Patents by Inventor Ichiro Umeda

Ichiro Umeda has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10872262
    Abstract: An information processing apparatus includes an acquiring unit to acquire an input image including an object, an extraction unit to extract a region that has been changed from a background image in the input image, as a changing region, a generating unit to generate a change region image in which a pixel value of each pixel represents whether or not a corresponding pixel in the input image belongs to the changing region, an extraction unit to extract a plurality of feature images from the input image as an output of a neural network by inputting a combination of the input image and the change region image to the neural network, and a detection unit to detect a position of the object from the plurality of feature images.
    Type: Grant
    Filed: April 7, 2017
    Date of Patent: December 22, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventors: Kotaro Yano, Ichiro Umeda, Muling Guo, Hiroyuki Uchiyama
  • Patent number: 10572736
    Abstract: An image processing apparatus includes an acquiring unit configured to acquire multiple tracking results about an object tracked in multiple video images captured by multiple imaging units. The tracking results correspond one-to-one to the video images. Each of the tracking results contains a position of the object detected from an image frame of the corresponding video image and a tracking label that identifies the object in the video image. The apparatus further includes a relating unit configured to relate objects, detected from image frames of the video images, based on the tracking results acquired by the acquiring unit to obtain relations and an object label generating unit configured to generate an object label based on the relations obtained by the relating unit. The object label uniquely identifies the object across the video images.
    Type: Grant
    Filed: March 14, 2016
    Date of Patent: February 25, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventors: Hiroyuki Uchiyama, Ichiro Umeda, Muling Guo, Kotaro Yano
  • Patent number: 10515459
    Abstract: An image processing apparatus includes a detection unit configured to detect positions of an index of which an arrangement is sequentially changed from respective images captured by two imaging devices, a calibration unit configured to calibrate a position of at least one of the two imaging devices based on the positions of the index arranged at an identical position detected from the respective images captured by the two imaging devices, a determination unit configured to determine a candidate position where the index is to be newly arranged based on the positions where the index has already been detected, and a presentation unit configured to present the candidate position.
    Type: Grant
    Filed: August 7, 2017
    Date of Patent: December 24, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventors: Hiroyuki Uchiyama, Kotaro Yano, Ichiro Umeda, Muling Guo
  • Patent number: 10417773
    Abstract: An image processing apparatus includes an obtaining unit configured to obtain a moving image, a detection unit configured to detect a detection target object from an interest image frame in the moving image, a tracking unit configured to obtain a tracked object in a neighborhood region of a detection position of the detection target object in an image frame preceding the interest image frame in the moving image, and a determination unit configured to determine whether or not the tracked object corresponds to the detection target object by integrating a position where the detection target object is detected by the detection unit and a position where the tracked object is obtained by the tracking unit.
    Type: Grant
    Filed: March 1, 2016
    Date of Patent: September 17, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventors: Kotaro Yano, Ichiro Umeda, Muling Guo, Lifeng Xu
  • Publication number: 20190205688
    Abstract: An information processing apparatus acquires an input image including an object, extracts, from the input image, a change region image which is an image of a changing region by using a background image, extracts a plurality of feature images by combining the input image and the change region image and using a convolutional neural network, and detects a position of the object from the plurality of feature images.
    Type: Application
    Filed: April 7, 2017
    Publication date: July 4, 2019
    Inventors: Kotaro Yano, Ichiro Umeda, Muling Guo, Hiroyuki Uchiyama
  • Patent number: 10212324
    Abstract: An image processing device includes a detection unit configured to detect an object from an image captured by each of a plurality of image capturing devices, a determination unit configured to determine whether the object is detected by two image capturing devices or more in the image capturing devices, a first estimation unit configured to estimate, when the object have been detected by the two image capturing devices or more, a three-dimensional position and information on a height of the object based on a detected position where the object is detected in an image captured for each of the two image capturing devices and positions and orientations of the two image capturing devices, and a second estimation unit configured to estimate, when the object have been detected by a single image capturing device, the three-dimensional position of the object.
    Type: Grant
    Filed: November 29, 2016
    Date of Patent: February 19, 2019
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Hiroyuki Uchiyama, Kotaro Yano, Ichiro Umeda, Muling Guo
  • Publication number: 20180101732
    Abstract: An image processing apparatus includes an acquiring unit configured to acquire multiple tracking results about an object tracked in multiple video images captured by multiple imaging units. The tracking results correspond one-to-one to the video images. Each of the tracking results contains a position of the object detected from an image frame of the corresponding video image and a tracking label that identifies the object in the video image. The apparatus further includes a relating unit configured to relate objects, detected from image frames of the video images, based on the tracking results acquired by the acquiring unit to obtain relations and an object label generating unit configured to generate an object label based on the relations obtained by the relating unit. The object label uniquely identifies the object across the video images.
    Type: Application
    Filed: March 14, 2016
    Publication date: April 12, 2018
    Inventors: Hiroyuki Uchiyama, Ichiro Umeda, Muling Guo, Kotaro Yano
  • Patent number: 9934446
    Abstract: An image processing apparatus acquires an image including an object and divides the image into a plurality of superpixels based on similarity of adjacent pixels. There is an acquisition, from the superpixels, of a plurality of candidate areas acting as candidates of an area of the object. A feature quantity is extracted from each of the plurality of candidate areas and checked against registered information concerning a feature quantity of object area. The area of the object in the image is output, based on a checked result.
    Type: Grant
    Filed: November 5, 2014
    Date of Patent: April 3, 2018
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Kotaro Yano, Ichiro Umeda
  • Publication number: 20180047184
    Abstract: An image processing apparatus includes a detection unit configured to detect positions of an index of which an arrangement is sequentially changed from respective images captured by two imaging devices, a calibration unit configured to calibrate a position of at least one of the two imaging devices based on the positions of the index arranged at an identical position detected from the respective images captured by the two imaging devices, a determination unit configured to determine a candidate position where the index is to be newly arranged based on the positions where the index has already been detected, and a presentation unit configured to present the candidate position.
    Type: Application
    Filed: August 7, 2017
    Publication date: February 15, 2018
    Inventors: Hiroyuki Uchiyama, Kotaro Yano, Ichiro Umeda, Muling Guo
  • Patent number: 9877012
    Abstract: An image processing apparatus includes a holding unit configured to hold a positional relationship of a plurality of image capturing units, an acquisition unit configured to detect objects from respective images captured by the plurality of image capturing units and acquire positions of the objects on the captured images and geometric attributes of the objects, an associating unit configured to associate the detected objects, based on the positional relationship, the positions and the geometric attributes, and an estimation unit configured to estimate a three-dimensional position of the objects based on the positional relationship and the positions of the detected objects.
    Type: Grant
    Filed: March 29, 2016
    Date of Patent: January 23, 2018
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Hiroyuki Uchiyama, Muling Guo, Kotaro Yano, Ichiro Umeda
  • Patent number: 9773322
    Abstract: An image processing apparatus includes a plurality of dictionaries configured to store a feature of an object and information on an imaging direction in a scene for each kind of imaged scene, a detecting unit configured to detect an object with reference to at least one of the plurality of dictionaries in the scene in which the object has been imaged and which is to be learned, an estimating unit configured to estimate the imaging direction the detected object, a selecting unit configured to select one dictionary from the plurality of dictionaries based on the imaging direction estimated by the estimating unit and the information on the imaging direction in each of the plurality of dictionaries, and a learning unit configured to learn the dictionary selected by the selecting unit, based on a detection result produced by the detecting unit.
    Type: Grant
    Filed: June 25, 2015
    Date of Patent: September 26, 2017
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Hiroyuki Uchiyama, Ichiro Umeda, Muling Guo, Kotaro Yano
  • Publication number: 20170154424
    Abstract: An image processing device includes a detection unit configured to detect an object from an image captured by each of a plurality of image capturing devices, a determination unit configured to determine whether the object is detected by two image capturing devices or more in the image capturing devices, a first estimation unit configured to estimate, when the object have been detected by the two image capturing devices or more, a three-dimensional position and information on a height of the object based on a detected position where the object is detected in an image captured for each of the two image capturing devices and positions and orientations of the two image capturing devices, and a second estimation unit configured to estimate, when the object have been detected by a single image capturing device, the three-dimensional position of the object.
    Type: Application
    Filed: November 29, 2016
    Publication date: June 1, 2017
    Inventors: Hiroyuki Uchiyama, Kotaro Yano, Ichiro Umeda, Muling Guo
  • Publication number: 20160350615
    Abstract: An image processing apparatus includes a setting unit that sets a detection area for detecting an object within an image captured by an image capturing apparatus and a correction unit that corrects a position of at least one of a plurality of detection areas to reduce a difference between angles corresponding to each detection area set by the setting unit and an image capturing direction of the image capturing apparatus.
    Type: Application
    Filed: May 19, 2016
    Publication date: December 1, 2016
    Inventors: Kotaro Yano, Ichiro Umeda, Muling Guo
  • Patent number: 9489566
    Abstract: There are provided an image recognition apparatus and an image recognition method according to which, when registering a face model for a face image, face images are sequentially acquired from frames of a moving image, feature amounts are extracted from the sequentially acquired face images, and a hypersphere defined by Support Vector Data Description (SVDD) is obtained from the group of training samples. Then, training samples in a boundary region of the hypersphere are registered as boundary samples. When performing matching of a face image of a recognition target, the reliability is calculated using the boundary samples, and a person with the highest reliability is output as a recognition result.
    Type: Grant
    Filed: August 14, 2013
    Date of Patent: November 8, 2016
    Assignee: Canon Kabushiki Kaisha
    Inventors: Kotaro Yano, Ichiro Umeda, Hiroshi Sato
  • Publication number: 20160292533
    Abstract: An image processing apparatus includes a holding unit configured to hold a positional relationship of a plurality of image capturing units, an acquisition unit configured to detect objects from respective images captured by the plurality of image capturing units and acquire positions of the objects on the captured images and geometric attributes of the objects, an associating unit configured to associate the detected objects, based on the positional relationship, the positions and the geometric attributes, and an estimation unit configured to estimate a three-dimensional position of the objects based on the positional relationship and the positions of the detected objects.
    Type: Application
    Filed: March 29, 2016
    Publication date: October 6, 2016
    Inventors: Hiroyuki Uchiyama, Muling Guo, Kotaro Yano, Ichiro Umeda
  • Publication number: 20160260226
    Abstract: An image processing apparatus includes an obtaining unit configured to obtain a moving image, a detection unit configured to detect a detection target object from an interest image frame in the moving image, a tracking unit configured to obtain a tracked object in a neighborhood region of a detection position of the detection target object in an image frame preceding the interest image frame in the moving image, and a determination unit configured to determine whether or not the tracked object corresponds to the detection target object by integrating a position where the detection target object is detected by the detection unit and a position where the tracked object is obtained by the tracking unit.
    Type: Application
    Filed: March 1, 2016
    Publication date: September 8, 2016
    Inventors: Kotaro Yano, Ichiro Umeda, Muling Guo, Lifeng Xu
  • Publication number: 20160140399
    Abstract: An object detection apparatus includes an extraction unit configured to extract a plurality of partial areas from an acquired image, a distance acquisition unit configured to acquire a distance from a viewpoint for each pixel in the extracted partial area, an identification unit configured to identify whether the partial area includes a predetermined object, a determination unit configured to determine, among the partial areas identified to include the predetermined object by the identification unit, whether to integrate identification results of a plurality of partial areas that overlap each other based on the distances of the pixels in the overlapping partial area, and an integration unit configured to integrate the identification results of the plurality of partial areas determined to be integrated to detect a detection target object from the integrated identification result of the plurality of partial areas.
    Type: Application
    Filed: November 13, 2015
    Publication date: May 19, 2016
    Inventors: Kotaro Yano, Ichiro Umeda
  • Publication number: 20160004935
    Abstract: An image processing apparatus includes a plurality of dictionaries configured to store a feature of an object and information on an imaging direction in a scene for each kind of imaged scene, a detecting unit configured to detect an object with reference to at least one of the plurality of dictionaries in the scene in which the object has been imaged and which is to be learned, an estimating unit configured to estimate the imaging direction the detected object, a selecting unit configured to select one dictionary from the plurality of dictionaries based on the imaging direction estimated by the estimating unit and the information on the imaging direction in each of the plurality of dictionaries, and a learning unit configured to learn the dictionary selected by the selecting unit, based on a detection result produced by the detecting unit.
    Type: Application
    Filed: June 25, 2015
    Publication date: January 7, 2016
    Inventors: Hiroyuki Uchiyama, Ichiro Umeda, Muling Guo, Kotaro Yano
  • Publication number: 20150138386
    Abstract: An image processing apparatus comprises: an image acquiring unit to acquire an image including an object; a dividing unit to divide the image, which is acquired by the image acquiring unit, into a plurality of superpixels based on similarity of adjacent pixels; a candidate area acquiring unit to acquire, from the superpixels divided by the dividing unit, a plurality of candidate areas acting as candidates of an area of the object; an extracting unit to extract a feature quantity from each of the plurality of candidate areas acquired by the candidate area acquiring unit; a checking unit to check the feature quantity, which is extracted from each candidate area by the extracting unit, against registered information concerning a feature quantity of object area; and an outputting unit to output the area of the object in the image, based on a checked result by the checking unit.
    Type: Application
    Filed: November 5, 2014
    Publication date: May 21, 2015
    Inventors: Kotaro Yano, Ichiro Umeda
  • Patent number: 8873839
    Abstract: There are provided a characteristic obtaining unit configured to obtain a subject characteristic including a characteristic of a subject, an image processing unit configured to generate a duplicate subject image by performing an image process to an image of the subject according to the subject characteristic obtained by the characteristic obtaining unit, and a learning unit configured to learn a matching dictionary by using the duplicate subject image generated by the image processing unit. Thus, it is possible to reduce the number of subject images necessary for the learning.
    Type: Grant
    Filed: October 7, 2010
    Date of Patent: October 28, 2014
    Assignee: Canon Kabushiki Kaisha
    Inventor: Ichiro Umeda