Patents Examined by Vu Le
-
Patent number: 12217440Abstract: A computer implemented method of decoding a signal. The method includes receiving a signal (which may be an electromagnetic signal), sampling the received signal to generate an input waveform having magnitude and phase components, applying a transform operation to the input waveform to generate a first decoded signal, and outputting the first decoded signal. The transform operation includes pre-processing the input waveform to generate a mirrored inverted waveform and applying a continuous wavelet transform to the mirrored inverted waveform to generate the first decoded signal. This allows inversion of the frequency and temporal resolution of the continuous wavelet transform, thereby enabling improved temporal and frequency decoding of a signal. The method is particularly suitable for signal filters and filtering units.Type: GrantFiled: July 28, 2020Date of Patent: February 4, 2025Assignee: The Secretary of State for DefenceInventor: Paul Mason
-
Patent number: 12217420Abstract: A computer-implemented method may include receiving a collection of unstained digital histopathology slide images at a storage device and running a trained machine learning model on one or more slide images of the collection to infer a presence or an absence of a salient feature. The trained machine learning model may have been trained by processing a second collection of unstained or stained digital histopathology slide images and at least one synoptic annotation for one or more unstained or stained digital histopathology slide images of the second collection. The computer-implemented method may further include determining at least one map from output of the trained machine learning model and providing an output from the trained machine learning model to the storage device.Type: GrantFiled: September 19, 2022Date of Patent: February 4, 2025Assignee: Paige.AI, Inc.Inventors: Patricia Raciti, Christopher Kanan, Alican Bozkurt, Belma Dogdas
-
Patent number: 12211216Abstract: Disclosed are apparatuses, systems, and techniques that may perform efficient deployment of machine learning for detection and classification of moving objects in streams of images. A set of machine learning models with different input sizes may be used for parallel processing of various regions of interest in multiple streams of images. Both the machine learning models as well as the inputs into these models may be selected dynamically based on a size of the regions of interest.Type: GrantFiled: January 25, 2022Date of Patent: January 28, 2025Assignee: NVIDIA CorporationInventor: Tushar Khinvasara
-
Patent number: 12211237Abstract: The invention relates to a method and a device for producing a thermal map of an area, wherein the thermal map is generated by a combination of two thermal images of different properties, and both thermal images comprise pixels associated with the area and have been recorded by satellites. The two thermal images are recorded at different times using different recording devices. Furthermore, a radiometric precision of the first thermal image is higher than that of the second thermal image, and a spatial resolution of the second thermal image is higher than that of the first thermal image. The two thermal images are used to determine a measurement value offset of a first pixel group belonging to the second thermal image and spatially associated with the area, and then corrected absolute measurement values of the pixels belonging to the second thermal image and spatially associated with the area are determined. A precise thermal map of the area is then created on this basis.Type: GrantFiled: May 8, 2019Date of Patent: January 28, 2025Assignee: Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.Inventor: Max Gulde
-
Patent number: 12205288Abstract: The present disclosure relates to a method, performed by at least one processor of an information processing system, of analyzing a pathological image. The method includes receiving a pathological image, detecting an object associated with medical information, in the received pathological image by using a machine learning model, generating an analysis result on the received pathological image, based on a result of the detecting, and outputting medical information about at least one region included in the pathological image, based on the analysis result.Type: GrantFiled: March 30, 2023Date of Patent: January 21, 2025Assignee: Lunit Inc.Inventors: Chan-Young Ock, Donggeun Yoo, Kyunghyun Paeng
-
Patent number: 12205261Abstract: Systems and apparatus are disclosed to detect constituents using a sensor arrangement. A sensor apparatus for detecting constituents of a material includes a first sensor, which interacts with the material, and is configured to measure an optical spectrum of the material. Further, the first sensor is coupled to an evaluation device that is configured to output an output value relating to the level of the one or more constituents in the material with the aid of the measured spectrum and calibration data. The sensor apparatus further includes a second sensor configured to analyse the material examined by the first sensor and to output a signal relating to the level of the one or more constituents in the material. The sensor apparatus further includes a calibration data generating device configured to generate the calibration data for the evaluation device with the aid of the signal of the second sensor.Type: GrantFiled: May 5, 2022Date of Patent: January 21, 2025Assignee: Deere & CompanyInventors: Ludger Aehling, Peter Schade
-
Patent number: 12205205Abstract: An image processing apparatus includes: an obtaining unit configured to obtain album information forming an album; a display control unit configured to display an editing screen for editing the album on a display based on the album information; and a recommendation unit configured to make a removal recommendation in the editing screen based on the album information, the removal recommendation being a recommendation to remove an image from an image group used in the album.Type: GrantFiled: February 7, 2022Date of Patent: January 21, 2025Assignee: Canon Kabushiki KaishaInventors: Jumpei Takeichi, Hiroyasu Kunieda, Takayuki Yamada
-
Patent number: 12198390Abstract: A three-dimensional data point encoding method, decoding method, and encoding device. The encoding method includes: determining maximum values of side lengths of a cuboid of three-dimensional data points to be encoded in three directions according to position coordinates of the three-dimensional data points to be encoded; performing at least one octree partition process on the cuboid, to obtain a plurality of first-type sub-blocks; performing at least one quadtree partition process or binary tree partition process on at least one first-type sub-block of the plurality of first-type sub-blocks; and encoding the three-dimensional data points to be encoded according to partition results of the cuboid.Type: GrantFiled: July 9, 2021Date of Patent: January 14, 2025Assignee: SZ DJI TECHNOLOGY CO., LTD.Inventors: Pu Li, Fu Zhang, Xiaozhen Zheng
-
Patent number: 12198414Abstract: Examples described herein provide a method that includes performing, by a processing device, using a neural network, pattern recognition on an image to recognize a feature in the image. The method further includes performing, by the processing device, upscaling of the image to increase a resolution of the image while maintaining the feature to generate an upscaled image.Type: GrantFiled: January 25, 2022Date of Patent: January 14, 2025Assignee: FARO Technologies, Inc.Inventors: Michael Müller, Georgios Balatzis
-
Patent number: 12193378Abstract: A computer implemented method of automatically controlling an enclosed crop growing device, comprising: feeding an image of the enclosed crop growing device into a machine learning model, wherein the image simultaneously depicts a plurality of crops of a plurality of different types at a plurality of different growth stages arranged at a plurality of predefined crop growing locations within the enclosed crop growing device, obtaining as an outcome of the ML model, a plurality of parameters for setting a plurality of environmental control components that control an environment of the enclosed crop growing device, and automatically adjusting the plurality of environmental control components according to the plurality of parameters.Type: GrantFiled: February 29, 2024Date of Patent: January 14, 2025Assignee: Agwa Farm Ltd.Inventors: Alon Wallach, Niv Stolarski
-
Patent number: 12190511Abstract: The present invention relates to a method of providing diagnosis assistance information by analyzing a medical image, the method including obtaining an image of the brain, labeling a feature value representing a region of the brain, determining a reference boundary in the image of the brain, calculating a first disease index and a second disease index, and providing diagnosis assistance information on the basis of the first and second disease indexes.Type: GrantFiled: August 2, 2022Date of Patent: January 7, 2025Assignee: NEUROPHET INC.Inventors: Dong Hyeon Kim, Min Ho Lee
-
Patent number: 12178631Abstract: A deep learning (DL) convolution neural network (CNN) reduces noise in positron emission tomography (PET) images, and is trained using a range of noise levels for the low-quality images having high noise in the training dataset to produce uniform high-quality images having low noise, independently of the noise level of the input image. The DL-CNN network can be implemented by slicing a three-dimensional (3D) PET image into 2D slices along transaxial, coronal, and sagittal planes, using three separate 2D CNN networks for each respective plane, and averaging the outputs from these three separate 2D CNN networks. Feature-oriented training can be implemented by segmenting each training image into lesion and background regions, and, in the loss function, applying greater weights to voxels in the lesion region. Other medical images (e.g. MRI and CT) can be used to enhance resolution of the PET images and provide partial volume corrections.Type: GrantFiled: September 22, 2023Date of Patent: December 31, 2024Assignee: CANON MEDICAL SYSTEMS CORPORATIONInventors: Chung Chan, Jian Zhou, Evren Asma
-
Patent number: 12183010Abstract: The present disclosure relates to a system and a method for performing instance segmentation based on semantic segmentation that is capable of (1) processing HD images in real-time given semantic segmentation; 2) delivering comparable performance with Mask R-CNN in terms of accuracy when combined with a widely-used semantic segmentation method (such as DPC), while consistently outperforms a state-of-the-art real-time solution; (3) working flexibly with any semantic segmentation model for instance segmentation; (4) outperforming Mask R-CNN if the given semantic segmentation is sufficiently good; and (5) being easily extended to panoptic segmentation.Type: GrantFiled: February 16, 2022Date of Patent: December 31, 2024Assignee: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.Inventors: Jian Tang, Chengxiang Yin, Kun Wu, Zhengping Che
-
Patent number: 12175674Abstract: The present disclosure provides methods and systems for measuring paraspinal muscle parameters using MRI. Two-dimensional MRI image slices of a subject's spine may be obtained. A slice selection model may identify one or more representative slices, each located at or adjacent to a physiological region corresponding to a specific biomechanical environment in a respective spine level of the subject's spine. A muscle segmentation model may segment each representative slice. Segmenting a representative slice may include generating an image segmentation mask including a plurality of pixels in the representative slice corresponding to paraspinal muscle and excluding a plurality of pixels in the representative slice corresponding to metal artifacts and/or to biological matter other than paraspinal muscle.Type: GrantFiled: September 19, 2023Date of Patent: December 24, 2024Assignee: Tissue Connect Systems, Inc.Inventors: Alexander P. Hughes, Frank Cammisa, Andrew Sama, Federico Girardi, Artine Arzani, Kyle Finos, Isaac Nathoo
-
Patent number: 12175752Abstract: Systems, methods, and data storage devices for improved classifier training using a video object tracker to determine video data samples are described. A group classifier may be trained using machine learning to classify image objects, based on a set of machine learning parameters, and assign them a group identifier. A retraining data set may be determined based on video data that was assigned that group identifier based on an object tracker. The group classifier may be retrained using the retraining data set to determine an updated set of machine learning parameters and the group classifier may be updated with those parameters.Type: GrantFiled: April 26, 2022Date of Patent: December 24, 2024Assignee: Sandisk Technologies, Inc.Inventor: Shaomin Xiong
-
Patent number: 12175678Abstract: An image processing apparatus, including a memory configured to store one or more instructions; and at least one processor configured to execute the one or more instructions to: based on a first image and a probability model, optimize an estimated pixel value and estimated gradient values of each pixel of an original image corresponding to the first image, obtain an estimated original image based on the optimized estimated pixel value of the each pixel of the original image, obtain a decontour map based on the optimized estimated pixel value and the estimated gradient values of the each pixel of the original image, and generate a second image by combining the first image with the estimated original image based on the decontour map.Type: GrantFiled: May 20, 2022Date of Patent: December 24, 2024Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Hanul Shin, Soomin Kang, Jaeyeon Park, Youngchan Song, Iljun Ahn, Tammy Lee
-
Patent number: 12175722Abstract: A connected component analysis (CCA) method, which can use labels repeatedly, comprising: defining a label pattern comprising a label and a plurality of neighboring labels; setting a center label of a current pixel of a target binary image according to a binary value of the current pixel and the neighboring pixels; setting at least two of the neighboring labels according to whether the current pixel is in any one of a first row, a first column and a last column; and recording the center label to a label buffer. Labels for marking pixels of the target binary image are first center labels, and then are second center labels, and are the first center labels again after the labels are the second center labels.Type: GrantFiled: December 17, 2021Date of Patent: December 24, 2024Assignee: PixArt Imaging Inc.Inventors: Joon Chok Lee, Zi Hao Tan
-
Patent number: 12175751Abstract: Systems, methods, and data storage devices using a video group classifier based on an object tracker are described. A group classifier may be trained using machine learning to classify image objects from a video frame and assign a classifier identifier. An object tracker and the group classifier may be used to determine correspondence between tracker identifiers and classifier identifiers for assigning group identifiers. The object tracker may then be used to determine image objects, assign tracker identifiers, and track the movement of those image objects through a video data stream to associate tracker identifiers with the video frames. The tracker identifier may be used to assign a group identifier to each video frame based the correspondence between the tracker identifier and the classifier identifier.Type: GrantFiled: April 26, 2022Date of Patent: December 24, 2024Assignee: Sandisk Technologies, Inc.Inventors: Shaomin Xiong, Toshiki Hirano
-
Patent number: 12175697Abstract: The present technology relates to an information processing apparatus and an information processing method that enable an operation to be performed using a wearable device that is less resistant to being worn all the times. The information processing apparatus according to one aspect of the present technology acquires a captured image obtained by capturing an image of a wearable device including a module whose appearance changes according to time, detects a module included in the captured image on the basis of an image representing an appearance of the module according to a current time, and estimates at least one of a position or a posture of the wearable device. The present technology can be applied to, for example, a transmissive HMD.Type: GrantFiled: March 16, 2020Date of Patent: December 24, 2024Assignee: SONY GROUP CORPORATIONInventor: Masayuki Yokoyama
-
Patent number: 12175770Abstract: A lane extraction method uses projection transformation of a 3D point cloud map, by which the amount of operations required to extract the coordinates of a lane is reduced by performing deep learning and lane extraction in a two-dimensional (2D) domain, and therefore, lane information is obtained in real time. In addition, black-and-white brightness, which is most important information for lane extraction on an image, is substituted by the reflection intensity of a light detection and ranging (LiDAR) sensor so that a deep learning model capable of accurately extracting a lane is provided. Therefore, reliability and competitiveness is enhanced in the field of autonomous driving, the field of road recognition, the field of lane recognition, and the field of HD road maps for autonomous driving, and the fields similar or related thereto, and more particularly, in the fields of road recognition and autonomous driving using LiDAR.Type: GrantFiled: June 7, 2022Date of Patent: December 24, 2024Assignee: MOBILTECHInventors: Jae Seung Kim, Yeon Soo Park