Patents Examined by Siamak Harandi
-
Patent number: 12293560Abstract: A method for context based separation between vehicle pixels and background pixels, which may include receiving a first image and a second image, the first image and the second images are of temporarily adjacent to each other and capture a same vehicle and background content. The method may also include obtaining a first bounding box that surrounds at least a part of the vehicle within the first image; wherein the first bounding has a first width and a first height; obtaining a second bounding box that surrounds at least the part of the vehicle within the second image; wherein the second bounding box has a second width and a second height; obtaining a mapping between pairs of initially matched pixels, wherein each pair comprises a first pixel and a second pixel that correspond to same entity portion, wherein the entity portion is a portion of the vehicle or of the background content.Type: GrantFiled: October 26, 2022Date of Patent: May 6, 2025Assignee: AUTOBRAINS TECHNOLOGIES LTDInventors: Kirill Diagilev, Shiyong Lin
-
Patent number: 12283022Abstract: The present invention provides an image processing method, wherein the image processing method includes the steps of: receiving an image signal, wherein the image signal comprises a first frame and a second frame; performing motion estimation on the first frame and the second frame to generate an interpolated frame; for each of a plurality of areas of the interpolated frame, determining whether there is a block in the first frame that moves to the area, and determine whether there is a block in the second frame that moves to the area, to determine whether the area belongs to a cover area or an uncover area; and in response to a determination result indicating that the area belongs to the cover area or the uncover area, adjusting image contents of the interpolated frame.Type: GrantFiled: June 16, 2022Date of Patent: April 22, 2025Assignee: Realtek Semiconductor Corp.Inventors: Guangyu San, Fangqi Xiong
-
Patent number: 12283088Abstract: The invention relates to a method for determining a driving corridor for a motor vehicle (1). The motor vehicle (10) comprises at least one camera (22) and a control unit (24), the camera (24) being designed to generate images of a front region (30) in front of the motor vehicle (10) and to forward these images to the control unit (24). The control unit (24) comprises a machine learning module (28) having an artificial neural network. The method comprises the following steps: an image of the front region (30) in front of the motor vehicle (10) is obtained by the at least one camera (22); characteristic image features of the image are extracted by means of the artificial neural network; by means of the same artificial neural network, image points (32) which delimit the driving corridor of the motor vehicle (10) and/or at least one driving corridor adjacent to the driving corridor are determined on the basis of the extracted characteristic image features.Type: GrantFiled: November 21, 2019Date of Patent: April 22, 2025Assignee: ZF AUTOMOTIVE GERMANY GMBHInventors: Manuel Schmidt, Christian Wissing, Andreas Homann, Christian Lienke, Torsten Bertram, Martin Krüger, Till Nattermann, Karl-Heinz Glander
-
Patent number: 12276960Abstract: A method for use with a multibody system includes two body sections assembled via a joint, one of the body sections including a camera which is moveable between a first position and a second position, includes detecting a reference object with the camera situated in the first position, determining a reference value of the reference object, requesting movement of the camera from the first position into the second position, initiating movement of the camera from the first position towards the second position, while iteratively sampling image of the reference object, determining a current object value of the reference object, based on the sampled image, matching the reference value with the current object value, and determining successfulness of the camera movement, based on the matching.Type: GrantFiled: December 10, 2020Date of Patent: April 15, 2025Assignee: DeLaval Holding ABInventor: Andreas Eriksson
-
Patent number: 12277728Abstract: A pupil detection device includes an eye area image obtaining unit that obtains image data representing an eye area image in a captured image obtained by a camera; a luminance gradient calculating unit that calculates luminance gradient vectors corresponding to respective individual image units in the eye area image, using the image data; an evaluation value calculating unit that calculates evaluation values corresponding to the respective individual image units, using the luminance gradient vectors; and a pupil location detecting unit that detects a pupil location in the eye area image, using the evaluation values.Type: GrantFiled: January 8, 2020Date of Patent: April 15, 2025Assignee: Mitsubishi Electric CorporationInventors: Atsushi Matsumoto, Ryosuke Torama, Shintaro Watanabe, Ryohei Murachi
-
Patent number: 12277801Abstract: A gesture recognition method includes: acquiring a target image containing a gesture to be recognized; inputting the target image to a gesture recognition model that has a first sub-model, a second sub-model, and a third sub-model, the first sub-model is to determine a gesture category and a gesture center point, the second sub-model is to determine an offset of the gesture center point, and the third sub-model is to determine a length and a width of a bounding box for the gesture to be recognized; acquiring an output result from the gesture recognition model, the output result includes the gesture category, the gesture center point, and the offset of the gesture center point, and the length and the width of the bounding box; and determining the gesture category and a position of the bounding box of the gesture to be recognized according to the output result.Type: GrantFiled: December 31, 2021Date of Patent: April 15, 2025Assignee: UBTECH ROBOTICS CORP LTDInventors: Chenghao Qian, Miaochen Guo, Jun Cheng, Jianxin Pang
-
Patent number: 12274573Abstract: A wall thickness estimation method includes: obtaining behavioral information based on a video in which an organ wall or a blood vessel wall is captured using four-dimensional angiography, the behavioral information being numerical information about changes over time in a position of each of a plurality of predetermined points in the organ wall or the blood vessel wall; generating, based on the behavioral information obtained in the obtaining, estimation information that visualizes mass of each of the plurality of predetermined points for estimating a thickness of the organ wall or a thickness of the blood vessel wall; and outputting the estimation information generated in the generating.Type: GrantFiled: August 19, 2021Date of Patent: April 15, 2025Assignee: OSAKA UNIVERSITYInventor: Yoshie Sugiyama
-
Patent number: 12277725Abstract: The disclosed techniques provide enhanced eye tracking systems utilizing joint estimation of biological parameters and hardware parameters. A system uses joint estimation of biological parameters, e.g., direction and position of an eye, with concurrent estimation of hardware parameters, e.g., camera position or camera direction, to self-calibrate and provide eye tracking estimations to accommodate for deformations and other changes of a device. Sensor data is used to select hardware parameters of a camera for use in the joint estimation with the biological parameters, where the hardware parameters are estimated based on glint and pupil position of a user. The disclosed techniques include a method to model changes of a device, as well as detect and compensate for them while the eye-tracking device is in normal use, without requiring a factory-calibration procedure to be repeated.Type: GrantFiled: October 20, 2021Date of Patent: April 15, 2025Assignee: Microsoft Technology Licensing, LLCInventors: Paulo Ricardo Dos Santos Mendonca, Rayna Demaster-Smith, Christopher Charles Aholt, Christopher Maurice Mei
-
Patent number: 12272090Abstract: An information processing apparatus includes: a controller that identifies a non-processing target subject, among multiple subjects in a frame included in a dynamic image, as a non-processing target that is not subjected to predetermined image processing, on a basis of positional relationships between multiple subject areas corresponding to the respective multiple subjects and a specific area in the frame; and an image processor that performs the predetermined image processing on a processing target area corresponding to a processing target subject other than the non-processing target subject, among the multiple subjects.Type: GrantFiled: August 11, 2020Date of Patent: April 8, 2025Assignee: SONY GROUP CORPORATIONInventor: Kazuhiro Shimauchi
-
Patent number: 12272089Abstract: A method includes identifying an image captured by an image capture device set at a first angle about an axis, the image corresponding to a time at which the image was captured, identifying within the image, a region of interest including an object to be used for calibration, determining, an image coordinate at which the object is displayed within the image, determining a camera angle corresponding to a position of the image capture system relative to the axis when the image was captured, identifying a bearing of the object relative to the reference direction, the bearing of the object determined using a geolocation of the image capture system and the time at which the image was captured, and determining, using the image coordinate, the camera angle, and the bearing of the object, an angular offset between the first angle and the reference direction to determine a second angle.Type: GrantFiled: September 23, 2024Date of Patent: April 8, 2025Assignee: Pano AI, Inc.Inventors: Sonia Kastner, John Royero, Seva Safris, Nicholas Reid, Kira Greco
-
Patent number: 12268494Abstract: Disclosed are a method and a device for obtaining a safe interval of a human body parameter in a built environment, a terminal device, and a storage medium. The method includes: obtaining a first facial image, a benchmark human body parameter, and a human body posture analysis result of a target user in a target built environment; inputting the first facial image into an emotion analysis model to obtain an emotion analysis result; and obtaining the safe interval of the human body parameter of the target user according to the emotion analysis result, the human body posture analysis result, and the benchmark human body parameter.Type: GrantFiled: January 19, 2022Date of Patent: April 8, 2025Assignee: Chongqing UniversityInventors: Runming Yao, Shaoxing Zhang, Chenqiu Du, Baizhan Li
-
Patent number: 12266202Abstract: The present disclosure in some embodiments provides an artificial intelligence or AI-based document classification apparatus and method for providing, based on a hierarchical attention network (HAN) and a semantic analysis technique, an evaluation of a document, and an explainable basis or supporting data for the evaluation, thereby generating an evaluation index for the document.Type: GrantFiled: October 20, 2021Date of Patent: April 1, 2025Assignee: HYUNDAI MOBIS CO., LTD.Inventors: Tae Hyun Kim, Eunbin Kim, Jung Kyu Kim
-
Patent number: 12266086Abstract: In one aspect, a method to reduce compression artefacts, includes generating a first set of weights based on pixel value differences, producing a soft binned histogram from values in a neighborhood of pixels, generating an adapted histogram from the soft binned histogram using interpolation, generating occurrence density weights from the adapted histogram, combining the first set of weights and the occurrence density weights, filtering pixel values a bilateral filter using the combined weights, mixing the filtered pixel values and original pixel values, and outputting the mix of filtered pixel values and original pixel values.Type: GrantFiled: February 22, 2022Date of Patent: April 1, 2025Assignee: V-Silicon Semiconductor (Hefei) Co., LtdInventor: Jeroen Maria Kettenis
-
Patent number: 12260606Abstract: An apparatus for detecting a mark by using image matching includes a damaged content obtaining unit configured to obtain damaged content generated based on original content including a plurality of cuts; a pre-processed content generating unit configured to generate pre-processed content by merging one or more images included in the damaged content or removing a partial region of one or more cuts included in the damaged content; a matchable content generating unit configured to generate matchable content, in which sizes or locations of one or more cuts included in the pre-processed content are adjusted by comparing one or more cuts included in the original image and the one or more cuts included in the pre-processed content; a matching unit configured to compare the original content with the matchable content, for each cut.Type: GrantFiled: February 5, 2021Date of Patent: March 25, 2025Assignee: NAVER WEBTOON LTD.Inventors: Sang Min Park, Choong Hyun Seo, Jin Seo Lee, Seung Ik Kim, Yo Seob Lee
-
Patent number: 12260628Abstract: Implementations of the present disclosure relate to methods, devices, and computer program products of extracting a feature for multimedia data that comprises a plurality of medium types. In a method, a first feature is determined for a first medium type in the plurality of medium types by masking a portion in a first medium object with the first medium type. A second feature is determined for a second medium type other than the first medium type in the plurality of medium types. The feature is generated for the multimedia data based on the first and second features. With these implementations, multiple medium types are considered in the feature extraction, and thus the feature may fully reflect various aspects of the multimedia data in an accurate way.Type: GrantFiled: April 19, 2022Date of Patent: March 25, 2025Assignee: LEMON INC.Inventors: Xiangyu Zeng, Hongyu Xiong, Yiqi Feng, Han Wang, Yuan Gao, Qingyi Lu, Rui Li
-
Patent number: 12254593Abstract: In a method for generating combined image data based on first magnetic resonance (MR) data and second MR data, the first MR data and the second MR data are provided, the first MR data having been generated by a first actuation of a magnetic resonance device from an examination area of an examination object using a first sequence module, and the second MR data having been generated by a second actuation of the magnetic resonance device from the examination area of the examination object using the first sequence module, the first MR data and the second MR data are registered to one another to generate first registered MR data and second registered MR data; the first registered MR data and the second registered MR data are statistically combined to generate combined image data, and the combined image data is provided as an output in electronic form as a data file.Type: GrantFiled: September 2, 2021Date of Patent: March 18, 2025Assignee: Siemens Healthineers AGInventors: Thomas Benkert, Marcel Dominik Nickel
-
Patent number: 12245833Abstract: A method includes collecting a set of measured points with a flexible catheter as the flexible catheter is inserted into one or more anatomic passageways of a patient in which the measured points are based on a position of the flexible catheter in a patient space, assigning each measured point of the set of measured points to a respective subset of a plurality of subsets of measured points based upon a depth of each measured point within the one or more anatomic passageways, comparing the plurality of subsets to identify an optimal subset of the plurality of subsets, and registering a model of the one or more anatomic passageways to the patient space based on a set of model points of the model and the optimal subset.Type: GrantFiled: November 28, 2023Date of Patent: March 11, 2025Assignee: INTUITIVE SURGICAL OPERATIONS, INC.Inventors: Timothy D. Soper, Vincent Duindam
-
Patent number: 12249003Abstract: A device and method with data preprocessing are disclosed. The device with preprocessing includes a first memory configured to store raw data, and a field programmable gate array (FPGA) in which reconfigurable augmentation modules are programmed, where the FPGA includes a decoder configured to decode the raw data, a second memory configured to store the decoded raw data, and a processor, where the processor is configured to determine target augmentation modules, from among the reconfigurable augmentation modules, based on a data preprocessing pipeline, perform the data preprocessing pipeline using the determined target augmentation modules to generate augmented data, including an augmentation of at least a portion of the decoded raw data stored in the second memory using an idle augmentation module, from among the target augmentation modules, and implement provision of the augmented data to a graphics processing unit (GPU) or Neural Processing Unit (NPU).Type: GrantFiled: December 22, 2021Date of Patent: March 11, 2025Assignees: Samsung Electronics Co., Ltd., UNIST(ULSAN NATIONAL INSTITUTE OF SCIENCE AND TECHNOLOGY)Inventors: Myeongjae Jeon, Chanho Park, Kyuho Lee
-
Patent number: 12239847Abstract: A method of determining treatment geometries for a radiotherapy treatment includes providing a patient model having one or more regions of interest (ROIs); defining a delivery coordinate space (DCS); for each beam's eye view (BEV) plane of each vertex in the DCS, and for each ROI, evaluating a dose of the ROI using transport solutions; evaluating a BEV scores of each pixel of the BEV plane using the doses of the one or more ROIs; determining one or more BEV regions in the BEV plane based on the BEV scores; determining a BEV region connectivity manifold based on the BEV regions; determining a set of treatment trajectories based on the BEV region connectivity manifold; and determining one or more IMRT fields. Each treatment trajectory defines a path through a set of vertices in the DCS. Each IMRT field defines a direction of incidence corresponding to a vertex in the DCS.Type: GrantFiled: September 8, 2023Date of Patent: March 4, 2025Assignee: SIEMENS HEALTHINEERS INTERNATIONAL AGInventor: Santtu Ollila
-
Patent number: 12244784Abstract: Inventory at a remote location may be verified by transmitting a security key associated with uniquely identifying object identification information from a verification server to a client machine at the remote location. The security key may then be used to generate a multi-view interactive digital media representation (MVIDMR) of the object that includes a plurality of images captured from different viewpoints. The MVIDMR may then be transmitted to the verification server.Type: GrantFiled: July 24, 2020Date of Patent: March 4, 2025Assignee: Fyusion, Inc.Inventors: Keith George Martin, Dave Morrison, Stefan Johannes Josef Holzer, Radu Bogdan Rusu