Patents Examined by Tsung-Yin Tsai
  • Patent number: 10467473
    Abstract: A computer-implemented method for processing images to identify Energy Infrastructure (EI) features within aerial images of global terrain is provided. The image processing method identifies information about EI features by applying an EI feature recognition model to aerial images of global terrain. The EI feature recognition model identifies the EI feature information according to image content of the aerial image and according to supplemental information about EI features in the global terrain. The method further uses the results of the identification to update the EI feature recognition model.
    Type: Grant
    Filed: May 29, 2019
    Date of Patent: November 5, 2019
    Assignee: SOURCEWATER, INC.
    Inventor: Joshua Adler
  • Patent number: 10460444
    Abstract: Disclosed is a memory device including plural bit lines, plural word lines and a control circuit. The bit lines are configured to receive pixel data of an image. Each word line includes plural factor units. The factor units of each word line are configured differently according to plural factors of a filter. When processing a first area of the image by the filter, the control circuit inputs the pixel data within the first area of the image to the bit lines, and enables one of the word lines for operation. When processing a second area of the image by the filter, the control circuit maintains the pixel data within the second area overlapping the first area on the bit lines, and inputs the pixel data within the second area which doesn't overlap the first area to the bit lines, and enables another one of the word lines for operation.
    Type: Grant
    Filed: March 16, 2018
    Date of Patent: October 29, 2019
    Assignee: MACRONIX INTERNATIONAL CO., LTD.
    Inventors: Yu-Yu Lin, Feng-Min Lee
  • Patent number: 10460170
    Abstract: A computer-implemented method for processing images to determine EI site status is provided. The method includes image processing of an aerial image by two EI feature recognition models. A first EI feature recognition model recognizes a first EI feature and a second EI feature recognition model recognizes a second EI feature. The results of each model are further used to determine a composite indication of EI site status.
    Type: Grant
    Filed: May 29, 2019
    Date of Patent: October 29, 2019
    Assignee: SOURCEWATER, INC.
    Inventor: Joshua Adler
  • Patent number: 10460194
    Abstract: A technique and system for counting the number of repetitions of approximately the same action in an input video sequence using 3D convolutional neural networks is disclosed. The proposed system runs online and not on the complete video. It analyzes sequentially blocks of 20 non-consecutive frames. The cycle length within each block is evaluated using a deep network architecture and the information is then integrated over time. A unique property of the disclosed method is that it is shown to successfully train on entirely synthetic data, created by synthesizing moving random patches. It therefore effectively exploits the high generalization capability of deep neural networks. Coupled with a region of interest detection mechanism and a suitable mechanism to identify the time scale of the video, the system is robust enough to handle real world videos collected from YouTube and elsewhere, as well as non-video signals such as sensor data revealing repetitious physical movement.
    Type: Grant
    Filed: March 6, 2015
    Date of Patent: October 29, 2019
    Inventors: Lior Wolf, Ofir Levy
  • Patent number: 10458776
    Abstract: An abrasion inspection apparatus includes: a first imaging unit installed on a track along which a vehicle is traveling, a guide wheel installed on the vehicle, the first imaging unit imaging an inside of the track; a second imaging unit installed on the track in a vehicle traveling direction with respect to the first imaging unit and imaging the inside of the track; an image acquisition unit acquiring a first image of a boundary of the guide wheel captured by the first imaging unit on a first direction side in the vehicle traveling direction, and a second image of the boundary of the guide wheel captured by the second imaging unit at the same time on an opposite side to the first direction side; and a guide wheel detection unit detecting an abrasion situation of the guide wheel according to a position of a boundary indicated in the acquired images.
    Type: Grant
    Filed: November 20, 2015
    Date of Patent: October 29, 2019
    Assignee: MITSUBISHI HEAVY INDUSTRIES, LTD.
    Inventors: Katsuaki Morita, Masahiro Yamada, Kazuki Ozaki, Hiroyuki Kono
  • Patent number: 10460169
    Abstract: A computer-implemented method for processing images to identify Energy Infrastructure (EI) features within aerial images of global terrain is provided. The image processing method identifies information about EI features by applying an EI feature recognition model to aerial images of global terrain. The EI feature recognition model identifies the EI feature information according to image content of the aerial image. The method further provides updates to the identification of the EI feature information according to relationships between identified EI features.
    Type: Grant
    Filed: May 29, 2019
    Date of Patent: October 29, 2019
    Assignee: SOURCEWATER, INC.
    Inventor: Joshua Adler
  • Patent number: 10452904
    Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining a document image, wherein the document image includes a plurality of objects; identifying a plurality of macroblocks within the document image; performing microblock processing within macroblocks of the plurality of macroblocks, wherein the microblock processing includes examining content of microblocks within a macroblock for extraction of key-value pairs, the examining content including performing an ontological analysis of microblocks, wherein the microblock processing includes associating confidence levels to the extracted key-value pairs; and outputting metadata based on the performing microblock processing within macroblocks of the plurality of macroblocks.
    Type: Grant
    Filed: December 1, 2017
    Date of Patent: October 22, 2019
    Assignee: International Business Machines Corporation
    Inventors: Kevin Northrup, Craig M. Trim, Terry Hickey, Thozamile Javu
  • Patent number: 10453205
    Abstract: The invention is directed to a method of identifying at least one type of surface in a digital image, comprising the steps of: (a) dividing (4) the image (2) in sub-images of the same size; (b) analyzing (6) the sub-images for identifying at least one type of surface; (c) sub-dividing (10) into sub-images each of the sub-images (8) of the preceding step where at least one type of surface is not identified; (d) analyzing (6) the sub-images of step (c) for identifying at least one type of surface; and (e) iterating steps (c) and (d). This is a hierarchical split based approach (HSBA) that can be used for detecting water zones in a Synthetic Aperture Radar (SAR) image.
    Type: Grant
    Filed: July 5, 2016
    Date of Patent: October 22, 2019
    Assignee: Luxembourg Institute of Science and Technology (LIST)
    Inventors: Renaud Hostache, Marco Chini, Patrick Matgen, Laura Giustarini
  • Patent number: 10445904
    Abstract: A method for the automatic generation of synthetic projections of an examination object from at least one three-dimensional data set acquired by way of a medical imaging system. The three-dimensional data set is used as a basis for determining position information relating to the arrangement of structures of the examination object and at least one synthetic projection based on the position information. We also describe a projection-image-ascertaining facility for the automatic generation of synthetic projections and a computer program product for executing the method.
    Type: Grant
    Filed: August 23, 2017
    Date of Patent: October 15, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Anna Jerebko, Andreas Fieselmann, Christoph Luckner
  • Patent number: 10445611
    Abstract: A method for detecting at least one pseudo-3D bounding box based on a CNN capable of converting modes according to conditions of objects in an image is provided. The method includes steps of: a learning device (a) instructing a pooling layer to generate a pooled feature map corresponding to a 2D bounding box, and instructing a type-classifying layer to determine whether objects in the pooled feature map are truncated or non-truncated; (b) instructing FC layers to generate box pattern information corresponding to the pseudo-3D bounding box; (c) instructing classification layers to generate orientation class information on the objects, and regression layers to generate regression information on coordinates of the pseudo-3D bounding box; and (d) backpropagating class losses and regression losses generated from FC loss layers. Through the method, rendering of truncated objects can be performed while virtual driving, and this is useful for mobile devices and also for military purpose.
    Type: Grant
    Filed: January 25, 2019
    Date of Patent: October 15, 2019
    Assignee: Stradvision, Inc.
    Inventors: Kye-Hyeon Kim, Yongjoong Kim, Insu Kim, Hak-Kyoung Kim, Woonhyu Nam, SukHoon Boo, Myungchul Sung, Donghun Yeo, Wooju Ryu, Taewoong Jang, Kyungjoong Jeong, Hongmo Je, Hojin Cho
  • Patent number: 10432976
    Abstract: The present technology relates to an image processing apparatus and method that are capable of enhancing encoding efficiency while suppressing a decrease in the efficiency of encoding processing. The image processing apparatus includes an encoding mode setter that sets, in units of coding units having a hierarchical structure, whether a non-compression mode is to be selected as an encoding mode for encoding image data, the non-compression mode being an encoding mode in which the image data is output as encoded data, and an encoder that encodes the image data in units of the coding units in accordance with a mode set by the encoding mode setter. The present disclosure can be applied to, for example, an image processing apparatus.
    Type: Grant
    Filed: January 25, 2018
    Date of Patent: October 1, 2019
    Assignee: VELOS MEDIA, LLC
    Inventor: Kazushi Sato
  • Patent number: 10419646
    Abstract: The present invention provides a gamma setting system for a display device including: an optical measuring unit measuring an optical property of a display device including an emissive display panel having red, green and blue sub-pixels; a control center performing a null setting step and an automatic setting step using the optical property of the display device; a system driving unit transmitting a result data between the display device and the control center; a first display unit displaying a TW target luminance, a TW target chromaticity and an RGB inherent chromaticity registered for the null setting step and the automatic setting step, a graph of a gray level voltage and a luminance of an RGB and a TW with respect to a gray level, a high level cell driving voltage (PVDD) and a low level cell driving voltage (PVEE) applied to an emitting element, a high level gamma source voltage (VDDH) and a low level gamma source voltage (VDDL) applied to a driving IC, a gamma slope, a contrast ratio, a driving type of th
    Type: Grant
    Filed: August 3, 2015
    Date of Patent: September 17, 2019
    Inventor: Tae-Bo Jung
  • Patent number: 10416680
    Abstract: An illustrative example embodiment of a detector device, which may be useful on an automated vehicle, includes an array of detectors arranged in one dimension. The array includes a plurality of first detectors and a plurality of second detectors. The first detectors respectively have one of the second detectors between the first detector and an adjacent one of the first detectors. The first detectors respectively are spaced from the one of the second detectors by a first distance. The one of the second detectors are respectively spaced from the adjacent one of the first detectors by a second distance that is larger than the first distance. The first detectors are spaced from each other by a third distance that is a sum of the first and second distance. The second detectors are also spaced from each other by the third distance.
    Type: Grant
    Filed: August 18, 2017
    Date of Patent: September 17, 2019
    Assignee: APTIV TECHNOLOGIES LIMITED
    Inventors: Zhengzheng Li, Carlos Alcalde
  • Patent number: 10395371
    Abstract: The present invention relates to systems and methods for adaptively optimizing broadband reference spectra for a multi-spectral image or adaptively optimizing reference colors for a bright-field image. The methods and systems of the present invention involve optimization techniques that are based on structures detected in an unmixed channel of the image, and involves detecting and segmenting structures from a channel, updating a reference matrix with signals estimated from the structures, subsequently unmixing the image using the updated reference matrix, and iteratively repeating the process until an optimized reference matrix is achieved.
    Type: Grant
    Filed: March 29, 2016
    Date of Patent: August 27, 2019
    Assignee: Ventana Medical Systems, Inc.
    Inventors: Ting Chen, Srinivas Chukka, Anindya Sarkar
  • Patent number: 10395365
    Abstract: In a method and computer for determining an imaging parameter for an imaging procedure, a patient-specific imaging value for imaging an image data set is provided to a computer. An imaging parameter is determined in the computer by applying a trained imaging rule to the patient-specific imaging value. The trained imaging rule is based on a number of training data sets, wherein the training data sets each includes at least one patient-specific training imaging value and at least one training imaging parameter and at least one training quality evaluation. The complex influences of the patient-specific imaging values and the imaging parameters on the result of imaging can be quantified thereby. Allocation of the training quality evaluation by individual operators or specific groups of operators makes it possible to adjust the image recording parameters flexibly and individually. The imaging parameter can be determined such that the result of imaging is individually adjusted to an operator.
    Type: Grant
    Filed: October 13, 2017
    Date of Patent: August 27, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Bernhard Schmidt, Thomas Flohr
  • Patent number: 10395621
    Abstract: A method of modifying a font character. An outline of the font character is received, the outline being a vector representation of the character. A slant angle parameter to be applied to the font outline is received, the slant angle specifying an amount of shearing to be applied to the font outline. A modified stroke width is determined for each segment of the font outline according to an initial angle of the segment and the slant angle, the modified stroke width being proportional to ratio of a length of the segment before and after applying the slant angle to the outline. The modified stroke width is used for adjusting an initial stroke width of the segment to compensate for changes to stroke width of the segment caused by applying the slant angle. The font character is rendered using the modified stroke width of the segments.
    Type: Grant
    Filed: December 14, 2016
    Date of Patent: August 27, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Albert Chang
  • Patent number: 10395385
    Abstract: In various implementations, object tracking in a video content analysis system can be augmented with an image-based object re-identification system (e.g., for person re-identification or re-identification of other objects) to improve object tracking results for objects moving in a scene. The object re-identification system can use image recognition principles, which can be enhanced by considering data provided by object trackers that can be output by an object traffic system. In a testing stage, the object re-identification system can selectively test object trackers against object models. For most input video frames, not all object trackers need be tested against all object models. Additionally, different types of object trackers can be tested differently, so that a context provided by each object tracker can be considered. In a training stage, object models can also be selectively updated.
    Type: Grant
    Filed: June 27, 2017
    Date of Patent: August 27, 2019
    Assignee: QUALCOMM Incorporated
    Inventors: Yang Zhou, Ying Chen, Yingyong Qi, Ning Bi
  • Patent number: 10380750
    Abstract: An image depth calculating device, which can calculate depth information of a binocular video with reduced computation, includes multiple modules. Modules receives a first frame information set that corresponds to a first frame time of the binocular video and establishes a first rhombic area that centers on a first pixel in a first viewing angle frame, to calculate a total pixel value of the first rhombic area. Modules further establishes a plurality of second rhombic areas that center on a plurality of second pixels of a pixel area in a second viewing angle frame to calculate a second total pixel value of each of the plurality of second rhombic areas. A depth calculating module compares the first total pixel value with each second total pixel value and calculates first frame depth information according to the result. An image depth calculating method is also provided.
    Type: Grant
    Filed: August 2, 2017
    Date of Patent: August 13, 2019
    Assignee: HON HAI PRECISION INDUSTRY CO., LTD.
    Inventors: Chih-Te Lu, Tung-Tso Tsai, Jung-Hao Yang, Chih-Yuan Chuang, Chin-Pin Kuo, Tsung-Yuan Tu
  • Patent number: 10373338
    Abstract: A calculation device comprises a controller configured to extract, from a captured image of a subject, a plurality of lines corresponding to straight lines parallel to each other in the subject, and to calculate first calibration data so that mapping lines obtained when the extracted plurality of lines are mapped to a three-dimensional coordinate space are parallel to each other.
    Type: Grant
    Filed: May 26, 2016
    Date of Patent: August 6, 2019
    Assignee: KYOCERA Corporation
    Inventors: Shushin Inoue, Tomofumi Koishi
  • Patent number: 10372986
    Abstract: A method and device for detecting an overhead cable from an aerial vessel, for instance from a helicopter in motion, and specifically for use in a landing preparing procedure. The method includes providing, from a camera arranged in the aerial vessel, a plurality of images of an area beneath the aerial vessel when the aerial vessel is in motion; detecting lines in the images; determining if the lines represent lines at ground level or lines at a level above ground level; and determining if a line at a level above ground level represents a possible overhead cable. The step of detecting lines in the images may include a modified SUSAN algorithm. The step of determining if the lines represent lines at ground level or lines above ground level may include parallax calculation.
    Type: Grant
    Filed: December 22, 2015
    Date of Patent: August 6, 2019
    Assignee: Kleon Prosjekt AS
    Inventors: Aasmund Barikmo, Arne Sommerfelt