-
公开(公告)号：US11265481B1
公开(公告)日：2022-03-01
申请号：US17114198
申请日：2020-12-07
Applicant: Amazon Technologies, Inc.
Inventor： Eliezer Rosengaus , Abhinav Kashyap , Lorenzo Sorgi
Abstract: Described are systems and methods for generating high dynamic range (“HDR”) images based on image data obtained from different image sensors for use in detecting events and monitoring inventory within a materials handling facility. The different image sensors may be aligned and calibrated and the image data from the sensors may be generated at approximately the same time but at different exposures. The image data may then be preprocessed, matched, aligned, and blended to produce an HDR image that does not include overexposed regions or underexposed regions.
-
公开(公告)号：US10739551B1
公开(公告)日：2020-08-11
申请号：US15840739
申请日：2017-12-13
Applicant: Amazon Technologies, Inc.
Inventor： Abhinav Kashyap , Leo Benedict Baldwin , Prachi Pradhan
Abstract: This disclosure describes techniques to compensate for changes in a depth of field of a camera caused by changes in orientation of the camera (e.g., tilt) and changes in the temperature of the camera. For instance, the described techniques may utilize an actuator, such as a voice-coil motor, of the camera to adjust an image distance of the camera lens to compensate for changes in the depth of field of the camera caused by changes in the orientation of the camera and/or changes in temperature of the camera. One or more models may be generated using calibrated input current values for the voice-coil motor which indicate, for various changes in orientation and temperature of the camera, input current values to cause the voice-coil motor to adjust the image distance of the camera to maintain the desired depth of field.
-
公开(公告)号：US12131575B1
公开(公告)日：2024-10-29
申请号：US17663273
申请日：2022-05-13
Applicant: AMAZON TECHNOLOGIES, INC.
Inventor： Manoj Aggarwal , Gerard Guy Medioni , Rajeev Ranjan , Joshua Engelsma , Baomin Wang , Abhinav Kashyap , Dilip Kumar
CPC classification number: G06V40/1365 , G06V10/145 , G06V40/1318 , G06V40/1347 , G06V40/50 , G02B5/208 , G02B5/3025
Abstract: A biometric identification system acquires a multimodal image. The system is trained to determine three embeddings: a first embedding associated with features present in a first modality, an intersection embedding associated with features present in both the first and a second modality, and an XOR embedding associated with features that are not shared between the first modality and the second modality. Once trained, the system may process a multimodal query image to determine query embedding data. Additional information, such as minutiae depicted in the multimodal query image may also be determined. The query embedding data, and in some implementations the additional information, may be compared with enrolled embedding data associated with a previously enrolled user. If the comparison exceeds a threshold value, an identity may be asserted.
-
公开(公告)号：US10863105B1
公开(公告)日：2020-12-08
申请号：US15635031
申请日：2017-06-27
Applicant: Amazon Technologies, Inc.
Inventor： Eliezer Rosengaus , Abhinav Kashyap , Lorenzo Sorgi
Abstract: Described are systems and methods for generating high dynamic range (“HDR”) images based on image data obtained from different image sensors for use in detecting events and monitoring inventory within a materials handling facility. The different image sensors may be aligned and calibrated and the image data from the sensors may be generated at approximately the same time but at different exposures. The image data may then be preprocessed, matched, aligned, and blended to produce an HDR image that does not include overexposed regions or underexposed regions.
-
-
-
Search Results
4
records
(took 0.019 seconds)
