Abstract: A method for generating training data for object detection is provided. The method includes dividing an image into a plurality of sliced images. The image includes meta information for an object in the image, the meta information including bounding box information associated with a bounding box surrounding the object, and marker information for markers associated with the object, the markers being located within the bounding box. The method includes designating at least one sliced object image from among the plurality of sliced images, at least a portion of the bounding box overlapping with each of the respective sliced object images. The method also includes designating at least one training data image from among the designated sliced object images based on the marker information. The method also includes generating the training data from the designated training data images.
Type:
Grant
Filed:
November 22, 2019
Date of Patent:
December 14, 2021
Assignee:
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventors:
Shingo Nagai, Kohhei Nomura, Madoka Yamagami, Yiru Lai
Abstract: Methods are provided for training and validating deep learning models for visual search and related tasks as they pertain to fashion items such as garments. The methods presented address the special needs of visual search as it pertains to fashion and related industries by generating large numbers of synthetic images or videos for training deep learning models, and also for validating those models. Given a 3D model of a target garment, the methods select appropriate 3D models for humans and scenes, and also selects various values for the customizable parameters of each of the 3D models, and then renders an image or video. A dataset comprising such synthetic images can be blended with real-world tagged images to create composite datasets for training.
Abstract: A mobile virtual network operator is provided. The operator includes a server that is communicatively coupled to a mobile device. The mobile device includes application software provided by the virtual network operator for allowing phone call and data connectivity.
Abstract: A double tire determination device includes an image input unit and a determination unit. The image input unit receives input of a captured image including a tire mounted on a vehicle. The determination unit determines whether the tire is a double tire, based on a ratio between a first area and a second area. The first area is an area of a first wheel region that is a part of a region of a wheel holding the tire and that is located on a side in a first direction with respect to a position of a rotation center of the tire. The second area is an area of a second wheel region that is a part of the region of the wheel holding the tire and that is located on a side in a second direction, which is opposite to the first direction, with respect to the position of the rotation center.
Abstract: The present disclosure includes systems and methods for color transfer. The method includes receiving a target image, and determining dominant source colors. The method further includes transforming the target image into a color model including a target luminance component and a target color information component. Additionally, the method includes segmenting the target image into a plurality of target segments based on the target color information component or the target luminance component and extracting dominant target colors from the target image by extracting information for at least one of the dominant target colors from each target segment of the plurality of target segments. Further, the method includes generating a color mapping relationship between the dominant target colors and the dominant source colors, and creating a recolored target image using the color mapping relationship.
Type:
Grant
Filed:
September 7, 2017
Date of Patent:
October 26, 2021
Assignees:
Trustees of Tufts College, THE BOARD OF REGENTS OF THE UNIVERSITY OF TEXAS SYSTEM
Abstract: A system comprises a computer including a processor and a memory, and the memory including instructions such that the processor is programmed to calculate, at a server, a distance between a fixed camera disposed within an environment and a vehicle traversing the environment based on at least two image frames captured by the fixed camera, wherein the at least two image frames depict the vehicle at different image coordinates; determine a position of the fixed camera based on the distance and vehicle distance measurements measured by a vehicle sensor; and generate a map representing the environment based on the position of the fixed camera and the vehicle distance measurements.
Type:
Grant
Filed:
January 24, 2020
Date of Patent:
October 26, 2021
Assignee:
Ford Global Technologies, LLC
Inventors:
Punarjay Chakravarty, Gintaras Vincent Puskorius
Abstract: Contract tracing systems and methods for infectious disease tracking are disclosed. An infectious disease tracking system includes a plurality of user devices, each user device configured to detect, using a wireless communication module, a signal emitted by another one of the plurality of user devices. The user device can determine that a strength of the signal exceeds a predetermined event initiation signal strength threshold corresponding to a physical proximity between users of the devices and can store a contact tracing event record in response to determining that the strength of the signal exceeds the predetermined event initiation signal strength threshold. The user device can transmit the contact tracing event records to a data center where they can be stored and used to identify close contacts when an index case of an infectious disease is identified.
Type:
Grant
Filed:
March 8, 2021
Date of Patent:
October 19, 2021
Assignee:
ROYAL CARIBBEAN CRUISES LTD.
Inventors:
Nicholas Weir, Ernesto M. Rubi, Daniel John Altin
Abstract: A computer system determines a likelihood of the presence of flame in a scene. The system obtains a series of digital infrared and optical images of the scene; identifies a candidate region in a location of the scene based on analysis of the infrared images; identifies an optical image slice based on analysis of the optical images and the location of the candidate region; and determines a likelihood of the presence of flame in the scene based on analysis of the optical image slice. Analysis of the infrared images includes detecting a high-temperature image region that exceeds a threshold temperature; detecting a turbulent motion image region; and determining whether the turbulent motion region is within a specified proximity of or overlaps with the high-temperature region. The optical image slice may be provided to a trained neural network, which returns a degree-of-confidence value that indicates whether flame is present.
Abstract: There is provided a parcel recognition device that recognizes parcel based on a color image including one or more parcels, the device including: a processor; and a memory, in which by cooperating with the memory, the processor estimates a region of the one or more parcels in the color image, switches a color of a background which is a region excluding the region of the one or more parcels in the color image, and recognizes each of the one or more parcels based on the background having the switched color and a color of the region of the parcel.
Abstract: An information processing apparatus and non-transitory computer readable medium are provided. The information processing apparatus includes a processor configured to: control a display to display a first space for a first conversation including a first message and a second space for a second conversation next to each other, the first conversation being a conversation of a first group including a first member, the second conversation being a conversation of a second group; in response to a first operation received on the display, control the display to display, in the second space, the first member of the first group or the first message of the first conversation. The first operation is a gesture moving along the display from a first place on the display to a second place on the display in contact the display.
Abstract: Methods and devices for operating a wireless communication device that can communicate with at least two different wireless networks using a single radio frequency modem are described. The communication device attaches to a first wireless network through the radio frequency (RF) modem, and then detaches from the first wireless network at a predetermined time before a start time of a selected event on a second wireless network. The device attaches to the second wireless network using the same RF modem before the start time of the selected event and collects at least a portion of event data associated with the selected event. After collecting at least a portion of event data, the device detaches from the second wireless network and re-attaches to the first wireless network.
Abstract: An information processing apparatus, non-transitory computer readable medium and method for processing information are provided. The information processing apparatus includes a processor configured to: control a display to display a first conversation space of a first group; and in response to a first operation being performed on the display, control the display to display a second conversation space of a second group that is different from the first group. The first conversation space includes a plurality of messages of the first group. The second conversation space includes a plurality of messages of the first group. The first operation is a gesture moving along the display from a first place on the display to a second place on the display in contact the display. The first operation starts while the first conversation space is being displayed.
Abstract: An apparatus for detecting an object includes a processor that extracts information for object detection from image data frames based on a hierarchical structure of a convolutional neural network (CNN) and transmits information for object detection extracted from an uppermost layer of the hierarchical structure to a lower layer to detect an object based on information received at each layer, and storage that stores the information for object detection and detected object information.
Type:
Grant
Filed:
March 7, 2019
Date of Patent:
September 7, 2021
Assignees:
Hyundai Motor Company, Kia Motors Corporation
Abstract: A mobile virtual network operator is provided. The operator includes a server that is communicatively coupled to a mobile device. The mobile device includes application software provided by the virtual network operator for allowing phone call and data connectivity.
Abstract: A mobile virtual network operator is provided. The operator includes a server that is communicatively coupled to a mobile device. The mobile device includes application software provided by the virtual network operator for allowing phone call and data connectivity.
Abstract: A method for approximating spectral data, the method comprising using at least one hardware processor for: providing a digital image comprising data in a first set of spectral bands; providing a dictionary comprising (a) signatures in a second set of spectral bands and (b) values in said first set of spectral bands, wherein said values correspond to the signatures, and wherein said first and second sets of spectral bands are different; and approximating, based on the dictionary, data in said second set of spectral bands of said digital image.
Type:
Grant
Filed:
September 6, 2017
Date of Patent:
August 10, 2021
Assignee:
B. G. NEGEV TECHNOLOGIES AND APPLICATIONS LTD.
Abstract: A system for displaying one or more images to select one or more matching formulas to match color and appearance of a target coating of an article includes a computing device, a display device, a host computer connected to the computing device, one or more data input devices, a first database containing repair formulas, color characteristics, and appearance characteristics, a second database containing identification information of an article or a three-dimensional model of an article or a three-dimensional mapping of a geometry of a part of an article, and a computer program product accessible to the computing device and/or the host computer and performing a computing process to retrieve at least one preliminary matching formula from the first database, select one article or a three-dimensional mapping of a geometry of one article from the second database, generate individual matching images, and display the individual matching images on the display device.
Type:
Grant
Filed:
August 29, 2019
Date of Patent:
August 3, 2021
Assignee:
AXALTA COATING SYSTEMS IP CO., LLC
Inventors:
Larry E. Steenhoek, Robert V. Canning, Jr.
Abstract: A method of detecting a 3D object from a 2D image includes receiving a 2D image including an object, acquiring an object detection region from the 2D image, iteratively searching for candidates for a direction of a volume including the object of the 2D image in a 3D coordinate system based on the object detection region, and detecting the volume from the 3D coordinate system based on results of the iterative searching.
Abstract: Methods, apparatus, systems and articles of manufacture to monitor the personal safety of a user of a portable electronic device are disclosed. Example portable electronic devices disclosed herein are to adjust a threshold alert level based on event information obtained for a location associated with the portable electronic device, the threshold alert level to indicate a degree of danger to which a user of the portable electronic device is exposed. Disclosed example portable electronic devices are also to determine that the threshold alert level has been satisfied when at least a threshold number of a set of usage attributes associated with the threshold alert level are detected in a monitored set of usage attributes. Disclosed example portable electronic devices are further to actuate an output device associated with the portable electronic device when the threshold alert level is satisfied.
Type:
Grant
Filed:
June 5, 2020
Date of Patent:
July 27, 2021
Assignee:
Intel Corporation
Inventors:
Olivia Melendez, Yuri Krimon, Yoganand Gandlur, Rathish Jayabharathi, Handeep Kaur, Daisy Rincon, Jorge L. Rojas, Rahul Sharma, Shidi Wang, Yan Mui Kitty Yeung
Abstract: A system and method for analyzing images using a non-transitory programmable device is disclosed. A user interface generator operating on the non-transitory programmable device receives specifications of a first image of a biological sample and a first image analysis step. A sequencer operating on the non-transitory programmable device applies the first image analysis step to the first image to develop annotated training data, and a machine learning system trainer operating on the non-transitory programmable device trains an untrained machine learning system to develop a trained machine learning system. When the trained machine learning system is presented with the first image as an input, the trained machine learning system develops a prediction of the annotated training data.