Reading Maps, Graphs, Drawings, Or Schematics Patents (Class 382/113)
  • Patent number: 11391576
    Abstract: The invention provides a system, a method, and a computer programmable product for generating map data of a region. The method comprises obtaining image data of the region. The method further comprises determining, based on the image data, a plurality of road objects corresponding to at least one road segment associated with the region. The method further comprises generating at least one cluster of road objects corresponding to the at least one road segment, based on the plurality of road objects. The method further comprises generating the map data of the region based on the at least one cluster of road objects.
    Type: Grant
    Filed: December 2, 2019
    Date of Patent: July 19, 2022
    Assignee: HERE GLOBAL B.V.
    Inventors: Abhilshit Soni, Ashish Dhiman, Mohit Agarwal
  • Patent number: 11308334
    Abstract: A computer system executing code instructions of a visual scene feature extractor and classifier system comprising a processor executing object recognition on a captured image of a visual scene of interest including a plurality of objects in the visual scene of interest to identify a first object from the plurality of objects with a set of feature attributes wherein the feature attributes include an image view of the first object where the processor executing code instructions for the visual scene feature extractor and classifier to generate a first feature vector value for a first feature attribute of the first object.
    Type: Grant
    Filed: October 21, 2019
    Date of Patent: April 19, 2022
    Assignee: VISUAL SEMANTICS, INC.
    Inventor: Gareth Ian Block
  • Patent number: 11300968
    Abstract: A method is disclosed for use in a planning agent, the method including: identifying a first agent in a vicinity of the planning agent; identifying a location of the first agent and a velocity of the first agent; calculating a set of occupancy costs for the first agent, each occupancy cost in the set of occupancy costs being associated with a different respective location in the vicinity of the planning agent, each occupancy cost in the set of occupancy costs being calculated at least in part based on a cost function that depends on the location of the first agent and the velocity of the first agent; and changing at least one of speed or direction of travel of the planning agent based on the set of occupancy costs.
    Type: Grant
    Filed: February 22, 2019
    Date of Patent: April 12, 2022
    Assignee: Massachusetts Institute of Technology
    Inventors: Alyssa Pierson, Wilko Schwarting, Sertac Karaman, Daniela L. Rus
  • Patent number: 11288889
    Abstract: A computer includes a processor and a memory, the memory storing instructions executable by the processor to determine a first bounding box for a road sign in an image, identify a second bounding box for a physical member, the second bounding box for the physical member extending from the first bounding box for the road sign, and upon identifying the second bounding box for the physical member, actuate one or more vehicle components.
    Type: Grant
    Filed: July 16, 2020
    Date of Patent: March 29, 2022
    Assignee: Ford Global Technologies, LLC
    Inventors: Naman Kohli, Anuja Anil Shirsat, Sonal Doomra, Matthew Castaldini
  • Patent number: 11288522
    Abstract: The present invention relates to a method of generating an overhead view image of an area. More particularly, the present invention relates to a method of generating a contextual multi-image based overhead view image of an area using ground map data and field of view image data. Various embodiments of the present technology can include methods, systems and non-transitory computer readable media and computer programs configured to determine a ground map of the geographical area; receiving a plurality of images of the geographical area; process the plurality of images to select a subset of images to generate the overhead view of the geographical area; divide the ground map into a plurality of sampling points of the geographical area; and determine a color of a plurality of patches of the overhead view image from the subset of images, each patch representing each sampling point of the geographical area.
    Type: Grant
    Filed: December 31, 2019
    Date of Patent: March 29, 2022
    Assignee: Woven Planet North America, Inc.
    Inventors: Clemens Marschner, Wilhelm Richert, Thomas Schiwietz, Darko Zikic
  • Patent number: 11257231
    Abstract: A method for monocular depth/pose estimation in a camera agnostic network is described. The method includes training a monocular depth model and a monocular pose model to learn monocular depth estimation and monocular pose estimation based on a target image and context images from monocular video captured by the camera agnostic network. The method also includes lifting 3D points from image pixels of the target image according to the context images. The method further includes projecting the lifted 3D points onto an image plane according to a predicted ray vector based on the monocular depth model, the monocular pose model, and a camera center of the camera agnostic network. The method also includes predicting a warped target image from a predicted depth map of the monocular depth model, a ray surface of the predicted ray vector, and a projection of the lifted 3D points according to the camera agnostic network.
    Type: Grant
    Filed: June 17, 2020
    Date of Patent: February 22, 2022
    Assignee: TOYOTA RESEARCH INSTITUTE, INC.
    Inventors: Vitor Guizilini, Sudeep Pillai, Adrien David Gaidon, Rares A. Ambrus, Igor Vasiljevic
  • Patent number: 11257230
    Abstract: Embodiments include a method for pruning anchor points from a feature map generated from a Light Detections And Ranging (LiDAR) point cloud, the method comprising: receiving, by a navigation system, a LiDAR point cloud from a LiDAR sensor, the LiDAR point cloud comprising data representing one or more objects in physical surroundings detected by the LiDAR sensor; extracting, by the navigation system, a feature map from the LiDAR point cloud, the feature map comprising a plurality of anchor points, each anchor point defined by an anchor box; smoothing, by the navigation system, the extracted feature map; determining, by the navigation system, density of pixels within the anchor box of each anchor point; and pruning, by the navigation system, anchor points from the feature map based on a plurality of factors related to the determined density of pixels within the box of each anchor point.
    Type: Grant
    Filed: February 4, 2020
    Date of Patent: February 22, 2022
    Assignee: NIO USA, Inc.
    Inventors: Zachary M. Kendrick, Disha Ahuja, Ashwath Aithal
  • Patent number: 11244517
    Abstract: Provided are a device and a method of generating printing information. The method includes acquiring at least one image part by splitting a basic image acquired based on a user input; determining a target article corresponding to the basic image from a three-dimensional (3D) article list stored in a database (DB) by using the at least one image part; providing a graphical user interface (GUI) capable of editing a shape of the target article according to a user input; and editing the shape of the target article, based on a user input via the GUI, and generating printing information used to 3D print the edited target article.
    Type: Grant
    Filed: February 15, 2016
    Date of Patent: February 8, 2022
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventor: Jae-hoon Lee
  • Patent number: 11238282
    Abstract: Systems and methods for automated detection of changes in extent of structures using imagery are disclosed, including a non-transitory computer readable medium storing computer executable code that when executed by a processor cause the processor to: align, with an image classifier model, a structure shape of a structure at a first instance of time to pixels within an aerial image depicting the structure captured at a second instance of time; assess a degree of alignment between the structure shape and the pixels, so as to classify similarities between the structure depicted within the pixels and the structure shape using a machine learning model to generate an alignment confidence score; and determine an existence of a change in the structure based upon the alignment confidence score indicating a level of confidence below a predetermined threshold level of confidence that the structure shape and the pixels within the aerial image are aligned.
    Type: Grant
    Filed: June 3, 2020
    Date of Patent: February 1, 2022
    Assignee: Pictometry International Corp.
    Inventors: Stephen Ng, David R. Nilosek, Phillip Salvaggio, Shadrian Strong
  • Patent number: 11232251
    Abstract: Systems, devices and methods operative for identifying a reference within a figure and an identifier in a text associated with the figure, the reference referring to an element depicted in the figure, the reference corresponding to the identifier, the identifier identifying the element in the text, placing the identifier on the figure at a distance from the reference, the identifier visually associated with the reference upon the placing, the placing of the identifier on the figure is irrespective of the distance between the identifier and the reference.
    Type: Grant
    Filed: May 26, 2019
    Date of Patent: January 25, 2022
    Inventors: Roman Tsibulevskiy, Barry Greenbaum
  • Patent number: 11202055
    Abstract: A stereoscopic vision system captures stereoscopic images. The stereoscopic images are processed to rapidly discriminate between portions of the images that are on a ground-plane and those that are off the ground plane. The discrimination is based on comparing locations within the images using an expected disparity shift.
    Type: Grant
    Filed: February 28, 2018
    Date of Patent: December 14, 2021
    Assignee: BlackBerry Limited
    Inventor: Gordon Bell
  • Patent number: 11134191
    Abstract: An image display method includes obtaining, by an electronic device, a first instruction triggered by a user, where the first instruction instructs the electronic device to display a panoramic image. The method further includes obtaining, by the electronic device in response to the first instruction, historical bearing information and real-time bearing information of a camera lens of the electronic device, where the historical bearing information indicates a historical bearing of the camera lens that is measured when the panoramic image is shot, and the real-time bearing information indicates a current target bearing of the camera lens. The method further includes displaying, by the electronic device, a target picture corresponding to the target bearing in the panoramic image when the historical bearing information includes the target bearing.
    Type: Grant
    Filed: April 26, 2017
    Date of Patent: September 28, 2021
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Wenlong Zhao, Guangxue Sun
  • Patent number: 11113290
    Abstract: An exemplary embodiment includes a system for an information visualization engine designed to dynamically organize, via associative clustered tiling and tessellation, and then present instantly addressable content via any electronic user interface, but especially via mobile devices such as touch screen cellular phones, and tablets.
    Type: Grant
    Filed: May 29, 2018
    Date of Patent: September 7, 2021
    Assignee: CLUSTER COMMUNICATIONS, INC.
    Inventors: Edward Russell Braziel, Eric Matthew Penner
  • Patent number: 11094198
    Abstract: This application discloses a lane determining method performed at a computing device. The computing device obtains image information of a road surface image collected by a vehicle; identifies first lane information of at least one first lane of the road surface from the image information, the first lane information including a location relationship between a travelling lane in which the vehicle is located in the road surface and the at least one first lane, and a feature of the first lane; performs feature matching between the feature of the at least one first lane and a feature of at least one second lane in a map in which the road surface is located, the feature of the at least one second lane obtained from the map; and determines a target lane of the vehicle in the map corresponding to the travelling lane in the map in accordance with the feature matching result.
    Type: Grant
    Filed: June 12, 2019
    Date of Patent: August 17, 2021
    Inventor: Yujin Fu
  • Patent number: 11048257
    Abstract: Controlling an unmanned aerial vehicle may include obtaining a first image from a fixed orientation image capture device of the unmanned aerial vehicle, obtaining a second image from an adjustable orientation image capture device of the unmanned aerial vehicle, obtaining feature correlation data based on the first image and the second image, obtaining relative image capture device orientation calibration data based on the feature correlation data, the relative image capture device orientation calibration data indicating an orientation of the adjustable orientation image capture device relative to the fixed orientation image capture device, obtaining relative object orientation data based on the relative image capture device orientation calibration data, the relative object orientation data representing a three-dimensional orientation of an external object relative to the adjustable orientation image capture device, and controlling a trajectory of the unmanned aerial vehicle in response to the relative object
    Type: Grant
    Filed: February 27, 2018
    Date of Patent: June 29, 2021
    Assignee: GoPro, Inc.
    Inventors: Sammy Omari, Pascal Gohl, Axel Murguet, Garance Bruneau, Fabio Diem, Lukas Schmid
  • Patent number: 11037011
    Abstract: A method for acquiring images of the surface of the earth, installing an aerial platform in a quasi-stationary position, equipped with an image acquisition system with a large field of view and a second, high-resolution, image acquisition system is disclosed. The method includes implementing successive observation cycles, each one including the acquisition of an image of a zone of interest by the first system, the partitioning of the image thus acquired into mesh units which each correspond to a sector of the zone of interest, the analysis of the image in order to detect the potential presence of unwanted marks, and the acquisition of an image by the second system for the mesh units for which no unwanted marks have been detected. Observation cycles are thereby implemented until images of the entire zone of interest have been acquired by the second system.
    Type: Grant
    Filed: November 8, 2018
    Date of Patent: June 15, 2021
    Assignee: Airbus Defence and Space SAS
    Inventor: Pierre-Luc Georgy
  • Patent number: 11024067
    Abstract: A method, non-transitory computer readable medium, and computing apparatus that identifies with automated image analysis two or more different types of content in image data for an electronic image associated with one or more of a plurality of types of claims. The image data associated with each of the identified two or more different types of content is converted by a different one of a plurality of automated content conversion techniques based on the association with the one or more types of claims and on the identified one of the plurality of types of content. Modified image data for the electronic image is generated based on the converted image data associated with each of the identified two or more different types of content. The modified image data for the electronic image with the converted image data for each of the identified two or more different types of content is provided.
    Type: Grant
    Filed: September 13, 2019
    Date of Patent: June 1, 2021
    Assignee: Mitchell International, Inc.
    Inventor: Marius Dornean
  • Patent number: 11022442
    Abstract: Methods, devices, and systems for indoor mapping are described herein. The methods include providing an indoor map containing a current location of a user device, the indoor map having a containing exterior space, a contained interior space within the containing exterior space, and a linkage, the linkage having a coordinate transformation to project coordinates of the interior space onto coordinates of the exterior space. The methods also include receiving a point of interest, determining a path from the current location to the point of interest, the current location and the point of interest being in walkable areas, the path including a transition between the interior space and the exterior space, and providing instructions to navigate along the path, the coordinates of the interior space and the coordinates of the exterior space are referenced by either the instructions prior to the transition and the instructions after the transition.
    Type: Grant
    Filed: March 15, 2018
    Date of Patent: June 1, 2021
    Assignee: MappedIn Inc.
    Inventors: Patrick Paskaris, Erkang Wei, James Nathan Swidersky, Sarah Knight, Mitchell Butler
  • Patent number: 11018982
    Abstract: Described herein are systems, methods, storage media, and computer programs that support data flow scheduling between processors. In one embodiment, a processor for processing data is disclosed. The processor comprises a flow classifier and a first set of circuits. The flow classifier is configured to assign a flow identifier to a data flow. The first set of circuits is configured to process a plurality of data blocks of the data flow and determine whether to provide information on the processing of the plurality of data blocks to another processor based on the flow identifier.
    Type: Grant
    Filed: November 14, 2016
    Date of Patent: May 25, 2021
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventor: Kang Yang
  • Patent number: 10996070
    Abstract: A route guidance apparatus and method are provided. The route guidance apparatus includes an image acquisition unit that collects image data of an area in front of a vehicle using a camera and a driver view recognition unit that calculates the range of a driver viewing angle by detecting a driver eye height driver a driver's gaze direction. An image processing unit extracts a region of interest corresponding to the range of the driver viewing angle from the image data and generates a route guidance image by overlaying a direction indicator corresponding to a driving route on the region of interest. A display unit outputs the route guidance image.
    Type: Grant
    Filed: October 21, 2019
    Date of Patent: May 4, 2021
    Assignees: Hyundai Motor Company, Kia Motors Corporation
    Inventor: Woo Sok Yang
  • Patent number: 10990815
    Abstract: Systems and processes can reduce or divide images of road networks into sub-images that depict straight or substantially straight sections of roads in the road networks. These sub-images or image segments can be normalized by, for example, rotating each of the sub-images such that the depicted roads are horizontal or otherwise share the same angle. By aligning disparate images of roads, it is possible to both reduce the amount of training data used to generate a machine learning model and to increase the accuracy of an automated lane marking or labelling system. Further, the use of normalized images by the machine learning model enables a reduction in computing resources used to perform automated lane marking processes while maintaining or improving accuracy of the lane marking processes.
    Type: Grant
    Filed: December 27, 2018
    Date of Patent: April 27, 2021
    Assignee: Beijing DiDi Infinity Technology and Development Co., Ltd.
    Inventors: Tingbo Hou, Yan Zhang
  • Patent number: 10972599
    Abstract: Disclosed is a system and method of providing enhanced content to a PSAP or other service center whereby when a 911 call is to be initiated, prior to the call or text communication being sent, the software application on the device contacts the cloud-based dynamic page service. The cloud-based dynamic page service receives event information, dynamically creates a page for the event along with a page identifier, and sends the page identifier to the software application of the initiating device. Then, the software application on the device initiates a 911 communication and includes the page identifier with the communication. In some cases, the page identifier may be sent as a separate communication.
    Type: Grant
    Filed: October 16, 2020
    Date of Patent: April 6, 2021
    Assignee: BEAMLIVE INC
    Inventors: Mehrdad Negahban, Michael Patrick Jones, Sahand Negahban Hagh, Brad Andrew Keahi Beck, Edward Chau Hoy
  • Patent number: 10944591
    Abstract: An apparatus is provided that includes a processor and a memory storing executable instructions that in response to execution by the processor cause the apparatus to at least perform a number of operations. The apparatus is caused to receive time information over a packet-switched computer network, with the time information including a current standard time, time-zone offset and timestamps that define a predetermined timeframe. The apparatus is caused to calculate a current local time from the current standard time and time-zone offset, and including an adjustment of the current local time in instances in which the timestamps indicate that the current standard time is within the predetermined timeframe. And the apparatus is caused to cause a clock to be set to the current local time.
    Type: Grant
    Filed: October 14, 2015
    Date of Patent: March 9, 2021
    Assignee: Electrolux Home Products, Inc.
    Inventors: James Fisher, Matthew David McClellan
  • Patent number: 10937325
    Abstract: According to various aspects, an obstacle map generator is provided, including: one or more processors configured to receive one or more depth images from a depth imaging system, determine, for each depth image of the one or more received depth images, a first set of pixels and a second set of pixels, each pixel of the first set of pixels has a depth value assigned thereto and each pixel of the second set of pixels has no depth value assigned thereto or has a depth value outside a predefined depth value range assigned thereto, assign a pre-defined depth value to one or more pixels of the second set of pixels, and generate an obstacle map based on the determined first set of pixels and the one or more pixels of the second set of pixels having the pre-defined depth value assigned thereto.
    Type: Grant
    Filed: December 27, 2018
    Date of Patent: March 2, 2021
    Assignee: INTEL CORPORATION
    Inventors: Daniel Pohl, Markus Achtelik, Bastian Jaeger, Andre Ryll, Jan Willem Vervoorst
  • Patent number: 10909988
    Abstract: An electronic device includes a display, wherein the display is configured to present a user interface, wherein the user interface comprises a coordinate system. The coordinate system corresponds to physical coordinates. The display is configured to present a sector selection feature that allows selection of at least one sector of the coordinate system. The at least one sector corresponds to captured audio from multiple microphones. The sector selection may also include an audio signal indicator. The electronic device includes operation circuitry coupled to the display. The operation circuitry is configured to perform an audio operation on the captured audio corresponding to the audio signal indicator based on the sector selection.
    Type: Grant
    Filed: September 24, 2018
    Date of Patent: February 2, 2021
    Assignee: Qualcomm Incorporated
    Inventors: Lae-Hoon Kim, Erik Visser, Phuong Lam Ton, Jeremy Patrick Toman, Jeffrey Clinton Shaw
  • Patent number: 10891501
    Abstract: A transport service system automatically associates road sign information with road segments based on image data including a representation of the road sign. The transport service system receives image data from one or more camera systems. Based on the image data, the transport service system determines a distance score and an orientation score for one or more candidate road segments. The transport service system additionally determines whether the image data is anomalous. Based on the determined distance and orientation scores, the transport service system generates a composite score and a confidence score for each candidate road segment. The confidence score is adjusted based on whether the image data is anomalous. Based on the generated scores, the transport service system identifies a most likely candidate road segment for association with the road sign.
    Type: Grant
    Filed: February 5, 2019
    Date of Patent: January 12, 2021
    Assignee: Uber Technologies, Inc.
    Inventors: Lin He, Nishanth Mohan
  • Patent number: 10782688
    Abstract: The present invention relates to the field of electronic photographing technologies, and provides a method, a control apparatus and a system for tracking and shooting a target. The method includes: in a tracking and shooting process, controlling, by a control apparatus, a photographing apparatus on an unmanned aerial vehicle to collect an image, and obtaining the collected image; selecting a tracked target in the image; calculating a movement speed, a movement direction and a location on the current image that are of the tracked target according to comparison between consecutive neighboring frame images; and controlling, according to the calculated movement speed, movement direction and location on the current image, the unmanned aerial vehicle to track the tracked target, so that the tracked target is always located on the image collected by the photographing apparatus.
    Type: Grant
    Filed: June 7, 2018
    Date of Patent: September 22, 2020
    Assignee: AUTEL ROBOTICS CO., LTD.
    Inventor: Zuoguang Li
  • Patent number: 10776651
    Abstract: The disclosed embodiments relate to a material handling method that generates three-dimensional (3-D) point cloud data based on a field-of-view of an image capturing unit. A first set of cluster areas are extracted from a plurality of cluster areas based on orientation data of the 3-D point cloud data. Further, a two-dimensional depth map is generated based upon the 3-D point cloud data. A candidate region that corresponds to a cluster area from the first set of cluster areas is determined. A ratio of a cross-sectional area of the cluster area and a cross-sectional area of the container is determined that exceeds a first cross-sectional threshold. Accordingly, a classification score of the candidate region is determined when the determined ratio exceeds a first cross-sectional threshold. In response to classifying the candidate region as a region-of-interest, a navigation path in the container that prevents collision with the region-of-interest is defined.
    Type: Grant
    Filed: January 18, 2019
    Date of Patent: September 15, 2020
    Assignee: INTELLIGRATED HEADQUARTERS, LLC
    Inventors: Karthikeyan Yuvaraj, Sriram Pavan Tankasala
  • Patent number: 10775174
    Abstract: A feature extraction system extracts map features from an aerial image. The feature extraction system receives an aerial image having pixels and predicts, for each pixel, a probability that the pixel corresponds to a map feature based on a machine learning model. The machine learning model is trained to determine a probability that a pixel corresponds to the map feature based on a training dataset comprising pairs of aerial images and corresponding mask images that describe known instances of the map feature. The feature extraction system identifies a subset of pixels of the plurality of pixels. Each pixel in the subset has a predicted probability that is greater than or equal to a threshold probability that a pixel corresponds to the map feature. The feature extraction system further determines a bounded geometry enclosing the identified subset of pixels, the bounding geometry encompassing an instance of the map feature.
    Type: Grant
    Filed: December 31, 2018
    Date of Patent: September 15, 2020
    Assignee: Mapbox, Inc.
    Inventors: Daniel Hofmann, Bhargav Kowshik KR
  • Patent number: 10733777
    Abstract: Provided are methods, systems, and devices for generating annotations in images that can include receiving image data including images associated with locations. The images can include key images comprising one or more key annotations located at one or more key annotation locations in the one or more key images. At least one image and a pair of the key images that satisfies one or more annotation criteria can be selected based in part on one or more spatial relationships of the plurality of locations associated with the images. An annotation location for an annotation in the image can be determined based in part on the one or more key annotation locations of the one or more key annotations in the pair of the key images that satisfies the one or more annotation criteria. An annotation can be generated at the annotation location of the image.
    Type: Grant
    Filed: June 13, 2018
    Date of Patent: August 4, 2020
    Assignee: Google LLC
    Inventor: Joshua Sam Schpok
  • Patent number: 10706125
    Abstract: Systems, methods, and devices for providing hour-of-service (“HOS”) calculations via a web based host server instead of on an onboard mobile device. In the various embodiments, an onboard vehicle recording device and driver-carried mobile devices may operate independently. The onboard vehicle recording device and driver-carried mobile device(s) may exchange information independently with a host server rather than exchanging information together onboard the vehicle.
    Type: Grant
    Filed: February 7, 2018
    Date of Patent: July 7, 2020
    Assignee: OMNITRACS, LLC
    Inventor: Thomas N. Flies
  • Patent number: 10697779
    Abstract: Embodiments are provided that include receiving sensor data from a sensor positioned at a plurality of positions in an environment. The environment includes a plurality of landmarks. The embodiments also include determining, based on the sensor data, a subset of the plurality of landmarks detected at each of the plurality of positions. The embodiments further include determining, based on the subset of the plurality of landmarks detected at each of the plurality of positions, a detection frequency of each landmark. The embodiments additionally include determining, based on the determined detection frequency of each landmark, a localization viability metric associated with each landmark. The embodiments still further include providing for display, via a user interface, a map of the environment. The map includes an indication of the localization viability metric associated with each landmark.
    Type: Grant
    Filed: April 21, 2017
    Date of Patent: June 30, 2020
    Assignee: X Development LLC
    Inventor: Dirk Holz
  • Patent number: 10643098
    Abstract: The invention relates to a system (51) for improving the spatial resolution of sensor data. The system comprises at least one receiver (53) and at least one processor (55). The at least one receiver (53) is configured to receive a sensor data set and a map. Each element of the sensor data set comprises a sensor footprint identifier allowing a sensor footprint to be identified and a brightness temperature measured for the sensor footprint. The map defines for each of a plurality of geographical areas whether it belongs to one of the first class and the second class. The first class represents a land type and the second class represents a water type. The geographical area is smaller than the sensor footprint.
    Type: Grant
    Filed: June 13, 2017
    Date of Patent: May 5, 2020
    Assignee: Vandersat B.V.
    Inventors: Richard Adrianus Maria De Jeu, Anna Helena Alida De Nijs, Michel Hendricus Wilibrord Van Klink
  • Patent number: 10621467
    Abstract: A system for detecting clouds and cloud shadows is described. In one approach, clouds and cloud shadows within a remote sensing image are detected through a three step process. In the first stage a high-precision low-recall classifier is used to identify cloud seed pixels within the image. In the second stage, a low-precision high-recall classifier is used to identify potential cloud pixels within the image. Additionally, in the second stage, the cloud seed pixels are grown into the potential cloud pixels to identify clusters of pixels which have a high likelihood of representing clouds. In the third stage, a geometric technique is used to determine pixels which likely represent shadows cast by the clouds identified in the second stage. The clouds identified in the second stage and the shadows identified in the third stage are then exported as a cloud mask and shadow mask of the remote sensing image.
    Type: Grant
    Filed: November 16, 2018
    Date of Patent: April 14, 2020
    Assignee: THE CLIMATE CORPORATION
    Inventors: Wei Guan, Pramithus Khadka, Jeffrey Gerard
  • Patent number: 10586384
    Abstract: Architecture that enables the preservation of label readability in a scene (e.g., map, map tiles, graphical background, etc.) by way of label orientation relative to a fixed heading on a plane or curved surface. After identifying an initial fixed heading, movement of the camera (e.g., zoom-in, zoom-out, position change, etc.) in the scene along that heading without changing the camera heading as measured relative to a fixed point does not alter label orientation. In a mapping implementation, after identifying an initial fixed camera heading over terrain of the Earth, movement of the camera (e.g., zoom-in, zoom-out, position change, etc.) in the scene without changing the camera heading as measured relative to some fixed point does not change label orientation. The orientation of labels may be changed if the heading of the camera is altered, but this change is delayed until camera movement quiesces.
    Type: Grant
    Filed: May 14, 2019
    Date of Patent: March 10, 2020
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Isaac Kenneth Kunen, Brenton Gunning, Daniel Dole, Juan Pablo Candelas Gonzalez, Donald A. Barnett, Romualdo Impas, David Buerer
  • Patent number: 10572766
    Abstract: An image collation device includes: a tentative matching point extraction unit configured to extract a plurality of tentative matching points that are pairs of corresponding feature points between a pair of input images; and a spatial verification unit configured to evaluate a degree of similarity between the pair of input images on the basis of all of a limiting conditions regarding consistency of a scale factor, a limiting conditions regarding consistency of a rotational angle, and a limiting conditions regarding consistency of a relative positional relationship according to a comparison of or a difference between geometric transformation parameters of the tentative matching points for each of the pairs of tentative matching points that is a combination of the tentative matching points extracted by the tentative matching point extraction unit.
    Type: Grant
    Filed: July 1, 2016
    Date of Patent: February 25, 2020
    Assignee: NIPPON TELEGRAPH AND TELEPHONE CORPORATION
    Inventors: Xiaomeng Wu, Kunio Kashino
  • Patent number: 10540782
    Abstract: A method for estimating a pose of a first object in relation to a second object, the second object comprising a visual marker comprising a plurality of ellipses comprises capturing a video image of the visual marker with an image capture device on the first object, then pre-processing frames of the video image on a graphics processing unit. The method comprises detecting the visual marker by finding contours in the frames to identify the plurality of ellipses and determining that a pattern of the plurality of ellipses match a known pattern of the visual marker. Then the method comprises obtaining coordinates of two or more of the plurality of ellipses of the visual marker, estimating the pose of the first object in relation to the second object by inputting the coordinates of the plurality of ellipses into a pose estimation algorithm, and filtering results of the pose estimation algorithm.
    Type: Grant
    Filed: November 15, 2017
    Date of Patent: January 21, 2020
    Assignee: Colorado Seminary Which Owns and Operates the University of Denver
    Inventors: Alessandro Benini, Matthew J. Rutherford, Kimon P. Valavanis
  • Patent number: 10528812
    Abstract: A system for object recognition and segmentation from digital images provides an intelligent object recognition and segmentation using one or more multilayer convolutional neural network (CNN) models trained in multiple-stages and in a parallel and distributed manner to improve training speed and efficiency. The training dataset used in each of the multiple training stages for the CNN models are generated, expanded, self-validated from a preceding stage. The trained final CNN models are augmented with post-model filters to enhance prediction accuracy by removing false positive object recognition and segmentation. The system provides improved accuracy to predict object labels to append to unlabeled image blocks in digital images. In one embodiment, the system may be useful for enhancing a digital landmark registry by appending identifying labels on new infrastructure improvements recognized in aerial or satellite land images.
    Type: Grant
    Filed: July 3, 2019
    Date of Patent: January 7, 2020
    Assignee: Accenture Global Solutions Limited
    Inventors: Gilles Brouard, Lewen Zhao, Natacha Fort, Ke Zeng, Adrien Jacquot, Vitalie Schiopu, Florin Cremenescu
  • Patent number: 10460453
    Abstract: A method for sparse optical flow based tracking in a computer vision system is provided that includes detecting feature points in a frame captured by a monocular camera in the computer vision system to generate a plurality of detected feature points, generating a binary image indicating locations of the detected feature points with a bit value of one, wherein all other locations in the binary image have a bit value of zero, generating another binary image indicating neighborhoods of currently tracked points, wherein locations of the neighborhoods in the binary image have a bit value of zero and all other locations in the binary image have a bit value of one, and performing a binary AND of the two binary images to generate another binary image, wherein locations in the binary image having a bit value of one indicate new feature points detected in the frame.
    Type: Grant
    Filed: September 15, 2016
    Date of Patent: October 29, 2019
    Assignee: TEXAS INSTRUMENTS INCORPORATED
    Inventors: Deepak Kumar Poddar, Anshu Jain, Desappan Kumar, Pramod Kumar Swami
  • Patent number: 10452940
    Abstract: A musical score image analyzer includes a processor and a memory having stored thereon instructions executable by the processor to cause the musical score image analyzer to perform: detecting musical symbols in a musical score image obtained by capturing a musical score having a plurality of staffs arranged in parallel to each other and the musical symbols respectively disposed in prescribed positions in the staffs; specifying a symbol column having the detected musical symbols which are arranged in a column; calculating an index relating an image capturing based on the symbol column; and instructing a capturing device to perform capturing operation of a still image for the musical score image when the index satisfies a prescribed condition.
    Type: Grant
    Filed: March 28, 2018
    Date of Patent: October 22, 2019
    Assignee: YAMAHA CORPORATION
    Inventor: Kazuhiko Yamamoto
  • Patent number: 10382744
    Abstract: A monitor system includes at least one three-dimensional camera circuit and a controller. Each of the at least one three-dimensional camera circuit is used for capturing a plurality of images including an object, and generating a depth map corresponding to the object according to the plurality of images. The controller is used for determining a plurality of feature points corresponding to the object according to the plurality of images or depth map, determining relative coordinates of the plurality of feature points according to the depth map, generating external information corresponding to the object according to the relative coordinates of the plurality of feature points, and generating monitor information corresponding to the object according to the external information corresponding to the object and reference parameters corresponding to the object.
    Type: Grant
    Filed: June 2, 2016
    Date of Patent: August 13, 2019
    Assignee: eYs3D Microelectronics, Co.
    Inventors: Chao-Chun Lu, Wen-Kuo Lin
  • Patent number: 10380135
    Abstract: Systems and methods that facilitate data center infrastructure management are discussed. One such system can include a plurality of data center infrastructure management (DCIM) tools. Each DCIM tool can maintain data associated with one or more data centers. Such a system can also include a data aggregation component that can extract the maintained data from at least two of the plurality of DCIM tools and can transform the extracted data into a common format. Such a system can also include an aggregated database that stores the extracted data, and can include a user interface that can provide for simultaneous access to the plurality of DCIM tools.
    Type: Grant
    Filed: November 20, 2014
    Date of Patent: August 13, 2019
    Assignee: WELLS FARGO BANK, N.A.
    Inventors: Angelo B. Macugay, Ken Camut, Deb Motto, Jason Hill, Charlie Wands, Bob Culver
  • Patent number: 10360686
    Abstract: A system for generating a ground truth dataset for motion planning of a vehicle is disclosed. The system includes an internet server that further includes an I/O port, configured to transmit and receive electrical signals to and from a client device; a memory; one or more processing units; and one or more programs stored in the memory and configured for execution by the one or more processing units, the one or more programs including instructions for: a corresponding module configured to correspond, for each pair of images, a first image of the pair to a LiDAR static-scene point cloud; and a computing module configured to compute a camera pose associated with the pair of images in the coordinate of the point cloud.
    Type: Grant
    Filed: June 13, 2017
    Date of Patent: July 23, 2019
    Assignee: TUSIMPLE
    Inventors: Yi Wang, Yi Luo, Wentao Zhu, Panqu Wang
  • Patent number: 10346356
    Abstract: Methods and systems for searching computer-aided design (CAD) data. One method includes receiving a selection of a type of CAD metadata, displaying a user interface including at least one input mechanism for receiving a search parameter associated with the type of CAD metadata, and receiving the search parameter through the user interface. The method also includes, in response to receiving the search parameter, automatically identifying, with an electronic processor, CAD metadata associated with the CAD data matching the search parameter, and providing the CAD metadata matching the search parameter to a user.
    Type: Grant
    Filed: January 22, 2016
    Date of Patent: July 9, 2019
    Assignee: Robert Bosch GmbH
    Inventors: Baljit Bains, Pendyala Naga Venkata Krishna Rao, Surendran Devaraj, Vijay Anthony Josepharuldass
  • Patent number: 10345453
    Abstract: A surveying system for a construction site has a restricted antenna system with a plurality of fixed location antennas each defined by a set of location data associated with a specific deployment position. The surveying system also has a computing device with a data processor and a display screen. A communications module establishes a data transfer link with the restricted antenna system over which spatial data for distances between current positions of the computing device and one or more of the plurality of fixed location antennas are received. The computing device is loadable with project drawings corresponding to the construction site and displayable on the display screen. A position marker is overlaid on the display of the project drawing at a position thereon corresponding to a computing device location value derived from the spatial data and the location data of one or more of the fixed location antennas.
    Type: Grant
    Filed: September 11, 2017
    Date of Patent: July 9, 2019
    Inventors: Jesse Gil, Ronald D. Shaw, Jeff Counterman
  • Patent number: 10248664
    Abstract: This disclosure relates to improved sketch-based image retrieval (SBIR) techniques. The SBIR techniques utilize an architecture comprising three interconnected neural networks to enable zero-shot image recognition and retrieval based on free-hand sketches. Zero-shot learning may be implemented to retrieve one or more images corresponding to the sketches without prior training on all categories of the sketches. The neural network architecture may do so, at least in part, by training encoder hashing functions to mitigate heterogeneity of sketches and images, and by applying semantic knowledge that is learned during a limited training phase to unknown categories.
    Type: Grant
    Filed: July 2, 2018
    Date of Patent: April 2, 2019
    Assignee: INCEPTION INSTITUTE OF ARTIFICIAL INTELLIGENCE
    Inventors: Yuming Shen, Li Liu, Fumin Shen, Ling Shao
  • Patent number: 10242248
    Abstract: The subject disclosure presents systems and methods for separating colors in an image by automatically and adaptively adjusting reference vectors based on information specific to the assay being imaged, resulting in an optimized unmixing process that provides stain information that is physically and physiologically plausible. The reference vectors are optimized iteratively, based on minimizing non-negative color contributions, background contributions, high-frequencies in color channels specific to background or unwanted fluorescence, signals from known immunohistochemical markers, and pairs of stains known to carry physiologically independent information. Adjustments to the reference vectors may be allowed within a range that is predetermined based on measuring colors from multiple input images.
    Type: Grant
    Filed: May 28, 2014
    Date of Patent: March 26, 2019
    Assignee: Ventana Medical Systems, Inc.
    Inventors: Joerg Bredno, Lou Dietz, Jim F. Martin
  • Patent number: 10240940
    Abstract: A route planning system applied in a server or in a mobile client device can plan a travel route according to client device location information. The route planning system includes an obtaining module, a selection module, and a calculation module. The obtaining module obtains the client device location information. The selection module determines a distance or scanning range according to the client device location information, and selects first pictures from the server or the client device of destinations or attractions which are within the scanning range, according to the location information of all the stored pictures. The calculation module calculates at least one route according to the location information of the first pictures. A route planning method is also provided.
    Type: Grant
    Filed: December 29, 2016
    Date of Patent: March 26, 2019
    Assignee: Chiun Mai Communication Systems, Inc.
    Inventors: Hsiu-Hua Yen, Chih-Pu Hsu, Chia-Wei Chien, Sung-Chieh Chang
  • Patent number: 10223806
    Abstract: A method of localization for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs comprise instructions, which when executed by a computing device, cause the computing device to perform by one or more autonomous vehicle driving modules execution of processing of images from a camera and data from a LiDAR using the following steps comprising: constructing a 3D submap and a global map; extracting features from the 3D submap and the global map; matching features extracted from the 3D submap against features extracted from the global map; refining feature correspondence; and refining location of the 3D submap.
    Type: Grant
    Filed: August 23, 2017
    Date of Patent: March 5, 2019
    Assignee: TUSIMPLE
    Inventors: Yi Luo, Yi Wang, Ke Xu
  • Patent number: 10209343
    Abstract: An electro-optical imaging sensors system is disclosed for detecting and locating a blast, including muzzle flash, created by the launch of a projectile from a gun barrel, rocket tube or similar device, generally associated with weapons fire. The system is used in conjunction with detection algorithms and provides the azimuth and elevation from the detecting sensor to the location of the blast (the launch location) and also provides the weapon classification.
    Type: Grant
    Filed: July 31, 2017
    Date of Patent: February 19, 2019
    Assignee: THE UNITED STATES OF AMERICA, AS REPRESENTED BY THE SECRETARY OF THE ARMY
    Inventors: Jeremy B. Brown, John E. Hutchison, III