for pre-processing a table in a document for natural language processing. A table in a document is parsed to extract column headers, row headers, and data cells, which are processed to determine an initial set of a main element comprising an entity whose value is to be extracted, a conditional element that refines the entity, and a value element comprising a value for the entity. A user selection is received of at least one of the column headers, row headers, and data cells for at least one of the main element, conditional element, and the value element in the initial set to produce a modified set of the main element, conditional element, and value element. The modified set is provided to a natural language processing engine to perform natural language processing of the document including the table, using the modified set.

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

Abstract: A display module and a manufacturing method thereof are provided. The display module includes a display panel and a fingerprint identification module disposed in the display panel, wherein the display panel includes a first substrate, a second substrate located above the first substrate, and a functional layer prepared and disposed above the second substrate, and the fingerprint identification module is disposed between the first substrate and the second substrate. The present application realizes a technical effect of a simplified manufacturing process of the display module and an overall simple structure through integrating the fingerprint identification module into the display panel.

Abstract: A multiple-lens optical fingerprint reader for reading fingerprints through a display has a spacer; and multiple microlenses with concave and convex surfaces in a microlens array, each microlens of multiple lenses focuses light arriving at that microlens from a finger adjacent the display through the spacer forms an image on associated photosensors on a photosensor array of an image sensor integrated circuit. A method of verifying identity of a user includes illuminating a finger of the user with an OLED display; focusing light from the finger through arrayed microlenses onto a photosensor array, reading the array into overlapping electronic fingerprint images; extracting features from the overlapping fingerprint images or from a stitched fingerprint image, and comparing the features to features of at least one user in a library of features and associated with one or more fingers of one or more authorized users.

Abstract: A display panel and a display device are provided, the display panel has a texture touch surface, and includes a driving circuit layer, a light source array, an image sensor array, and a black matrix layer. The light source array includes a plurality of light sources, the image sensor array includes a plurality of image sensors, the black matrix layer includes a plurality of first light-transmitting openings and a plurality of second light-transmitting openings. The driving circuit layer includes a plurality of light-transmitting portions, and each of the plurality of first light-transmitting openings is arranged corresponding to at least one of the plurality of light-transmitting portions, and in a first light-transmitting opening and a light-transmitting portion that are arranged correspondingly, a plane size of the first light-transmitting opening in a direction parallel to the surface of the display panel is smaller than a plane size of the light-transmitting portion.

Abstract: A method of detecting a biometric feature with an electronic device and the method includes the following steps. Firstly, a detection region of the electronic device is provided, and the electronic device includes a plurality of first color pixels, a plurality of second color pixels, and a sensor module. Then, a first color light and a second color light are respectively generated by turning on at least a portion of the first color pixels and at least a portion of the plurality of second color pixels in the detection region. Next, a first area and a second area are simultaneously generated by the first color and the second color light, wherein the first area and the second area are overlapped with the detection region, and the sensor module is overlapped with the detection region. Finally, a biometric feature is determined.

Abstract: A sensing device includes a first substrate, a first sensing element, a first light-shielding layer, a second light-shielding layer and an insulating layer. The first sensing element is disposed on the first substrate. The first light-shielding layer is disposed on the first sensing element and has a first opening, wherein the first opening is completely overlapped with the first sensing element. The second light-shielding layer is disposed on the first light-shielding layer and includes an upper light-shielding part and a lateral light-shielding part, wherein the upper light-shielding part is overlapped with the first light-shielding layer and has a second opening, and the lateral light-shielding part is separated from the upper light-shielding part. The insulating layer is disposed between the first light-shielding layer and the second light-shielding layer, and the lateral light-shielding part covers a sidewall of the insulating layer.

Abstract: A method of processing a fingerprint image in an electronic apparatus includes: obtaining an original fingerprint image by sensing a fingerprint of a user; estimating a spatial change trend of original contrast values in the original fingerprint image; generating a reference contrast map based on the estimated spatial change trend; normalizing a contrast distribution of the original fingerprint image based on the reference contrast map, and generating a normalization fingerprint image having a normalized contrast distribution.

Abstract: A processor-implemented method includes: generating a preprocessed infrared (IR) image by performing first preprocessing based on an IR image including an object; generating a preprocessed depth image by performing second preprocessing based on a depth image including the object; and determining whether the object is a genuine object based on the preprocessed IR image and the preprocessed depth image.

Abstract: An object recognition system of the present disclosure includes: a light source section that irradiates a subject with dot light having a predetermined pattern; an event detection sensor that receives the dot light having the predetermined pattern reflected by the subject and detects, as an event, that a change in luminance of a pixel exceeds a predetermined threshold; and a signal processor that performs, in a case where a plurality of successive pixels in a pixel array section of the event detection sensor detects occurrence of an event in a certain period, processing of removing the event as noise, the plurality of successive pixels being equal to or greater than a predetermined number of pixels.

Abstract: A method includes receiving a set of video frames that correspond to a video, including a first video frame and a second video frame that each include a face, wherein the second video frame is subsequent to the first video frame. The method further includes performing face tracking on the first video frame to identify a first face resampling keyframe and performing face tracking on the second video frame to identify a second face resampling keyframe. The method further includes deriving an interpolation amount. The method further includes determining a first interpolated face frame based on the first face resampling keyframe and the interpolation amount. The method further includes determining a second interpolated face frame based on the second face resampling keyframe and the interpolation amount. The method further includes rendering an interpolated first face and an interpolated second face. The method further includes displaying a final frame.

Abstract: A first image showing a non-frontal view is received. CNN outputs generated based on the first image are concatenated to generate a concatenated CNN output. The concatenated CNN output is input to a first encoder to generate a first value for a first statistical property and a first value for a second statistical property. Configural information is generated based on the first image. The configural information is input to a second encoder to generate a second value for the first statistical property and a second value for the second statistical property. Vectors are generated based on the first and second values for the first statistical property, and the first and second values for the second statistical property. A latent vector is generated based on the vectors. The latent vector is input to a decoder to generate a second image showing a frontal view.

Abstract: An application running on a user's mobile communication device photographically captures images of a code image. The code image may be permanently displayed at the transport location, or may be provided on a vehicle temporarily at the transport location. The displayed code image encodes travel data including ticket prices of a travel service from the transport location, and the application decodes the travel data from the captured images. The user can use the application to purchase a travel ticket on the travel service.

Abstract: A technique for controlling access to one or more attractions is achieved using a number of access keys, each being issued to one or more users. An electronic queue management part manages a virtual queue in respect of each attraction and receives electronic requests for attraction access, each request relating to an access key and being for the users associated with it to access a particular attraction. Receipt of each request causes the respective users to be added to a corresponding virtual queue. A time at which each group of users reaches the front of the virtual queue and can access the attraction is determined. The users access the attractions by presenting an access key to an access control part, in communication with the electronic queue management part. Only a user presenting an access key at the correct time for accessing the attraction is allowed access to the attraction.

Abstract: A method for determining a status of one of multiple machine components of a machine on the basis of a digital machine model, wherein the digital machine model describes the multiple machine components, includes the steps of: determining component manufacturer data of the multiple machine components; determining machine manufacturer data of the multiple machine components; determining machine operator data of the multiple machine components; and determining the status of the one of the multiple machine components by linking the determined component manufacturer data, the determined machine manufacturer data and the determined machine operator data.

Abstract: An information processing method performed using a computer includes: obtaining first vehicle information from a vehicle that is a monitoring target of a monitor, the first vehicle information indicating at least one of a running state and an external state of the vehicle; determining a monitoring priority level of the vehicle according to a degree of request for monitoring the vehicle by the monitor, the degree being based on the first vehicle information; generating presentation information for monitoring the vehicle, based on the monitoring priority level; and causing a presentation device to output the presentation information.

Abstract: An information providing method is performed in an information providing system. The information providing method includes: acquiring pieces of speed information of a vehicle in association with identification information of an in-vehicle device from the in-vehicle device via roadside antennas, each of the pieces of speed information having been stored in the in-vehicle device each time the vehicle moves a prescribed distance before the vehicle passes by the roadside antennas; and causing an information display device to display evaluation information in association with the identification information, the evaluation information indicating a frequency of occurrence of sudden acceleration or deceleration events of the vehicle obtained from a proportion of differences between calculation values outside a threshold range, the calculation values being calculated on the basis of the pieces of speed information in a prescribed period corresponding to the pieces of speed information stored in the in-vehicle device.

Abstract: An example operation may include one or more of receiving, at a server, sensor data from one or more sensors disposed on a vehicle, receiving, at the server, additional sensor data from a computing device operating inside the vehicle, determining the sensor data and the additional sensor data correspond to the vehicle's operational status, determining whether one or more of the sensor data and the additional sensor data exceed one or more thresholds, and when one or more of the sensor data and the additional sensor data exceed the one or more thresholds, providing a value to the vehicle.

Abstract: Embodiments of the invention include a vehicle telematics system including a telematics device and a remote server system, wherein the telematics device obtains sensor data from at least one sensor installed in a vehicle, calculates peak resultant data based on the sensor data, generates crash score data based on the peak resultant data and a set of crash curve data for the vehicle, and provides the obtained sensor data when the crash score data exceeds a crash threshold to the remote server system and the remote server system obtains vehicle sensor data and vehicle identification data from the vehicle telematics device, calculates resultant change data and absolute speed change data based on the obtained sensor data and/or the vehicle identification data, and generates crash occurred data when the resultant change data exceeds a first threshold value and when the absolute speed change data is below a second threshold value.

Abstract: Systems and methods for evaluating and transmitting combined external data from one or more assets are described herein. An example method may include collecting, by a data processing device communicatively coupled to a central data portal, sensor data from one or more assets, processing, by the data processing device, the sensor data to evaluate status data concerning status of the one or more assets, transmitting, by the data processing device, the status data to the central data portal, and storing and visualizing, by the central data portal, the status data. The data processing device can be co-located with one of the assets. The assets may be selected from a building, a room, outdoor location, a vehicle, a person, an indoor location, and an outdoor location.

Abstract: A fault diagnostic device 80 includes an input unit 81 and a generation unit 82. The input unit 81 receives input of observation data of a vehicle operating at a predetermined speed. The generation unit 82 extracts time series features of the observation data as features indicating a normal condition, and generates a feature master indicating the normal condition of the vehicle based on the extracted features.