Patents Issued in February 1, 2024
-
Publication number: 20240037898Abstract: Disclosed are a method for predicting reconstructability, a computer device, and a storage medium. In the method, a plurality of viewpoints to be evaluated for a target sampling point are obtained. The target sampling point is located on a rough geometric model. A spatial characteristic of the target sampling point is obtained based on spatial relationships between the plurality of viewpoints to be evaluated and the target sampling point. An image characteristic of the target sampling point is extracted from a target captured image based on a plurality of pre-acquisition viewpoints. The pre-acquisition viewpoints are obtained based on poses of a camera capturing the target captured image. The target captured image is an image containing the target sampling point. The predicting reconstructability for the target sample point is predicted based on the image characteristic and the spatial characteristic.Type: ApplicationFiled: July 21, 2023Publication date: February 1, 2024Inventors: Hui HUANG, Yilin LIU
-
Publication number: 20240037899Abstract: An edge device can include a processing device, an image sensor, and a memory having instructions that are executable by the processing device for causing the processing device to perform operations. The processing device can receive, from the image sensor, an image of an environment. The processing device can determine a visibility measure corresponding to the environment by determining a dark channel of the image, determining, based on the dark channel of the image, a transmission map of the image, and determining, based on the transmission map, a visual contrast of the image. The processing device can generate information corresponding to the visibility measure.Type: ApplicationFiled: July 26, 2023Publication date: February 1, 2024Inventors: Chenxi LIU, Ruimin KE, Yinhai WANG
-
Publication number: 20240037900Abstract: An image processing device includes an extracting part and a prediction part. The extracting part extracts an unsaturated area, in which pixel values are not saturated, and a saturated area, in which pixel values are saturated, from image data that is captured by an imaging device and that shows an image including a plurality of pixels. The prediction part predicts a pixel value of a pixel of interest in the saturated area based on pixel values of a plurality of border pixels in a border area, the border area being located in the unsaturated area and bordering the saturated area.Type: ApplicationFiled: September 29, 2023Publication date: February 1, 2024Inventors: Soichi HAGIWARA, Yuji UMEZU
-
Publication number: 20240037901Abstract: Disclosed is an image dehazing method, including: obtaining a second dark channel map corresponding to a target image based on a first dark channel value corresponding to each pixel in the target image; obtaining an atmospheric light value; obtaining a haze intensity value; obtaining a dehazing intensity correction value based on the haze intensity value, a first dark channel value corresponding to each pixel in a first dark channel map, or a brightness value corresponding to each pixel in the target image; obtaining an estimated value of a transmittance based on the dehazing intensity correction value, a second dark channel value corresponding to each pixel in the second dark channel map, and the atmospheric light value; and obtaining an estimated dehazed image based on the estimated value of the transmittance, the target image and the atmospheric light value. Therefore, the generation of the halo effect can be avoided.Type: ApplicationFiled: July 26, 2023Publication date: February 1, 2024Applicant: ALi CorporationInventor: Lun LIANG
-
Publication number: 20240037902Abstract: An information processing apparatus obtains first feature data generated from image data including a plurality of pixels given different first coordinates, the first feature data including a plurality of feature values given different second coordinates. The information processing apparatus generates a first inference result indicating an image region of the image data by feeding the first feature data to a first machine learning model. The information processing apparatus generates second feature data corresponding to the image region from the first feature data on the basis of coordinate mapping information indicating mapping between the first coordinates and the second coordinates. The information processing apparatus generates a second inference result for the image region by feeding the second feature data to a second machine learning model.Type: ApplicationFiled: April 7, 2023Publication date: February 1, 2024Applicant: Fujitsu LimitedInventors: Takanori NAKAO, Xuying LEI
-
Publication number: 20240037903Abstract: A method and a system for estimating a thermal maturity of a rock sample of a subterranean region of interest are disclosed. The method includes preparing a plurality of rock samples of the subterranean region of interest and obtaining an image of an organic matter sample from the plurality of the rock. Further, the histograms are obtained based on RGB pixel values extracted from the image of the organic matter sample and a functional relationship describing the histograms is determined. Additionally, the method includes constructing a regression model using weight values of the functional relationship as input values and estimating the thermal maturity of the rock sample of the subterranean region of interest based on the constructed regression model.Type: ApplicationFiled: July 28, 2022Publication date: February 1, 2024Applicant: Saudi Arabian Oil CompanyInventors: Christian Andry Cesari, Mustafa Ali H. Al Ibrahim, Mokhles M. Mezghani
-
Publication number: 20240037904Abstract: A method for providing information about an artist to a user by using murals, according to one embodiment of the present invention, comprises: an artist registration step in which a server obtains predetermined artist information, including murals, from an electronic device of an artist so as to register artist information about the artist; and a user use step in which the server obtains predetermined request information, including murals, from an electronic device of a user and provides, to the electronic device of the user, artist information about an artist, from among the registered plurality of artists, that satisfies predetermined matching conditions on the basis of the request information, wherein the predetermined matching conditions can be conditions satisfying a preset similarity or higher by comparing the murals included in the request information with the murals included in the information about the registered plurality of artists.Type: ApplicationFiled: April 19, 2021Publication date: February 1, 2024Applicants: RP INC.Inventor: Jung Kyu PARK
-
Publication number: 20240037905Abstract: Embodiments may: select a set of training images; extract a first set of features from each training image of the set of training images to generate a first feature tensor for each training image; extract a second set of features from each training image to generate a second feature tensor for each training image; reduce a dimensionality of each first feature tensor to generate a first modified feature tensor for each training image; reduce a dimensionality of each second feature tensor to generate a second modified feature tensor for each training image; construct a first generative model representing the first set of features and a second generative model representing the second set of features of the set of training images; identify a first candidate image; and apply a regression algorithm to the first candidate image and each of the first generative model and the second generative model to determine whether the first candidate image is similar to the set of training images.Type: ApplicationFiled: October 9, 2023Publication date: February 1, 2024Applicant: VIZIT LABS, INC.Inventors: Jehan Hamedi, Zachary Halloran, Elham Saraee
-
Publication number: 20240037906Abstract: Systems and methods for color prediction are described. Embodiments of the present disclosure receive an image that includes an object including a color, generate a color vector based on the image using a color classification network, where the color vector includes a color value corresponding to each of a set of colors, generate a bias vector by comparing the color vector to teach of a set of center vectors, where each of the set of center vectors corresponds to a color of the set of colors, and generate an unbiased color vector based on the color vector and the bias vector, where the unbiased color vector indicates the color of the object.Type: ApplicationFiled: July 26, 2022Publication date: February 1, 2024Inventors: Qiuyu Chen, Quan Hung Tran, Kushal Kafle, Trung Huu Bui, Franck Dernoncourt, Walter W. Chang
-
Publication number: 20240037907Abstract: A method includes: responsive to a scan command, controlling a sensor assembly to scan a machine-readable indicium within a sensor field of view; obtaining an image corresponding to the sensor field of view; determining, from the machine-readable indicium, a decoded item identifier and a scan confidence level associated with the decoded item identifier; determining, from the image, a classified item identifier corresponding to the machine-readable indicium, and a classification confidence level associated with the classified item identifier; selecting, based on the scan confidence level and the classification confidence level, one of the decoded item identifier and the classified item identifier; and generating output data based on the selected one of the decoded item identifier and the classified item identifier.Type: ApplicationFiled: July 27, 2022Publication date: February 1, 2024Inventors: David S. Koch, Miroslav Trajkovic, Yan Zhang, Sam Leitch, Dimitry Kapmar
-
Publication number: 20240037908Abstract: In an embodiment, a method includes: receiving raw data from a millimeter-wave radar sensor; generating a first radar-Doppler image based on the raw data; generating a first radar point cloud based on the first radar-Doppler image; using a graph encoder to generate a first graph representation vector indicative of one or more relationships between two or more parts of the target based on the first radar point cloud; generating a first cadence velocity diagram indicative of a periodicity of movement of one or more parts of the target based on the first radar-Doppler image; and classifying an activity of a target based on the first graph representation vector and the first cadence velocity diagram.Type: ApplicationFiled: July 29, 2022Publication date: February 1, 2024Applicant: Infineon Technologies AGInventors: Souvik Hazra, Avik Santra
-
Publication number: 20240037909Abstract: An example method for vane classification includes scanning, using a structured light scanner, a vane for a turbine engine to capture three-dimensional (3D) data about the vane. The method further includes generating a point cloud from the 3D data about the vane. The method further includes connecting, using a processing system, points of the point cloud to generate a mesh surface. The method further includes determining, using the processing system, an airflow for an airfoil of the vane based at least in part on the mesh surface. The method further includes constructing the turbine engine based at least in part on the airflow for the airfoil of the vane without reference to an adjacent airfoil of the vane.Type: ApplicationFiled: July 29, 2022Publication date: February 1, 2024Inventors: Kun Tong, Tracy A. Propheter-Hinckley, Venumadhava Ponnala, Andres Diaz Alvarado
-
Publication number: 20240037910Abstract: A computer-implemented method of classifying an image using a quantum trained vision system. The method comprises enhancing contrast of the image and applying dimension reduction to the contrast-enhance image. The enhanced contrast and dimensionally reduced image is passed to a quantum trained vision system and a result is generated from the quantum trained vision system. The result could be a simply yes/no or true/false binary result to see whether the image fell into one of several predefined classes. Alternatively, the result could be an indication of an object in the image.Type: ApplicationFiled: August 1, 2022Publication date: February 1, 2024Inventors: Victor Onofre, Daniel García, Román Orús
-
Publication number: 20240037911Abstract: Provided is an image classification method, an electronic device and a storage medium, relating to a field of artificial intelligence technology, and specifically, to the technical fields of deep learning, image processing and computer vision, which may be applied to scenes such as image classification. The image classification method includes: extracting a first image feature of a target image by using a first network model, where the first network model includes a convolutional neural network module; extracting a second image feature of the target image by using a second network model, where the second network model includes a deep self-attention transformer network (Transformer) module; fusing the first image feature and the second image feature to obtain a target feature to be recognized; and classifying the target image based on the target feature to be recognized.Type: ApplicationFiled: February 14, 2023Publication date: February 1, 2024Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.Inventors: Ying Xin, Song Xue, Yuan Feng, Chao Li, Bin Zhang, Yunhao Wang, Shumin Han
-
Publication number: 20240037912Abstract: A method for analyzing fashion attributes using large amounts of pieces of image data is provided. The method includes: collecting image data including at least one item; statistically analyzing on the image data based on an attribute classification AI model; and visualizing the results of the statistical analysis, wherein the attribute classification AI model is a model for detecting said at least one item included in the image data, and for recognizing, labeling and classifying fashion attributes of the at least one item.Type: ApplicationFiled: June 22, 2023Publication date: February 1, 2024Applicant: Omnious Co., Ltd.Inventors: Jae Young JUN, Jun Cheol PARK, Yun Hun JANG, Hyung Won CHOI
-
Publication number: 20240037913Abstract: An image processing system is described which has a memory holding at least one image depicting at least one person previously unseen by the image processing system. The system has a trained probabilistic model which describes a relationship between image features, context, identities and a plurality of names of people, wherein at least one of the identities identifies a person depicted in the image without an associated name in the plurality of names. The system has a feature extractor which extracts features from the image, and a processor which predicts an identity of the person depicted in the image using the extracted features and the probabilistic model.Type: ApplicationFiled: October 10, 2023Publication date: February 1, 2024Inventors: Sebastian NOWOZIN, Tom ELLIS, Cecily Peregrine Borgatti MORRISON, Daniel COELHO DE CASTRO
-
Publication number: 20240037914Abstract: A computing device to authenticate works of art comprises a processor programmed to receive test image data corresponding to an image of a test painting to be authenticated; receive a plurality of first artist image data files; receive a plurality of multiple artist image data files; generate a plurality of test painting tiles from the test image data file; generate a plurality of groups of first artist painting tiles; generate a plurality of groups of multiple artist painting tiles; train a classifier to determine one of a plurality of classes for each first artist painting tile and each multiple artist painting tile; use the trained classifier to determine the class for each test painting tile; and determine whether the test painting was likely painted by the first artist according to a percentage of the test painting tiles determined to be the class corresponding to the first artist.Type: ApplicationFiled: December 2, 2021Publication date: February 1, 2024Inventor: Lior Shamir
-
Publication number: 20240037915Abstract: A method of improving a main output of a main AI model [language will be added when claims are finalized]Type: ApplicationFiled: July 26, 2022Publication date: February 1, 2024Inventor: Amol Ajgaonkar
-
Publication number: 20240037916Abstract: A method for creating part images for training machine learning models, the method including: receiving a three-dimensional model of a part, wherein the part model includes physical properties of the part including weight; simulating dropping the part on a surface from a selected height and orientation; randomly placing one or more camera positions around the dropped part; rendering an image of the part model for each of the one or more camera positions; and labeling each image with part information.Type: ApplicationFiled: July 26, 2022Publication date: February 1, 2024Inventor: Taylor Jensen
-
Publication number: 20240037917Abstract: An information processing method according to the application concerned is implemented in a computer; and includes obtaining a two-dimensional simulation image that is formed when a plurality of target subjects present in a three-dimensional simulation space is captured by a virtual camera, and generating the simulation image that visually displays information indicating the degree of overlapping of the plurality of target subjects in the simulation image.Type: ApplicationFiled: July 28, 2022Publication date: February 1, 2024Applicants: SoftBank Corp., NeuralX Inc.Inventors: Yuko ISHIWAKA, Masaki NAKADA
-
Publication number: 20240037918Abstract: A multi-view fine-grained identification method, apparatus, electronic device and medium. By applying the technical scheme of the application, an initial classification model can be trained by using a sample data set consisting of multi-view images of a plurality of multi-view samples. Thus, an efficient fine-grained identification model can be obtained, and this model can actively select the next view image of the same sample for image identification. On the one hand, by aggregating information of multi-view images of the same sample, the limitation of traditional fine-grained image identification methods that only rely on a single picture to provide clues for discrimination is solved. On the other hand, by predicting view images for discrimination, identification efficiency based on multi-view fine-grained identification is improved.Type: ApplicationFiled: April 17, 2023Publication date: February 1, 2024Applicant: BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONSInventors: Zhanyu MA, Kongming LIANG, Ruoyi DU, Wenqing YU
-
Publication number: 20240037919Abstract: A method of automatically improving artificial intelligence (AI) model performance is provided. The method includes: collecting image data including at least one item; performing pre-training based on self-supervised training for a pre-training model by using the image data; and setting initial values of the AI model and performing fine-tuning by using the pre-training model.Type: ApplicationFiled: June 22, 2023Publication date: February 1, 2024Applicant: Omnious Co., Ltd.Inventors: Eun Seop SHIN, Won Jong JO, Jeong Tae CHO, Ji Hun LEE, Hyung Won CHOI, Yun Hun JANG, Jun Cheol PARK
-
Publication number: 20240037920Abstract: A system and method for training a machine learning module to provide classification and localization information for an image study. The method includes receiving a current image study. The method includes applying the machine learning module to the current image study to generate a classification result including a prediction for one or more class labels for the current image study using User Interface 104 a classification module of the machine learning module. The method includes receiving, via a user interface, a user input indicating a spatial location corresponding to a predicted class label. The method includes training a localization module of the machine learning module using the user input indicating the spatial location corresponding to the predicted class label.Type: ApplicationFiled: December 18, 2021Publication date: February 1, 2024Inventors: MATTHIAS LENGA, AXEL SAALBACH, NICOLE SCHADEWALDT, STEFFEN RENISCH, HEINRICH SCHULZ
-
Publication number: 20240037921Abstract: An information processing apparatus includes one or more memories, and one or more processors that, when executing instructions stored in the one or more memories, function as the following units: an acquisition unit configured to acquire learning data including data and a label indicating a category of the data, a base holding unit configured to hold a base for generating a representative vector in the category, a learning unit configured to learn a parameter related to generation of the representative vector based on the acquired learning data, and a first generation unit configured to generate the representative vector based on the parameter and the base.Type: ApplicationFiled: July 21, 2023Publication date: February 1, 2024Inventor: TOMONORI YAZAWA
-
Publication number: 20240037922Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for adapting generative neural networks to target domains utilizing an image translation neural network. In particular, in one or more embodiments, the disclosed systems utilize an image translation neural network to translate target results to a source domain for input in target neural network adaptation. For instance, in some embodiments, the disclosed systems compare a translated target result with a source result from a pretrained source generative neural network to adjust parameters of a target generative neural network to produce results corresponding in features to source results and corresponding in style to the target domain.Type: ApplicationFiled: July 27, 2022Publication date: February 1, 2024Inventors: Yijun Li, Nicholas Kolkin, Jingwan Lu, Elya Shechtman
-
Publication number: 20240037923Abstract: Methods, systems, and apparatuses for unsupervised data drift detection for classification neural networks are disclosed.Type: ApplicationFiled: September 28, 2022Publication date: February 1, 2024Applicant: Blaize, Inc.Inventors: Adam P. Geringer, Val G. Cook
-
Publication number: 20240037924Abstract: A method for processing digital image recognition of invariant representations of hierarchically structured entities can be performed by a computer using an artificial neural network. The method involves learning a sparse coding dictionary on an input signal to obtain a representation of low-complexity components. Possible transformations are inferred from the statistics of the sparse representation by computing a correlation matrix. Eigenvectors of the Laplacian operator on the graph whose adjacency matrix is the correlation matrix from the previous step are computed. A coordinate transformation is performed to the base of eigenvectors of the Laplacian operator, and the first step is repeated with the next higher hierarchy level until all hierarchy levels of the invariant representations of the hierarchically structured entities are processed and the neural network is trained. The trained artificial neural network can then be used for digital image recognition of hierarchically structured entities.Type: ApplicationFiled: December 1, 2021Publication date: February 1, 2024Applicant: Merck Patent GmbHInventor: Helmut LINDE
-
Publication number: 20240037925Abstract: Examples of simulated powdered model generation for neural networks are described herein. In some examples, a set of simulated powdered models that simulate application of powder to a computer aided design (CAD) model are generated. In some examples, synthetic images of the simulated powdered models placed in a virtual environment are generated. In some examples, a neural network is trained to recognize real objects based on the synthetic images of the simulated powdered models.Type: ApplicationFiled: March 3, 2021Publication date: February 1, 2024Inventors: Joyce Xin Yan LIM, Quang-Cuong PHAM
-
Publication number: 20240037926Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing instance segmentation by detecting and segmenting individual objects in an image. In one aspect, a method comprises: processing an image to generate data identifying a region of the image that depicts a particular object; obtaining data defining a plurality of example object segmentations; generating a respective weight value for each of the example object segmentations; for each of a plurality of pixels in the region of the image, determining a score characterizing a likelihood that the pixel is included in the particular object depicted in the region of the image using: (i) the example object segmentations, and (ii) the weight values for the example object segmentations; and generating a segmentation of the particular object depicted in the region of the image using the scores for the pixels in the region of the image.Type: ApplicationFiled: October 12, 2023Publication date: February 1, 2024Inventors: Weicheng Kuo, Anelia Angelova, Tsung-Yi Lin
-
Publication number: 20240037927Abstract: A processor is configured to: acquire training data that consists of a learning expression medium and a correct answer label for at least one of a plurality of types of classes included in the learning expression medium; input the learning expression medium to a neural network such that probabilities that each class included in the learning expression medium will be each of the plurality of types of classes are output; integrate the probabilities that each class will be each of the plurality of types of classes on the basis of classes classified by the correct answer label of the training data; and train the neural network on the basis of a loss derived from the integrated probability and the correct answer label of the training data.Type: ApplicationFiled: October 10, 2023Publication date: February 1, 2024Inventor: Satoshi IHARA
-
Publication number: 20240037928Abstract: In a method for generating an image processing sequence, when a next routine sequence set is used as a sequence set in a routine of this time, a reference sequence stored in a storage device is compared with each of a plurality of image processing sequences forming a sequence set, and an output image according to the image processing sequence is generated, using a processed image associated with the reference sequence, with respect to a sequence that is the same as the reference sequence and that is formed by an image input layer and a sequence element coupled continuously from the image input layer, of the image processing sequences.Type: ApplicationFiled: July 27, 2023Publication date: February 1, 2024Inventor: Masashi KANAI
-
Publication number: 20240037929Abstract: Selections of content shared from a remote device during a video conference are copied to a destination of a computing device connected to the video conference live or at which a recording of the video conference is viewed. The content shared from the remote device during the video conference is output at a display of the computing device. A portion of the content is selected according to an instruction received from a user of the computing device while output at the display of the computing device to copy to a destination associated with software running at the computing device. The portion of the content is identified using a machine vision process performed against the content while output at the display of the computing device. The portion of the content is then copied to the destination.Type: ApplicationFiled: May 8, 2023Publication date: February 1, 2024Inventor: Shane Paul Springer
-
Publication number: 20240037930Abstract: A method, system, apparatus, and non-transitory computer-readable medium for image processing using a multi-task neural network framework may be provided. The method be performed by one or more processors and may include receiving an input image, and performing an image processing task based on the input image using the multi-task neural network framework, wherein the multi-task neural network framework is trained using a combination of task specific losses, the task specific losses including a plurality of first losses associated with the multi-task neural network framework and a plurality of second losses associated with a plurality of single-task neural network models. The method may also include generating an output of the image processing task based on up sampling an output of the multi-task neural network framework.Type: ApplicationFiled: July 29, 2022Publication date: February 1, 2024Applicant: Rakuten Group, Inc.Inventors: Geethu JACOB, Vishal AGARWAL, Bjorn STENGER
-
Publication number: 20240037931Abstract: A system for providing an enhanced vision transformer block for mobile vision transformers to perform computer vision tasks, such as image classification, segmentation, and objected detection is disclosed. A local representation block of the block applies a depthwise-separable convolutional layer to vectors of an input image to facilitate creation of local representation outputs associated with the image. The local representation output is fed into a global representation block, which unfolds the local representation outputs, applies vision transformers, and folds the result to generate a global representation output associated with the image. The global representation output is fed to a fusion block, which concatenates the local representations with the global representations, applies a point-wise convolution to the concatenation to generate a fusion block output, and fuses input features of the image with the fusion block out to generate an output to facilitate performance of a computer vision tasks.Type: ApplicationFiled: July 26, 2023Publication date: February 1, 2024Inventors: Abhishek Chaurasia, Shakti Nagnath Wadekar
-
Publication number: 20240037932Abstract: An information processing method, applied to an electronic device including an object detection unit and a control unit, comprising determining that a target object is detected. The object detection unit sends a status switch instruction to the control unit and controls the object detection unit to switch from a first status to a second status, and the status switch instruction is used to cause the electronic device to switch from a third status to a fourth status. The method further includes determining that the object detection unit enters the second status. In response to a control instruction sent by the control unit, the object detection unit obtains an object feature of the target object to cause the electronic device to perform recognition on the target object based on the object feature.Type: ApplicationFiled: July 28, 2023Publication date: February 1, 2024Inventor: Zhou YU
-
Publication number: 20240037933Abstract: System and computer-implemented method for monitoring a function model for providing data for at least one function of a computer-controlled machine, in particular an image recognition algorithm.Type: ApplicationFiled: July 27, 2023Publication date: February 1, 2024Inventors: Bjoern Scholz, David Kulicke, Harald Walter, Hoang Trinh, Holger Kahle, K B Mohan Kishor, Marcio Jose De Menezes Junior, Peter Fruehberger
-
Publication number: 20240037934Abstract: A method for detecting a pattern image includes causing a projector to display a first pattern image, acquiring a first captured image that is an image, captured with a camera, of the first pattern image, performing detection of a second pattern image corresponding to the first pattern image from the first captured image, when the detection of the second pattern image from the first captured image fails, performing first correction that increases possibility of successful detection of the second pattern image on the first captured image to acquire a second captured image, and performs detection of the second pattern image from the second captured image.Type: ApplicationFiled: July 28, 2023Publication date: February 1, 2024Inventor: Yuki MORI
-
Publication number: 20240037935Abstract: Properly parking personal mobility vehicles (PMVs) is an important for safety and public satisfaction. The large number of daily rides of ride-share PMVs makes it impossible to verify manually that each PMV is properly parked. Aspects of this disclosure include systems and methods for verifying that PMVs are properly parked. These systems and methods can include training a machine learning model on a server. The system can request that users submit images to the server, such that the server can verify that the user properly parked the PMV. The server can transmit a finished indication when it determines that the user properly parked the vehicle. The server can transmit instructions to the user to take various actions when it determines that the user improperly parked the vehicle or when the image is insufficient to determine whether the user properly parked the vehicle.Type: ApplicationFiled: October 6, 2023Publication date: February 1, 2024Inventors: Jinsong TAN, Yi SU, Andrew Hanlin XIA
-
Publication number: 20240037936Abstract: A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.Type: ApplicationFiled: October 11, 2023Publication date: February 1, 2024Applicant: Boston Dynamics, Inc.Inventors: Alex Perkins, Charles DuHadway, Peter Anderson-Sprecher
-
Publication number: 20240037937Abstract: A sensing plan and a trimming plan in vegetation management are efficiently formulated. A vegetation management system includes: a data acquisition unit configured to acquire at least a satellite image of a power transmission line arrangement region; a site work situation collection unit configured to collect a situation of a trimming work executed at a site of the power transmission line arrangement region; and a planning unit configured to divide the power transmission line arrangement region into a plurality of partial regions, manage a status relating to the trimming work and the acquisition of the satellite image in association with each of the partial regions, and formulate a trimming work plan and a satellite image sensing plan based on the status. The status includes a non-shooting status, a shooting status, a clear waiting status, and a cleared status.Type: ApplicationFiled: June 15, 2023Publication date: February 1, 2024Applicant: Hitachi, Ltd.Inventor: Tomonori YAMAMOTO
-
Publication number: 20240037938Abstract: A system includes one or more processors; and one or more non-transitory, computer-readable media including instructions that, when executed by the one or more processors, cause the computing system to: receive a machine data set; process the machine data set with a trained deep learning model to generate predicted variety profile index values; and cause a visualization to be displayed.Type: ApplicationFiled: October 6, 2023Publication date: February 1, 2024Inventors: William Kess Berg, Jon J. Fridgen, Jonathan Michael Bokmeyer, Andrew James Woodyard
-
Publication number: 20240037939Abstract: A group captioning system includes computing hardware, software, and/or firmware components in support of the enhanced group captioning contemplated herein. In operation, the system generates a target embedding for a group of target images, as well as a reference embedding for a group of reference images. The system identifies information in-common between the group of target images and the group of reference images and removes the joint information from the target embedding and the reference embedding. The result is a contrastive group embedding that includes a contrastive target embedding and a contrastive reference embedding with which to construct a contrastive group embedding, which is then input to a model to obtain a group caption for the target group of images.Type: ApplicationFiled: October 16, 2023Publication date: February 1, 2024Inventors: Quan Hung TRAN, Long Thanh MAI, Zhe LIN, Zhuowan LI
-
Publication number: 20240037940Abstract: A computer vision temporal action localization (TAL) computing tool and operations are provided. The TAL computing tool receives a coarse temporal bounding box, having a first start point and a first end point, for an action in the input video data, and a first set of logits, where each logit corresponds to a potential classification of the action in the input video data. The TAL computing tool executes a first engine on the coarse temporal bounding box to generate a second set of logits, and a second engine on the first set of logits to generate a refined temporal bounding box having a second start point and a second end point. The TAL computing tool performs the computer vision temporal action localization operation based on the second set of logits and the refined temporal bounding box to specify a temporal segment of the input video data corresponding to an action represented in the input video data, and a corresponding classification of the action represented in the temporal segment.Type: ApplicationFiled: July 28, 2022Publication date: February 1, 2024Inventors: Bo Wu, Chuang Gan, Pin-Yu Chen, Yang Zhang, Xin Zhang
-
Publication number: 20240037941Abstract: Methods and systems provide for search results within segmented communication session content. In one embodiment, the system receives a transcript and video content of a communication session between participants, the transcript including timestamps for a number of utterances associated with speaking participants; processes the video content to extract textual content visible within the frames of the video content; segments frames of the video content into a number of contiguous topic segments; determines a title for each topic segment; assigns a category label for each topic segment; receives a request from a user to search for specified text within the video content; determines one or more titles or category labels for which a prediction of relatedness with the specified text is present; and presents content from at least one topic segment associated with the one or more titles or category labels for which a prediction of relatedness is present.Type: ApplicationFiled: January 31, 2023Publication date: February 1, 2024Inventors: Andrew Miller-Smith, Renjie Tao, Ling Tsou
-
Publication number: 20240037942Abstract: Document portion identification in a recorded video is disclosed, including: obtaining a recorded video; identifying a document portion that appears during the recorded video, wherein the document portion belongs to a document; and determining a video segment during which the document portion appears in the recorded video.Type: ApplicationFiled: April 4, 2023Publication date: February 1, 2024Inventors: Thomas H. Strader, Christopher Buchholz
-
Publication number: 20240037943Abstract: The disclosure includes a platform for analyzing athletes and generating matches between athletes and organizations. The platform receives data descriptive of an athlete. The platform analyzes, using a model, the data descriptive of the athlete to determine one or more attributes of the athlete. The platform generates, using the model, a match between the athlete and an organization based on the one or more attributes of the athlete and one or more characteristics of the organization.Type: ApplicationFiled: July 7, 2023Publication date: February 1, 2024Inventors: Mikekena Richardson, Lannette Richardson
-
Publication number: 20240037944Abstract: Implementations of the subject technology provides analyzing a recording of content. The subject technology generates metadata information based at least in part on the analyzing. The subject technology identifies, based at least in part on at least one of a user preference or a detected event, a region of interest or an object of interest in the recording of content. Based at least in part on the identified region of interest or object of interest, the subject technology generates a modified version of the recording of content. Further, the subject technology stores the modified version of the recording of content for subsequent playback on an electronic device.Type: ApplicationFiled: October 16, 2023Publication date: February 1, 2024Inventors: Ranjit DESAI, Maneli NOORKAMI
-
Publication number: 20240037945Abstract: Embodiments described in this disclosure include a process for collecting energy tool usage data from surgical videos and using such data for post surgery analysis. The process can begin by receiving a plurality of surgical videos of a surgical procedure involving an energy tool. For each surgical video in the plurality of surgical videos, the process detects a set of activation events in the surgical video, wherein each detected activation event includes an identified starting timestamp and a duration. The process further extracts a set of energy tool usage data based on the set of detected activation events, and then stores the extracted set of energy tool usage data in a database indexed based on a set of energy tool usage metrics. Next, in response to a user search request, the process returns the stored energy tool usage data that matches the search request from the database.Type: ApplicationFiled: July 27, 2022Publication date: February 1, 2024Inventors: Meysam TORABI, Varun GOEL, Jocelyn Elaine BARKER, Rami ABUKHALIL, Richard W. TIMM, Pablo E. GARCIA KILROY
-
Publication number: 20240037946Abstract: A video camera includes a camera for capturing a video stream and a controller that is operably coupled to the camera. The controller, which includes processing resources, is configured to determine a current utilization of one or more of the processing resources and to determine which of a plurality of video analytics algorithms should be executed based at least in part on the determined current utilization of the one or more processing resources. The controller is configured to execute two or more of the plurality of video analytics algorithms on the video stream to identify one or more events in the video stream, wherein the controller executes the two or more of the plurality of video analytics algorithms, and sends an alert in response to identifying one or more events in the video stream.Type: ApplicationFiled: November 30, 2022Publication date: February 1, 2024Inventors: Abhisekh Jain, Sivasanthanam Dhayalan, Jeslin Paul Joseph
-
Publication number: 20240037947Abstract: Techniques for identifying human interaction limitations based on historical information are provided. An indication of a public safety incident is received. The public safety incident involves at least one person and occurs at an incident location. Historical video of the incident location is acquired. The historical video of the incident location is analyzed to identify the presence of the at least one person. A behavior of the at least one person in the historical video of the incident location is analyzed to identify at least one human interaction limitation. A first responder that is responding to the public safety incident is informed of the at least one human interaction limitation.Type: ApplicationFiled: July 27, 2022Publication date: February 1, 2024Inventors: ROBERT BETKA, GRZEGORZ SZUREK, KATARZYNA BARD RUGIELLO, JAKUB KLESZCZ, OLIWIA STRZELEC