-
公开(公告)号：US12131539B1
公开(公告)日：2024-10-29
申请号：US17853236
申请日：2022-06-29
Applicant: Amazon Technologies, Inc.
Inventor： Chris Broaddus , Jayakrishnan Kumar Eledath , Tian Lan , Hui Liang , Gerard Guy Medioni , Chuhang Zou
CPC classification number: G06V20/44 , G06Q30/0643 , G06T7/70 , G06V10/7715 , G06V10/82 , G06V20/41 , G06V20/46 , G06V40/11 , H04N7/181 , G06T2207/10016 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084 , G06T2207/20132 , G06T2207/30196 , G06T2207/30242
Abstract: Cameras having storage fixtures within their fields of view are programmed to capture images and process clips of the images to generate sets of features representing product spaces and actors depicted within such images, and to classify the clips as depicting or not depicting a shopping event. Where consecutive clips are determined to depict a shopping event, features of such clips are combined into a sequence and transferred, along with classifications of the clips and a start time and end time of the shopping event, to a multi-camera system. A shopping hypothesis is generated based on such sequences of features received from cameras, along with information regarding items detected within the hands of such actors, to determine a summary of shopping activity by an actor, and to update a record of items associated with the actor accordingly.
-
公开(公告)号：US12073571B1
公开(公告)日：2024-08-27
申请号：US17727452
申请日：2022-04-22
Applicant: Amazon Technologies, Inc.
Inventor： Boris Cherevatsky , Roman Goldenberg , Gerard Guy Medioni , Ofer Meidan , Ehud Benyamin Rivlin , Dilip Kumar
IPC: G06T7/292 , G06F18/2113 , G06F18/2415 , G06T7/55 , G06T11/60 , H04N7/18 , H04N23/90
CPC classification number: G06T7/292 , G06F18/2113 , G06F18/2415 , G06T7/55 , G06T11/60 , H04N7/181 , H04N7/188 , H04N23/90 , G06T2207/10024 , G06T2207/10028 , G06T2207/20081 , G06T2210/12
Abstract: The motion of objects within a scene may be detected and tracked using digital (e.g., visual and depth) cameras aligned with fields of view that overlap at least in part. Objects may be identified within visual images captured from the scene using a tracking algorithm and correlated to point clouds or other depth models generated based on depth images captured from the scene. Once visual aspects (e.g., colors or other features) of objects are correlated to the point clouds, shapes and/or positions of the objects may be determined and used to further train the tracking algorithms to recognize the objects in subsequently captured frames. Moreover, a Kalman filter or other motion modeling technique may be used to enhance the prediction of a location of an object within subsequently captured frames.
-
公开(公告)号：US11810362B1
公开(公告)日：2023-11-07
申请号：US16808014
申请日：2020-03-03
Applicant: Amazon Technologies, Inc.
Inventor： Behjat Siddiquie , Jayakrishnan Kumar Eledath , Petko Tsonev , Nishitkumar Ashokkumar Desai , Gerard Guy Medioni , Jean Laurent Guigues , Chuhang Zou , Connor Spencer Blue Worley , Claire Law , Paul Ignatius Dizon Echevarria , Matthew Fletcher Harrison , Pahal Kamlesh Dalal
IPC: G06F16/587 , G06K9/00 , G06V20/52 , G06V10/22 , G06V40/20
CPC classification number: G06V20/52 , G06F16/587 , G06V10/235 , G06V40/20
Abstract: This disclosure describes techniques for updating planogram data associated with a facility. The planogram may indicate inventory locations within the facility for various types of items supported by product fixtures. In particular an image of a product fixture is analyzed to identify image segments corresponding to product groups, where each product group consists of instances of the same product and each image segment corresponds to a group of image points. Image data is further analyzed to determine coordinates of the points of each image segment. A product space corresponding to the product group is then defined based on the coordinates of the points of the product group. In some cases, for example, a product space may be defined in terms of the coordinates of the corners of a rectangular bounding box or volume.
-
公开(公告)号：US11688198B1
公开(公告)日：2023-06-27
申请号：US17457551
申请日：2021-12-03
Applicant: AMAZON TECHNOLOGIES, INC.
Inventor： Rajeev Ranjan , Gerard Guy Medioni , Manoj Aggarwal , Dilip Kumar
IPC: G06V40/13 , G06V10/94 , G06F18/213 , G06F18/214
CPC classification number: G06V40/1318 , G06F18/213 , G06F18/2148 , G06V10/95
Abstract: A biometric identification system uses inputs acquired using different modalities. A model having an intersection branch and an XOR branch is trained to determine an embedding using features present in all modalities (an intersection of modalities), and features that are distinctive to each modality (an XOR of that modality relative to the other modality(s)). During training, a first loss function is used to determine a first loss value with respect to the branches. Probability distributions are determined for the output from the branches, corresponding to the intersection and XORs of each modality. A second loss function uses these probability distributions to determine a second loss value. A total loss function for training the model may be a sum of the first loss and the second loss. Once trained, the model may process query inputs to determine embedding data for comparison with embedding data of a previously enrolled user.
-
公开(公告)号：US11663805B1
公开(公告)日：2023-05-30
申请号：US17209845
申请日：2021-03-23
Applicant: Amazon Technologies, Inc.
Inventor： Zheng Tang , Prithviraj Banerjee , Manoj Aggarwal , Gerard Guy Medioni
CPC classification number: G06V10/25 , G06K9/6215 , G06K9/6262 , G06V40/1335 , G06V40/1347 , G06V40/1365
Abstract: This disclosure describes a user-recognition system that may perform one or more verification methods upon identifying a previous image that matches a current image of a palm of a user. For instance, the user-recognition system may perform the verification method(s) as part of the recognition method (e.g., after recognizing a matching image), in response to an audit process, in response to a request to re-analyze the image data (e.g., because a user indicates that he or she was not associated with a particular purchase or shopping session), and/or the like.
-
Patent Agency Ranking
公开(公告)号：US11482045B1
公开(公告)日：2022-10-25
申请号：US16799502
申请日：2020-02-24
Applicant: Amazon Technologies, Inc.
Inventor： Jaechul Kim , Nishitkumar Ashokkumar Desai , Jayakrishnan Kumar Eledath , Kartik Muktinutalapati , Shaonan Zhang , Hoi Cheung Pang , Dilip Kumar , Kushagra Srivastava , Gerard Guy Medioni , Daniel Bibireata
IPC: G06K9/00 , G06V40/20 , G06K9/62 , G06F17/16 , G06Q30/02 , G06N3/08 , G06N20/00 , G06V20/10 , G06V20/52
Abstract: Where an event is determined to have occurred at a location within a vicinity of a plurality of actors, imaging data captured using cameras having the location is processed using one or more machine learning systems or techniques operating on the cameras to determine which of the actors is most likely associated with the event. For each relevant pixel of each image captured by a camera, the camera returns a set of vectors extending to pixels of body parts of actors who are most likely to have been involved with an event occurring at the relevant pixel, along with a measure of confidence in the respective vectors. A server receives the vectors from the cameras, determines which of the images depicted the event in a favorable view, based at least in part on the quality of such images, and selects one of the actors as associated with the event accordingly.
-
公开(公告)号：US11328513B1
公开(公告)日：2022-05-10
申请号：US15806098
申请日：2017-11-07
Applicant: Amazon Technologies, Inc.
Inventor： Eli Osherovich , Ehud Benyamin Rivlin , Yacov Hel-Or , Dmitri Veikherman , Dilip Kumar , Gerard Guy Medioni , George Leifman
Abstract: Described is a multiple-camera system and process for detecting, tracking, and re-verifying agents within a materials handling facility. In one implementation, a plurality of feature vectors may be generated for an agent and maintained as an agent model representative of the agent. When the object being tracked as the agent is to be re-verified, feature vectors representative of the object are generated and stored as a probe agent model. Feature vectors of the probe agent model are compared with corresponding feature vectors of candidate agent models for agents located in the materials handling facility. Based on the similarity scores, the agent may be re-verified, it may be determined that identifiers used for objects tracked as representative of the agents have been flipped, and/or to determine that tracking of the object representing the agent has been dropped.
-
公开(公告)号：US11232294B1
公开(公告)日：2022-01-25
申请号：US15717792
申请日：2017-09-27
Applicant: Amazon Technologies, Inc.
Inventor： Prithviraj Banerjee , Leonid Pishchulin , Jean Laurent Guigues , Gerard Guy Medioni
Abstract: Actors may be detected and tracked within a scene using multiple imaging devices provided in a network that are aligned with fields of view that overlap at least in part. Processors operating on the imaging devices may evaluate the images using one or more classifiers to recognize body parts within the images, and to associate the body parts with a common actor within the scene. Each of the imaging devices may generate records of the positions of the body parts and provide such records to a central server, that may correlate body parts appearing within images captured by two or more of the imaging devices and generate a three-dimensional model of an actor based on positions of the body parts. Motion of the body parts may be tracked in subsequent images, and the model of the actor may be updated based on the motion.
-
公开(公告)号：US11042836B1
公开(公告)日：2021-06-22
申请号：US16435268
申请日：2019-06-07
Applicant: AMAZON TECHNOLOGIES, INC.
Inventor： Michel Leonard Goldstein , Ramanathan Palaniappan , Fan Sun , Liefeng Bo , Ohil Krishnamurthy Manyam , Navid Shiee , Gerard Guy Medioni
Abstract: Items may be stowed in an inventory location, such as a shelf. An interaction may take place where one of the items is picked from or placed on the inventory location. Sensor data can be acquired from two or more sensors, such as cameras or weight sensors, configured to collect such sensor data for the inventory location. Hypotheses to describe interactions at the inventory location may be determined using sensor data from each different sensor. However, the confidence value for such hypotheses may not be reliable. Fusion of sensor data may be performed where sets of hypotheses from the different sensors are combined and the resulting hypotheses are more accurate.
-
公开(公告)号：US10902280B1
公开(公告)日：2021-01-26
申请号：US16460948
申请日：2019-07-02
Applicant: AMAZON TECHNOLOGIES, INC.
Inventor： Gang Hua , Li Guan , Dilip Kumar , Gerard Guy Medioni
IPC: G06K9/46 , G06T17/20 , G06F16/532 , G06K9/00
Abstract: The presence of an object in a query image may be searched for using a feature of the query image. A local descriptor value for the feature is first determined. Previously stored object data for various 3D objects is then retrieved, with each set of stored object data including a probability distribution that describes a feature of a 3D object as obtained from images at different camera poses. A probability value is then determined using the local descriptor value for the feature in the query image and the available distribution data from the stored object data. The distribution data is then ranked based on the resulting probability values and the highest ranked distribution data is associated with the feature in the query image. Output data may also be generated to identify the 3D object in the query image based on an object identifier of the highest ranked distribution data.
-
-
-
-
-
-
-
-
-
Search Results
66
records
(took 0.045 seconds)
