Patents Issued in April 14, 2022
-
Publication number: 20220114786Abstract: This disclosure describes systems, methods, and devices related to generating a three-dimensional full-body reconstruction using image data from a single camera. A method may include receiving first point cloud data from the camera, the point cloud data representing a person; identifying a first human body template, the first human body template representing body joints; generating, based on a comparison of the first human body template to the first point cloud data, parameters associated with the body joints; and generating, based on the parameters, a second human body template representing the person.Type: ApplicationFiled: December 22, 2021Publication date: April 14, 2022Inventors: Guoqing Zhang, Bennett Ng
-
Publication number: 20220114787Abstract: An improved virtual environment creation and testing process can be achieved by a combination of spatial partitioning and reverse tree generation. The reverse tree may be representative of the virtual environment and may be generated starting from a smallest portion or zone of the virtual environment (represented as a leaf node) and expanding up towards a root node representative of the entire virtual environment. Advantageously, the system can add new zones to the virtual environment and representative tree data structure that are external to the existing virtual environment without generating a new tree data structure. Thus, the computing resources utilized by the system disclosed herein may be significantly reduced compared to existing processes while improving the flexibility of the spatial partitioning and tree generation process thereby enabling spatial partitioning to be performed in real or near real time as a developer authors the virtual environment.Type: ApplicationFiled: October 13, 2020Publication date: April 14, 2022Inventor: Alexander Loodin Ek
-
Publication number: 20220114788Abstract: An augmented reality/mixed reality system that provides an immersive user experience. That experience is provided with increased speed of update with low computational resources for occlusion data representing a user's hand that can be used to occlude virtual objects. The hand occlusion data are generated by computing a hand mesh from live depth sensor data. A small amount of data is processed by masking live depth data with a model in which a hand is simply represented by multiple segments identified from key-points. The hand occlusion data may be generated by predicting changes in a hand pose between a time of capture of the depth data and the time when the hand mesh will be used for occlusion processing. The hand mesh may be distorted to represent the hand in the predicted pose.Type: ApplicationFiled: December 20, 2021Publication date: April 14, 2022Applicant: Magic Leap, Inc.Inventor: David Geoffrey Molyneaux
-
Publication number: 20220114789Abstract: A virtual and real image fusion method is disclosed. The method comprises the following operations: obtaining a picture of a three dimensional space by a first camera, in which the picture comprises a screen picture and a tag picture of an entity tag and the screen picture is projected on the entity tag; obtaining a corresponding point data of the entity tag on the screen picture according to the picture by a processor; obtaining a spatial correction parameter according to the corresponding point data by the processor; and displaying an image on the screen picture according to the spatial correction parameter by the processor.Type: ApplicationFiled: January 13, 2021Publication date: April 14, 2022Inventors: Li-Ting CHEN, Ming-Fang WENG
-
Publication number: 20220114790Abstract: A hybrid implementation enables sharing the processing of 3D data locally and remotely based on processing and bandwidth factors. The hybrid implementation is flexible in determining what information to process locally, what information to transmit to a remote system, and what information to process remotely. Based on the available bandwidth, computing power/availability locally and computing power/availability remotely, the hybrid implementation is able to direct the processing of the data. By performing some of the processing locally and some of the processing remotely, more efficient processing is able to be implemented.Type: ApplicationFiled: April 20, 2021Publication date: April 14, 2022Inventor: Nikolaos Georgis
-
Publication number: 20220114791Abstract: A system aligns a 3D model of an environment with image frames of the environment and generates a visualization interface that displays a portion of the 3D model and a corresponding image frame. The system receives LIDAR data collected in the environment and generates a 3D model based on the LIDAR data. For each image frame, the system aligns the image frame with the 3D model. After aligning the image frames with the 3D model, when the system presents a portion of the 3D model in an interface, it also presents an image frame that corresponds to the portion of the 3D model.Type: ApplicationFiled: July 2, 2021Publication date: April 14, 2022Inventors: Michael Ben Fleischman, Jeevan James Kalanithi, Gabriel Hein, Elliott St. George Wilson Kember
-
Publication number: 20220114792Abstract: The MR display device includes a controller and a display unit. The controller recognizes a reality object from a reality video imaged by a camera and links a predetermined virtual object to the reality object based on an operation of an experiencing person. The display unit displays a video of the linked virtual object. The controller acquires a recognition result of a reality object generated by the other MR display device and data of the linked virtual object, via a communication unit, synthesizes the acquired data and the own data, and displays a video obtained by the synthesis on the display unit. In addition, the controller allows an edit of the virtual object linked to the reality object on the video displayed on the display unit, based on an operation of the experiencing person.Type: ApplicationFiled: February 6, 2019Publication date: April 14, 2022Inventors: Osamu KAWAMAE, Masuo OKU
-
Publication number: 20220114793Abstract: A system includes an augmented virtual reality (AVR) object creation engine, an AVR object enhancement engine, an AVR object positioning engine, and an AVR media authoring engine. The AVR object creation engine is configured to convert real world data into one or more AVR objects. The AVR object enhancement engine is configured to enhance the one or more AVR objects to include at least one of processed data visualization and multiuser controls. The AVR object positioning engine is configured to position the enhanced one or more AVR objects in a virtual space-time. The AVR media authoring engine is configured to make available, as AVR media, a scene tree including the virtual space-time in which the enhanced one or more AVR objects are positioned.Type: ApplicationFiled: September 13, 2021Publication date: April 14, 2022Applicant: Flow Immersive, Inc.Inventors: Jason Marsh, Aleksei Karpov, Timofey Biryukov
-
Publication number: 20220114794Abstract: Methods, computer-readable media, and apparatuses for presenting medical records associated with a body part of person via an augmented reality device are described. For example, a processing system including at least one processor may identify at least one body part of a person in a visual data feed of an augmented reality device, obtain based on the identifying at least a first medical record of the person that is associated with the at least one body part, obtain at least a second medical record of at least one relative of the person that is associated with the at least one body part, and present, via the augmented reality device, at least the first medical record and the least the second medical record.Type: ApplicationFiled: December 20, 2021Publication date: April 14, 2022Inventors: Joseph Soryal, Naila Jaoude, Samuel N. Zellner
-
Publication number: 20220114795Abstract: In one implementation, a method includes: instantiating a first objective-effectuator (OE) associated with first attributes and a second OE associated with second attributes into a synthesized reality (SR) setting, wherein the first OE is encapsulated within the second OE; providing a first objective to the first OE based on the first and second attributes; providing a second objective to the second OE based on the second attributes, wherein the first and second objectives are associated with a time period between a first and second temporal points; generating a first set of actions for the first OE based on the first objective and a second set of actions for the second OE based on the second objective; and rendering for display the SR setting for the time period including the first set of actions performed by the first OE and the second set of actions performed by the second OE.Type: ApplicationFiled: December 21, 2021Publication date: April 14, 2022Inventors: Ian M. Richter, Michael J. Rockwell, Amritpal Singh Saini, Olivier Soares
-
Publication number: 20220114796Abstract: In one implementation, a method of including a person in a CGR experience or excluding the person from the CGR experience is performed by a device including one or more processors, non-transitory memory, and a scene camera. The method includes, while presenting a CGR experience, capturing an image of scene; detecting, in the image of the scene, a person; and determining an identity of the person. The method includes determining, based on the identity of the person, whether to include the person in the CGR experience or exclude the person from the CGR experience. The method includes presenting the CGR experience based on the determination.Type: ApplicationFiled: December 21, 2021Publication date: April 14, 2022Inventors: Daniel Ulbricht, Amit Kumar K C, Angela Blechschmidt, Chen-Yu Lee, Eshan Verma, Mohammad Haris Baig, Tanmay Batra
-
Publication number: 20220114797Abstract: A method includes: recording a series of frames; recording a set of motion data representing motion of the mobile device; detecting relative positions of a 3D constellation of objects based on the series of frames and the set of motion data; generating classifications of the 3D constellation of objects by calculating a classification of each object in a set of object classes; calculating a transform aligning the 3D constellation of objects with a 3D localization map; accessing a set of augmented reality assets defined by the 3D localization map; calculating a position of the mobile device relative to the 3D localization map based on the transform and the set of motion data; and rendering the set of augmented reality assets based on positions of the set of augmented reality assets in the 3D localization map and based on the position of the mobile device in the 3D localization map.Type: ApplicationFiled: December 20, 2021Publication date: April 14, 2022Inventors: Mark Stauber, Jaeyong Sung, Devin Haslam, Amichai Levy
-
Publication number: 20220114798Abstract: Methods and systems are disclosed for displaying an augmented reality virtual object on a multimedia device. One method comprises detecting, in an augmented reality environment displayed using a first device, a virtual object; detecting, within the augmented reality environment, a second device, the second device comprising a physical multimedia device; and generating, at the second device, a display comprising a representation of the virtual object.Type: ApplicationFiled: December 21, 2021Publication date: April 14, 2022Inventors: Kevin GORDON, Charlotte SPENDER
-
Publication number: 20220114799Abstract: A three-dimensional model generation method includes: acquiring first sphere position information of each first sphere of multiple first spheres in a camera coordinate system based on a first image including a first object, where the first spheres are configured to represent different parts of the first object respectively; generating a first rendered image based on the first sphere position information of the first spheres; obtaining gradient information of the first rendered image based on the first rendered image and a semantically segmented image of the first image; and adjusting the first sphere position information of the first spheres based on the gradient information of the first rendered image, and generating a three-dimensional model of the first object by utilizing the adjusted first sphere position information of the first spheres.Type: ApplicationFiled: December 21, 2021Publication date: April 14, 2022Applicant: SHANGHAI SENSETIME INTELLIGENT TECHNOLOGY CO., LTD.Inventors: Min WANG, Feng QIU, Wentao LIU, Chen QIAN, Lizhuang MA
-
Publication number: 20220114800Abstract: In various examples, sensor data—such as masked sensor data—may be used as input to a machine learning model to determine a confidence for object to person associations. The masked sensor data may focus the machine learning model on particular regions of the image that correspond to persons, objects, or some combination thereof. In some embodiments, coordinates corresponding to persons, objects, or combinations thereof, in addition to area ratios between various regions of the image corresponding to the persons, objects, or combinations thereof, may be used to further aid the machine learning model in focusing on important regions of the image for determining the object to person associations.Type: ApplicationFiled: December 20, 2021Publication date: April 14, 2022Inventors: Parthasarathy Sriram, Fnu Ratnesh Kumar, Anil Ubale, Farzin Aghdasi, Yan Zhai, Subhashree Radhakrishnan
-
Publication number: 20220114801Abstract: The present disclosure relates to systems and methods for image processing. The system may obtain at least one image of an object. For each of the at least one image, the system may determine a recognition result of the image. The recognition result may include an image type of the image, a type of a lesion in the image, a region of the lesion in the image, and/or an image feature of the image. Further, the system may process the at least one image of the object based on at least one recognition result corresponding to the at least one image.Type: ApplicationFiled: December 17, 2021Publication date: April 14, 2022Applicant: SHANGHAI UNITED IMAGING HEALTHCARE CO., LTD.Inventors: Liang XU, Juan FENG, Jun XIANG, Na ZHANG, Yang HU, Yan'ge MA, Kai CUI, Le YANG
-
Publication number: 20220114802Abstract: According to an embodiment of the disclosure, an electronic device may include a communication interface, a dynamic vision sensor (DVS) to generate bit data for each of a plurality of image frames, based on change in illuminance, a processor electrically connected with the communication interface and the DVS, and a memory electrically connected with the processor. The memory may store instructions, and the instructions may cause the processor to filter out at least a partial frame of the plurality of image frames, based on a ratio of the number of a bit value, which is included in the bit data and corresponds to each pixel, to the number of total pixels constituting each of the plurality of image frames, and recognize a shape of a surrounding object of the electronic device, based on another frame of the plurality of image frames. Moreover, various embodiment found through the disclosure are possible.Type: ApplicationFiled: September 10, 2019Publication date: April 14, 2022Inventors: Dongkyu LEE, Yongwook KIM, Yongju YU, Kiyoung KWON, Jimin KIM, Chulkwi KIM
-
Publication number: 20220114803Abstract: A method includes obtaining, by a camera, a current image, determining a pattern of the target object in the current image, determining, based on the pattern of a target object in the current image, whether a three-dimensional model of the target object is reconstructible, and displaying first prompt information on a display in response to determining that the three-dimensional model of the target object is reconstructible. The current image is at least one of a plurality of frames of images of the target object. The first prompt information is usable to indicate that the three-dimensional model of the target object is reconstructible.Type: ApplicationFiled: December 20, 2021Publication date: April 14, 2022Inventors: Guoyi WANG, Bing CHEN, Wenchao SUN, Ziya XU
-
Publication number: 20220114804Abstract: The present disclosure relates to a network training method and device, an image processing method and device, the method comprising: performing pixel shuffling on a first image in a training set to obtain a second image, wherein the first image is an image subjected to pixel shuffling; performing, by a feature extraction network of a neural network, feature extraction on the first image to obtain a first image feature, and performing, by a feature extraction network, feature extraction on the second image to obtain a second image feature; performing, by a recognition network of the neural network, recognition on the first image feature to obtain a recognition result of the first image; and training the neural network according to the recognition result, the first image feature and the second image feature. Embodiments of the present disclosure enable improvement of recognition precision of neural networks.Type: ApplicationFiled: July 21, 2021Publication date: April 14, 2022Applicant: BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD.Inventors: Wanli OUYANG, Maoqing TIAN, Shuai YI, Dongzhan ZHOU, Xinchi ZHOU
-
Publication number: 20220114805Abstract: The automated driving perception systems described herein provide technical solutions for technical problems facing navigation sensors for autonomous vehicle navigation. These systems may be used to combine inputs from multiple navigation sensors to provide a multimodal perception system. These multimodal perception systems may augment raw data within a development framework to improve performance of object detection, classification, tracking, and sensor fusion under varying external conditions, such as adverse weather and light, as well as possible sensor errors or malfunctions like miss-calibration, noise, and dirty or faulty sensors. This augmentation may include injection of noise, occlusions, and misalignments from raw sensor data, and may include ground-truth labeling to match the augmented data. This augmentation provides improved robustness of the trained perception algorithms against calibration, noise, occlusion, and faults that may exist in real-world scenarios.Type: ApplicationFiled: December 22, 2021Publication date: April 14, 2022Inventors: Julio Fernando Jarquin Arroyo, Ignacio J. Alvarez, Cornelius Buerkle, Fabian Oboril
-
Publication number: 20220114806Abstract: The present invention relates to a method, system and software for automatically capturing a target image in a movable device. The method comprises at least one of the steps of providing at least one image feature for the target image to be captured; monitoring image data; and capturing at least one target image when the image data monitored fulfill the image feature.Type: ApplicationFiled: December 23, 2019Publication date: April 14, 2022Inventors: Hicham BADRI, Aleksandr MOVCHAN, Appu SHAJI
-
Publication number: 20220114807Abstract: A system and method relating to object detection may include receiving an image frame comprising an array of pixels captured by an image sensor associated with the processing device, identifying a near-field image segment and a far-field image segment in the image frame, applying a first neural network trained for near-field image segments to the near-field image segment for detecting the objects presented in the near-field image segment, and applying a second neural network trained for far-field image segments to the far-field image segment for detecting the objects presented in the near-field image segment.Type: ApplicationFiled: July 24, 2019Publication date: April 14, 2022Applicant: Optimum Semiconductor Technologies Inc.Inventors: Sabin Daniel IANCU, Beinan WANG, John GLOSSNER
-
Publication number: 20220114808Abstract: A method for identifying a user using an image of an object of the user that has a biometric characteristic of the user, wherein the object is one of a palm of the hand of the user, a face of the user, an eye of the user, a bottom of a foot of the user, the method comprising: obtaining, by an optical sensor of a mobile device, the image of the object; providing the image to a neural network; processing the image by the neural network, thereby identifying both, the position of the object and the object in the image; extracting, from the identified object, the biometric characteristic; storing the biometric characteristic in a storage device and/or providing at least the biometric characteristic as input to an identification means, comprising processing the input in order to determine whether the biometric characteristic identifies the user.Type: ApplicationFiled: January 22, 2020Publication date: April 14, 2022Inventors: Hardik Gupta, Satheesh Murugan
-
Publication number: 20220114809Abstract: Systems and methods may include tracking one or a plurality features across a decreasing scale of tiled sets of one or more images. Aspects may include generating point data for each of the tracked features based on a coordinate system relative to the first camera or the second camera, and transforming the point data to a Global Positioning System/Inertial Navigation System (GPS/INS) coordinate system based on (1) an origin of a first GPS device coupled to the first camera and (2) a rotation of the first camera relative to an INS device coupled to the first camera. Aspects may include generating, based on the transformed point data, a geodetic mapping function, determining, based on the geodetic mapping function, georegistered coordinates of the tracked features, using the georegistered coordinates of the tracked features to characterize the water flow.Type: ApplicationFiled: October 8, 2021Publication date: April 14, 2022Applicant: The Government of the United States of America, as represented by Secretary of the NavyInventors: Carlo C. Zuniga Zamalloa, Blake J. Landry, Edward F. Braithwaite, III
-
Publication number: 20220114810Abstract: A forest resource information generation structure and a forest resource information generation method enable more efficiently grasping forest resource information via direct measurement of a breast height diameter with no need for an actual measurement data collection process such as a ground survey are provided.Type: ApplicationFiled: October 12, 2021Publication date: April 14, 2022Inventors: Motoyoshi Kikuchi, Kou Onoda, Yuka Kawamata, Koki Kimura, Satoshi Tsuchiya
-
Publication number: 20220114811Abstract: Provided is an image processing method including identifying a plurality of real-world objects or a plurality of virtual objects included in an image recognized by a device, obtaining depth information of each of the plurality of identified real-world objects or virtual objects, and outputting light of a virtual image corresponding to the plurality of identified real-world object or virtual object based on the depth information of each of the plurality of identified real-world objects or virtual objects.Type: ApplicationFiled: January 17, 2020Publication date: April 14, 2022Inventors: Gennadiy KIS, Andrii BUGAIOV
-
Publication number: 20220114812Abstract: Event occurrence is estimated from time series information which is high-dimensional information such as an image. A hazard estimation unit 11 estimates a likelihood of occurrence of an event according to a hazard function for each of a plurality of time-series image groups including time-series image groups in which no events have occurred and time-series image groups in which events have occurred, each of the plurality of time-series image groups being given an occurrence time of an event in advance, and a parameter estimation unit 12 estimates a parameter of the hazard function such that a likelihood function that is represented by including the occurrence time of an event given for each of the plurality of time-series image groups and the likelihood of occurrence of an event estimated for each of the plurality of time-series image groups is optimized.Type: ApplicationFiled: February 7, 2020Publication date: April 14, 2022Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATIONInventors: Yoshiaki TAKIMOTO, Yusuke TANAKA, Takeshi KURASHIMA, Shuhei YAMAMOTO, Maya OKAWA, Hiroyuki TODA
-
Publication number: 20220114813Abstract: A method for detecting an obstacle, an electronic device, a roadside device and a cloud control platform are provided and relates to the fields of automatic drive and intelligent traffic. The method includes acquiring a current image, wherein the current image includes an obstacle object representing an obstacle located on a predetermined plane; determining a transformation parameter between the current image and a template image based on current coordinates of a plurality of reference points on the predetermined plane in the current image and template coordinates of corresponding reference points for the plurality of reference points in the template image; and determining a position of the obstacle in a world coordinate system utilizing the transformation parameter and pixel coordinates of the obstacle object in the current image.Type: ApplicationFiled: December 22, 2021Publication date: April 14, 2022Inventor: Jinrang JIA
-
Publication number: 20220114814Abstract: A vehicular trailering assist system includes a rear backup camera disposed at a rear portion of a vehicle and a video display screen disposed in the vehicle and viewable by a driver of the vehicle. During a reversing maneuver of the vehicle with the trailer hitched thereto, the vehicular trailering assist system determines a projected path of travel of the vehicle with the trailer hitched thereto based at least in part on (i) image data captured by the rear backup camera, (ii) vehicle parameters provided to the vehicular trailering assist system and (iii) trailer parameters provided to the vehicular trailering assist system. During the reversing maneuver of the vehicle with the trailer hitched thereto, the video display screen displays the projected path for viewing by the driver of the equipped vehicle during the reversing maneuver.Type: ApplicationFiled: December 20, 2021Publication date: April 14, 2022Inventor: Devendra Bajpai
-
Publication number: 20220114815Abstract: There is provided a collision avoidance method of a moving body collision avoidance device including acquiring a driving image of the moving body, recognizing an object in the acquired driving image using a neural network model, calculating a relative distance between the moving body and the object based on the recognized object, calculating a required collision time between the object and the moving body based on the calculated relative distance, and controlling an operation of the moving body based on the calculated required collision time.Type: ApplicationFiled: October 12, 2021Publication date: April 14, 2022Applicant: THINKWARE CORPORATIONInventors: Suk Pil Ko, Young Yong Kim
-
Publication number: 20220114816Abstract: A method for controlling an internal light source of a vehicle, wherein the internal light source is for darkening of glasses. The method includes acquiring an image recognition result, wherein the image recognition is for determining whether an occupant of the vehicle wears glasses, and controlling the light source responsive to the acquired image recognition result. In some embodiments, controlling the light source includes activating the light source when the image recognition result indicates that the occupant wears glasses. In some embodiments, the image recognition result is indicative of whether glasses darken responsive to activation of the light source and controlling the light source comprises deactivating the light source when the image recognition result indicates that the glasses do not darken responsive to activation of the light source.Type: ApplicationFiled: December 18, 2021Publication date: April 14, 2022Inventors: Magnus NILSSON, Jonathan JOHANSSON
-
Publication number: 20220114817Abstract: System and methods are provided for detecting occupancy state in a vehicle having an interior passenger compartment the systems and methods include analyzing data of the interior passenger compartment to yield at least one probability of a current occupancy state of said vehicle and further analyzing additional data of the interior passenger compartment to yield predicted probabilities of said occupancy state of said vehicle, wherein each probability of the predicted probabilities relate to the probability of changing said current occupancy state to different occupancy state combining the current at least one probability of the current occupancy state with the predicted probabilities of the occupancy state to yield an updated probability of an updated occupancy state of said vehicle; determining the current occupancy state based on said updated probability of an updated occupancy state of said vehicle and generating an output to control one or more devices or applications based on the determined occupancy staType: ApplicationFiled: February 17, 2020Publication date: April 14, 2022Inventor: Yuval Gronau
-
Publication number: 20220114818Abstract: A vehicular driver monitoring system includes a driver monitoring camera and an illumination source accommodated within a movable head of an interior rearview mirror of a vehicle. The illumination source is electrically controlled to modulate near-infrared (NIR) light emitted by the illumination source whereby NIR light emitted by the illumination source comprises a characteristic modulation signature. Ambient light that is present within the interior cabin of the vehicle and modulated NIR light emitted by the illumination source that is reflected off at least the head of the driver of the vehicle are incident at the imaging array sensor of the driver monitoring camera. Processing of captured image data at an image processor distinguishes (i) NIR light emitted by the illumination source that has the characteristic modulation signature and that is reflected off the head of the driver from (ii) ambient light present within the interior cabin of the vehicle.Type: ApplicationFiled: December 20, 2021Publication date: April 14, 2022Inventor: Niall R. Lynam
-
Publication number: 20220114819Abstract: A cell tracking method for performing cell tracking on the basis of a plurality of cell images captured in time series, including an extraction process of extracting a tracking region corresponding to the cell for each cell images; a tracking process of calculating a change information in a position of the extracted tracking region and tracking the cell on the basis of the change information; a determination process of determining whether or not the cell as a tracking target is in a cell division state on the basis of the cell image; and an analysis process of analyzing a movement state of the cell on the basis of the change information from which the change information in a period of the cell division state is excluded when the cell is determined to be in the cell division state in the determination process.Type: ApplicationFiled: October 25, 2021Publication date: April 14, 2022Applicant: NIKON CORPORATIONInventors: Toru ICHIHASHI, Hiroaki KII, Tetsuomi TAKASAKI, Takayuki UOZUMI, Yoichi YAMAZAKI, Masaki KINEHARA
-
Publication number: 20220114820Abstract: Methods and an electronic device for image searches are described. In one example, a method for image search includes: an input image is received, multiple semantic features are extracted from the input image using one or more convolutional layers and one or more fully connected layers of a neural network; processing the multiple semantic features to obtain a binary code by using at least one additional layer of the neural network; the multiple semantic features are processed to obtain a binary code by using at least one additional layer of the neural network; and a hash-based search is performed by using the binary code to retrieve one or more images that includes at least part of the multiple semantic features.Type: ApplicationFiled: December 23, 2021Publication date: April 14, 2022Inventor: Jenhao HSIAO
-
Publication number: 20220114821Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to categorize image text. An example apparatus includes region detection model training circuitry to identify candidate regions in an input image that include text, and generate bounding boxes around respective ones of the identified candidate regions. The example apparatus also includes mask application circuitry to improve optical character recognition (OCR) by applying a mask to the input image, wherein the mask removes content of the input image except for portions of the input image within the bounding boxes, and OCR circuitry to perform OCR on the masked input image to obtain text data within the bounding boxes.Type: ApplicationFiled: July 19, 2021Publication date: April 14, 2022Inventors: Roberto Arroyo, David Jiménez, Javier Martínez Cebrián
-
Publication number: 20220114822Abstract: A method, an apparatus, a device, a storage medium and a program product of performing a text matching are provided, which relate to a field of a computer technology, and in particular to natural language processing and deep learning technologies. The method includes: determining a word set and a plurality of semantic units from a text set, the word set is associated with a first predetermined attribute, and the text set contains a plurality of first texts indicating an object information and a plurality of second texts indicating an object demand information; generating a graph; and generating a final feature representation associated with the text set and the word set based on the graph and a graph convolution model, so as to perform the text matching.Type: ApplicationFiled: December 22, 2021Publication date: April 14, 2022Inventors: Chao MA, Jingshuai ZHANG, Qifan HUANG, Kaichun YAO, Peng WANG, Hengshu ZHU
-
Publication number: 20220114823Abstract: An inference method includes acquiring similarities between a domain name serving as an analysis object and each domain name indicated in a legitimate domain name list as feature amounts, and inferring a degree that the domain name serving as the analysis object is wrongly recognized as a legitimate domain name based on the feature amounts acquired at the acquiring and a training model that outputs, as a response to input of the feature amounts, a degree that the domain name serving as the analysis object is wrongly recognized as the legitimate domain name, by processing circuitry.Type: ApplicationFiled: February 4, 2020Publication date: April 14, 2022Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATIONInventors: Daiki CHIBA, Takashi KOIDE, Ayako HASEGAWA, Mitsuaki AKIYAMA
-
Publication number: 20220114824Abstract: A non-transitory computer-readable recording medium storing a specifying program for causing a computer to execute processing including: acquiring a first value that indicates a result of inter-document distance analysis between each of a plurality of sentences stored in a storage unit and an input first sentence; acquiring a second value that indicates a result of latent semantic analysis between each of the sentences and the first sentence; calculating similarity between each of the sentences and the first sentence on the basis of a vector that corresponds to each of the sentences and has magnitude based on the first value acquired for each of the sentences and an orientation based on the second value acquired for each of the sentences; and specifying a second sentence similar to the first sentence among the plurality of sentences on the basis of the calculated similarity between each of the sentences and the first sentence.Type: ApplicationFiled: December 22, 2021Publication date: April 14, 2022Applicant: FUJITSU LIMITEDInventor: Yu Tomita
-
Publication number: 20220114825Abstract: An example apparatus for mining multi-scale hard examples includes a convolutional neural network to receive a mini-batch of sample candidates and generate basic feature maps. The apparatus also includes a feature extractor and combiner to generate concatenated feature maps based on the basic feature maps and extract the concatenated feature maps for each of a plurality of received candidate boxes. The apparatus further includes a sample scorer and miner to score the candidate samples with multi-task loss scores and select candidate samples with multi-task loss scores exceeding a threshold score.Type: ApplicationFiled: August 20, 2021Publication date: April 14, 2022Inventors: Anbang Yao, Yun Ren, Hao Zhao, Tao Kong, Yurong Chen
-
Publication number: 20220114826Abstract: There is provided a method for identifying potential associates of at least one target person, the method comprising: providing a plurality of videos; identifying appearances of the at least one target person in the plurality of videos; establishing a plurality of video scenes from the plurality of videos, wherein each one of the plurality of video scenes begins at a first predetermined duration before a first appearance of the at least one target person in the respective video scene and ends at a second predetermined duration after a last appearance of said at least one target person in the respective video scene; determining individuals who appear in more than a predetermined threshold number of the plurality of video scenes; and identifying the individuals as potential associates of the at least one target person.Type: ApplicationFiled: December 22, 2021Publication date: April 14, 2022Applicant: NEC CorporationInventors: Hui Lam ONG, Satoshi YAMAZAKI, Wei Jian PEH, Hong Yen ONG
-
Publication number: 20220114827Abstract: A fingerprint recognition detection circuit includes an operational amplifier, an integrating capacitor and a first switch connected in series, and a second switch. A non-inverting input terminal of the operational amplifier is coupled to a reference voltage terminal, and an inverting input terminal of the operational amplifier is coupled to a fingerprint sensing capacitor. The integrating capacitor and the first switch are coupled between the inverting input terminal of the operational amplifier and an output terminal of the operational amplifier. The second switch is coupled between the inverting input terminal of the operational amplifier and the output terminal of the operational amplifier, and the second switch is connected in parallel with the integrating capacitor and the first switch connected in series.Type: ApplicationFiled: April 10, 2020Publication date: April 14, 2022Inventors: Binbin LIU, Chen MENG, Wei SHI, Wenjie ZHONG, Zhong HU, Yongbo WANG, Zhenghua LU, Dahai HU, Guo LIU, Guoan WANG, Jiarong LIU
-
Publication number: 20220114828Abstract: A display device includes: a display panel; a fingerprint sensor which is disposed on a surface of the display panel and senses a user's fingerprint by emitting ultrasonic waves; and a first vibrator which is disposed on a surface of the fingerprint sensor and generates vibrations based on driving voltages applied thereto.Type: ApplicationFiled: December 17, 2021Publication date: April 14, 2022Inventors: Jong Tae KIM, Sang Wook YOO
-
Publication number: 20220114829Abstract: A working mode switching method and apparatus, a storage medium, and an electronic device are disclosed. The electronic device comprises a display screen, a first acousto-electric conversion module, and a second acousto-electric conversion module. The first acousto-electric conversion module and the second acousto-electric conversion module are located on one side of the display screen and connected to the display screen; and the first acousto-electric conversion module and the second acousto-electric conversion module are used for realizing the conversion between ultrasonic or acoustic signals and electrical signals.Type: ApplicationFiled: December 22, 2021Publication date: April 14, 2022Inventors: Zhijia CUI, Le YANG, Anping WU, Chao ZHENG, Wenzhen ZHANG
-
Publication number: 20220114830Abstract: A method of generating a finger image includes determining a quantity of electric charge to be removed from each of a plurality of detection circuits connected to a fingerprint sensor, based on an amplifier characteristic of each of the plurality of detection circuits; obtaining a second electrical quantity by removing the quantity of electric charge from a first electrical quantity that is input to each of the plurality of detection circuits; integrating the second electrical quantity to obtain an integrated value; and generating the fingerprint image based on comparison between the integrated value of the second electrical quantity and a predetermined threshold value.Type: ApplicationFiled: December 23, 2021Publication date: April 14, 2022Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Kyunghyun SON, Jaechul Park, Jinmyoung Kim
-
Publication number: 20220114831Abstract: A display panel and a display equipment. The display panel includes a base substrate; a plurality of light emitting devices disposed on the base substrate; a plurality of photosensitive devices disposed on the base substrate, an orthographic projection of each photosensitive device on the base substrate being disposed at a gap of orthographic projections of the adjacent light emitting devices on the base substrate; and a plurality of light shading parts disposed on one side, facing away from the base substrate, of a layer where the light emitting devices are disposed, wherein the light shading parts are in one-to-one correspondence with the photosensitive devices, and an orthographic projection of each light shading part on the base substrate is at least partially overlapped with the orthographic projection of the corresponding photosensitive device on the base substrate.Type: ApplicationFiled: May 28, 2020Publication date: April 14, 2022Inventor: Xiaoquan HAI
-
Publication number: 20220114832Abstract: An electronic device includes a fingerprint sensing layer including a plurality of columns of fingerprint pixel circuits, a touch layer including a plurality of columns of touch electrodes, a signal reading circuit including a plurality of common reading circuits each connected to at least one column of the touch electrodes and at least one column of the fingerprint pixel circuit and a control module configured to control the common reading circuits to be communicated with either the fingerprint pixel circuits or the touch electrodes at a timing; when the common reading circuit is communicated with the touch electrodes, acquire a touch signal which is collected by the touch electrodes and read by the common reading circuit; and when the common reading circuit is communicated with the fingerprint pixel circuits, acquire a fingerprint signal which is collected by the fingerprint pixel circuits and read by the common reading circuit.Type: ApplicationFiled: May 12, 2020Publication date: April 14, 2022Applicants: Beijing Xiaomi Mobile Software Co., Ltd. Nanjing Branch, BEIJING XIAOMI MOBILE SOFTWARE CO., LTD.Inventor: Chih-jen CHENG
-
Publication number: 20220114833Abstract: Disclosed are a data detection method and device, a computer equipment, and a storage medium. The method includes: obtaining a designated identification picture including a human face; correcting the designated identification picture to be placed in a preset standard posture to obtain an intermediate picture; inputting the intermediate picture into a preset face feature point detection model to obtain multiple face feature points; calculating a cluster center position of the face feature points, and generating a minimum bounding rectangle of the face feature points; retrieving a standard identification picture from a preset database; scaling the standard identification picture in proportion to obtain a scaled picture; overlapping a reference center position in the scaled picture and a cluster center position in the intermediate picture, so as to obtain an overlapping part in the intermediate picture; and marking the overlapping part as an identification body of the designated identification picture.Type: ApplicationFiled: June 29, 2020Publication date: April 14, 2022Inventor: Jinlun Huang
-
Publication number: 20220114834Abstract: A face recognition monitoring system based on spectrum and multi-band fusion, including a spectrum camera, a first module for acquiring a face spectral image, a second module for preprocessing data of the face spectral image, a face spectral image database and a third module for recognizing the face spectral image. The spectrum camera includes an optical lens and a silicon-based detector. The silicon-based detector includes a photoelectric conversion substrate and a filter film arranged thereon. The filter film includes N units each including a visible spectrum sensing area, a near-infrared spectral image sensing area and a RGGB image acquisition area. The N units cover all pixels on the photoelectric conversion substrate. A recognition method using the above system is also provided.Type: ApplicationFiled: December 20, 2021Publication date: April 14, 2022Inventors: Yu REN, Gang NIE, Hao ZHOU, Yuchen LIU, Xiaohui LIU, Shuo WANG, Yongsheng ZHANG, Hongxing CAI, Zhihai YAO
-
Publication number: 20220114835Abstract: A light-emitting device includes: a light source including plural light-emitting elements; a first optical member that is provided in a light-emitting path of the light source, the first optical member being configured to narrow a spread angle of light emitted from each of the light-emitting elements of the light source and emit the narrowed light; and a second optical member that is provided on a light-emitting side of the first optical member and is configured to diffuse and irradiate light incident from the first optical member.Type: ApplicationFiled: December 22, 2021Publication date: April 14, 2022Applicant: FUJIFILM BUSINESS INNOVATION CORP.Inventors: Takeshi MINAMIRU, Satoshi INADA, Takafumi HIGUCHI, Shigetoshi NAKAMURA, Kenichi ONO