-
公开(公告)号：US20220408698A1
公开(公告)日：2022-12-29
申请号：US17361258
申请日：2021-06-28
Applicant: PING AN TECHNOLOGY (SHENZHEN) CO., LTD.
Inventor： CHEN DU , JUIHSIN LAI , MEI HAN
Abstract: A system and a method for detecting animals in a region of interest are disclosed. An image that captures a scene in the region of interest is received. The image is fed to an animal detection model to produce a group of probability maps for a group of key points and a group of affinity field maps for a group of key point sets. One or more connection graphs are determined based on the group of probability maps and the group of affinity field maps. Each connection graph outlines a presence of an animal in the image. One or more animals present in the region of interest are detected based on the one or more connection graphs.
-
公开(公告)号：US20220405500A1
公开(公告)日：2022-12-22
申请号：US17304419
申请日：2021-06-21
Applicant: Google LLC
Inventor： Mayank Bhargava , Idris Syed Aleem , Yinda Zhang , Sushant Umesh Kulkarni , Rees Anwyl Simmons , Ahmed Gawish
IPC: G06K9/00 , G06T7/73 , G06K9/32 , G06K9/62 , G06T17/00 , G06T7/50 , G06T19/20 , G06T7/246 , G02C7/02
Abstract: A computer-implemented method includes receiving a two-dimensional (2-D) side view face image of a person, identifying a bounded portion or area of the 2-D side view face image of the person as an ear region-of-interest (ROI) area showing at least a portion of an ear of the person, and processing the identified ear ROI area of the 2-D side view face image, pixel-by-pixel, through a trained fully convolutional neural network model (FCNN model) to predict a 2-D ear saddle point (ESP) location for the ear shown in the ear ROI area. The FCNN model has an image segmentation architecture.
-
公开(公告)号：US20220398395A1
公开(公告)日：2022-12-15
申请号：US17344659
申请日：2021-06-10
Applicant: Sony Group Corporation , Sony Corporation of America
Inventor： Cheng-Yi Liu
Abstract: A method for removing extraneous content in a first plurality of images, captured at a corresponding plurality of poses and a corresponding first plurality of times, by a first drone, of a scene in which a second drone is present includes the following steps, for each of the first plurality of captured images. The first drone predicts a 3D position of the second drone at a time of capture of that image. The first drone defines, in an image plane corresponding to that captured image, a region of interest (ROI) including a projection of the predicted 3D position of the second drone at a time of capture of that image. A drone mask for the second drone is generated, and then applied to the defined ROI, to generate an output image free of extraneous content contributed by the second drone.
-
34.发明申请
公开(公告)号：US20220388507A1
公开(公告)日：2022-12-08
申请号：US17339720
申请日：2021-06-04
Applicant: TeleNav, Inc.
Inventor： Gregory Stewart Aist , Casey Thomas Carter , Shalu Grover , Michele Santamaria
Abstract: A method of operation of a vehicle system including capturing a current image from a current location towards a travel direction along a travel path; generating an image category for the current image based on a weather condition, the current location, or a combination thereof; determining a clear path towards the travel direction of the travel path based on the image category, the current image, and a previous image; and communicating the clear path for assisting in operation of a vehicle.
-
35.发明申请
公开(公告)号：US20220379911A1
公开(公告)日：2022-12-01
申请号：US17330876
申请日：2021-05-26
Applicant: Argo AI, LLC
Inventor： G. Peter K. Carr , FNU Ratnesh Kumar
Abstract: Methods of determining relevance of objects that a vehicle detected are disclosed. A system will receive a data log of a run of the vehicle. The data log includes perception data captured by vehicle sensors during the run. The system will identify an interaction time, along with a look-ahead lane based on a lane in which the vehicle traveled during the run. The system will define a region of interest (ROI) that includes a lane segment within the look-ahead lane. The system will identify, from the perception data, objects that the vehicle detected within the ROI during the run. For each object, the system will determine a detectability value by measuring an amount of the object that the vehicle detected. The system will create a subset with only objects having at least a threshold detectability value, and it will classify any such object as a priority relevant object.
-
公开(公告)号：US20220374645A1
公开(公告)日：2022-11-24
申请号：US17394159
申请日：2021-08-04
Applicant: Meta Platforms, Inc.
Inventor： Elizabeth Kelsey Santoro , Denis Savenkov , Koon Hui Geoffrey Goh , Kshitiz Malik , Ruchir Srivastava
Abstract: In one embodiment, a method includes accessing visual signals comprising images portraying textual content in a real-world environment associated with a first user from a client system associated with the first user, recognizing the textual content based on machine-learning models and the visual signals, determining a context associated with the first user with respect to the real-world environment based on the visual signals, executing tasks determined based on the textual content and the determined context for the first user, and sending instructions for presenting execution results of the tasks to the first user to the client system.
-
公开(公告)号：US20220318552A1
公开(公告)日：2022-10-06
申请号：US17219500
申请日：2021-03-31
Applicant: EarthSense, Inc.
Inventor： Girish Chowdhary , Chinmay Soman , Patric Liu , Michael McGuire , Michael Hansen
Abstract: A method, non-transitory computer readable medium, and system that manage agricultural analysis in dynamic environments includes detecting a location of one or more agricultural objects of interest in image data of an environment captured by a sensor device during active navigation of the environment. An orientation and position of the sensor device with respect to the image data is determined. Each of the one or more agricultural objects of interest is analyzed based on the image data, the detected location of the one or more agricultural objects of interest, and the determined orientation and position of the sensor device to determine one or more characteristics about the one or more agricultural objects of interest. At least one action is initiated based on the determined one or more characteristics about the one or more agricultural objects of interest.
-
38.发明申请
公开(公告)号：US20220309279A1
公开(公告)日：2022-09-29
申请号：US17211055
申请日：2021-03-24
Applicant: YAHOO ASSETS LLC
Inventor： Topojoy BISWAS , Avijit SHAH , Deven Santosh SHAH
Abstract: The disclosed systems and methods provide a novel framework that provides mechanisms for performing cost-effective, accurate and scalable detection and recognition of fine-grained events. The framework functions by training high precision and high recall object/optical character recognition (OCR) models and aligning video frames to text commentaries of the videos (e.g., licensed play-by-play). The disclosed framework operates as a single algorithm that performs multimodal alignments between events/actions within videos and their prescribed text. Thus, the disclosed framework is able to scale to fine-grained action categories across different venues by delving into the key frames and key aspects of a video to identify particular actions performed by particular actors, thereby providing the novelty of fine-granted action detection and recognition.
-
公开(公告)号：US20220300764A1
公开(公告)日：2022-09-22
申请号：US17323656
申请日：2021-05-18
Applicant: Toyota Research Institute, Inc.
Inventor： Zhijian Liu , Simon A.I. Stent , John H. Gideon , Jie Li
Abstract: Systems and methods for training a model are described herein. In one example, a system for training the model includes a processor and a memory in communication with the processor having a training module. The training module has instructions that cause the processor to determine a contrastive loss using a self-supervised contrastive loss function, adjust, based on the contrastive loss, model weights a visual backbone that generated feature maps and/or a textual backbone that generated feature vectors. The training module also has instructions that cause the processor to determine a localized loss using a supervised loss function that compares an image-caption attention map with visual identifiers and adjust, based on the localized loss, the model weights the visual backbone and/or the textual backbone.
-
公开(公告)号：US20220300748A1
公开(公告)日：2022-09-22
申请号：US17203583
申请日：2021-03-16
Applicant: TOYOTA RESEARCH INSTITUTE, INC.
Inventor： Pavel V. TOKMAKOV , Rares A. AMBRUS , Wolfram BURGARD , Adrien David GAIDON
Abstract: A method for tracking an object performed by an object tracking system includes encoding locations of visible objects in an environment captured in a current frame of a sequence of frames. The method also includes generating a representation of a current state of the environment based on an aggregation of the encoded locations and an encoded location of each object visible in one or more frames of the sequence of frames occurring prior to the current frame. The method further includes predicting a location of an object occluded in the current frame based on a comparison of object centers decoded from the representation of the current state to object centers saved from each prior representation associated with a different respective frame of the sequence of frames occurring prior to the current frame. The method still further includes adjusting a behavior of an autonomous agent in response to identifying the location of the occluded object.
