公开(公告)号：US20230360380A1

公开(公告)日：2023-11-09

申请号：US18044443

申请日：2020-09-11

Applicant: Siemens Aktiengesellschaft

Inventor： Fan Bo Meng ,  Xiang Li ,  Xiao Feng Wang

IPC: G06V10/82 ,  G06V10/75 ,  G06V10/774

CPC classification number: G06V10/82 ,  G06V10/76 ,  G06V10/774 ,  G06V2201/12 ,  G06V2201/07

Abstract: The present disclosure provides methods and/or systems for identifying an object. An example method includes: generating a plurality of synthesized images according to a three-dimensional digital model, the plurality of synthesized images having different view angles; respectively extracting eigenvectors of the plurality of synthesized images; generating a first fused vector by fusing the eigenvectors of the plurality of synthesized images; inputting the first fused vector into a classifier to train the classifier; acquiring a plurality of pictures of the object, the plurality of pictures respectively having same view angles as at least a portion of the plurality of synthesized images; respectively extracting eigenvectors of the plurality of pictures; generating a second fused vector by fusing the eigenvectors of the plurality of pictures; and inputting the second fused vector into the trained classifier to obtain a classification result of the object.

公开(公告)号：US20230360297A1

公开(公告)日：2023-11-09

申请号：US18223279

申请日：2023-07-18

Applicant: HANWHA TECHWIN CO., LTD.

Inventor： Jin Hyuk CHOI ,  Song Taek JEONG ,  Jae Cheon SONG

IPC: G06T11/60 ,  G06T11/00 ,  G06T11/40 ,  G06V40/20 ,  G06V10/44 ,  G06V10/22 ,  G06V20/52 ,  G06V40/16

CPC classification number: G06T11/60 ,  G06T11/001 ,  G06T11/40 ,  G06V40/20 ,  G06V10/44 ,  G06V10/235 ,  G06V20/52 ,  G06V40/172 ,  G06V2201/07

Abstract: An image masking method is provided. The method includes: extracting an object from an image; obtaining characteristic information about the extracted object by analyzing the extracted object; determining whether the extracted object is a masking target according to an input setting value or the obtained characteristic information; and performing masking such that the obtained characteristic information is reflected on the extracted object, in response to determining that the extracted object is the masking target among a plurality of objects extracted from the input image, wherein the setting value is set by an input designating at least a partial region in the input image, and wherein in the determining whether the extracted object is the masking target, an object positioned in the at least a partial region is determined as the masking target among the extracted objects.

公开(公告)号：US20230351803A1

公开(公告)日：2023-11-02

申请号：US18302670

申请日：2023-04-18

Applicant: CANON KABUSHIKI KAISHA

Inventor： YUSUKE TODOROKI

IPC: G06V40/16 ,  G06T7/62 ,  G06T7/70 ,  G06V10/25 ,  G06V10/56 ,  G06V10/764

CPC classification number: G06V40/161 ,  G06T7/62 ,  G06T7/70 ,  G06V10/25 ,  G06V10/56 ,  G06V10/764 ,  G06V2201/07 ,  G06T2207/10024 ,  G06T2207/20084 ,  G06T2207/20132 ,  G06T2207/30201

Abstract: An information processing apparatus includes an object detection unit configured to detect a region of a first object in an image, an editing unit configured to edit the image based on the detected region of the first object, a first attribute detection unit configured to detect a first subject having a first attribute in the edited image, a second attribute detection unit configured to, in a case where the first subject having the first attribute is detected in the edited image, detect a second subject having a second attribute different from the first attribute in the edited image, and a sorting unit configured to sort the edited image based on a result of detecting the second subject having the second attribute.

公开(公告)号：US20230351741A1

公开(公告)日：2023-11-02

申请号：US18302230

申请日：2023-04-18

Applicant: Robert Bosch GmbH

Inventor： Maximilian Menke ,  Reiko Lettmoden ,  Thomas Wenzel

IPC: G06V10/82 ,  G06V10/75 ,  G06V20/58 ,  G06V20/40

CPC classification number: G06V10/82 ,  G06V10/751 ,  G06V20/58 ,  G06V20/49 ,  G06V2201/12 ,  G06V2201/07

Abstract: A computer-implemented method for training a machine learning system for transferring images of a source domain into a target domain. The method includes: ascertaining source patches based on source images of a source domain and target patches based on target images of a target domain, the source patches and the target patches each being assigned pixel-by-pixel pieces of meta-information; ascertaining tuples, each including one source patch and at least one target patch which characterizes a neighbor of the source patch nearest to k according to a similarity measure, k being a hyperparameter of the method and the similarity measure characterizing a similarity between a source patch and a target patch based on the pixel-by-pixel meta-information of the source patch and of the target patch; training the machine learning system based on the source patches of the tuples and on the target patches of the tuples.

公开(公告)号：US20230351724A1

公开(公告)日：2023-11-02

申请号：US17800688

申请日：2020-02-18

Applicant: Google LLC

Inventor： Tingbo Hou ,  Adel Ahmadyan ,  Jianing Wei ,  Matthias Grundmann

IPC: G06V10/75 ,  G06V10/80 ,  G06V20/40 ,  G06T7/70

CPC classification number: G06V10/751 ,  G06V10/817 ,  G06V20/46 ,  G06T7/70 ,  G06V2201/12 ,  G06V2201/07 ,  G06T2207/20081

Abstract: The present disclosure is directed to systems and methods for performing object detection and pose estimation in 3D from 2D images. Object detection can be performed by a machine-learned model configured to determine various object properties. Implementations according to the disclosure can use these properties to estimate object pose and size.

公开(公告)号：US20230343141A1

公开(公告)日：2023-10-26

申请号：US18136397

申请日：2023-04-19

Applicant: ANIRUDHA SURABHI VENKATA JAGANNADHA RAO

Inventor： ANIRUDHA SURABHI VENKATA JAGANNADHA RAO

IPC: G06V40/20 ,  G06V20/40

CPC classification number: G06V40/23 ,  G06V20/44 ,  G06V2201/07

Abstract: A system for identifying location and direction of impact events in real-time comprises an impact event monitoring device includes multiple sensors, a processing device, and a memory unit. The sensors and the memory unit are electrically coupled to the processing device. The sensors configured to measure impact parameters, the impact parameters include quaternions, Euler angles, vital statistics, rotational angle of the head of the individual and the object, motion of the individual and the object, gyroscope vectors, and velocity. The measured impact parameters are transmitted to the processing device and is configured to analyze measured impact parameters and create impact data of impact events, second computing device includes an impact event reporting module. The impact event reporting module configured to receive the impact data of the impact events from the processing device thereby enabling an emergency service provider to determine severity of impact events to provide better treatment to the individual.

公开(公告)号：US20230339734A1

公开(公告)日：2023-10-26

申请号：US17660739

申请日：2022-04-26

Applicant: Deere & Company

Inventor： Scott R. Stahle ,  Doug M. Lehmann ,  Rachel Bruflodt ,  Samantha F. Echaves ,  Harry E. Rawlins ,  Giovanni A. Wuisan

IPC: B60W50/14 ,  G06V20/58 ,  B66F9/075 ,  B60W30/182 ,  B60K35/00

CPC classification number: B66F9/0755 ,  B60K35/00 ,  B60W30/182 ,  B60W50/14 ,  G06V20/58 ,  B60K2370/119 ,  B60K2370/176 ,  B60K2370/179 ,  B60W2050/146 ,  B60W2300/121 ,  B60W2420/42 ,  B60W2554/80 ,  B60W2556/45 ,  G06V2201/07

Abstract: A method and system of controlling a work machine having an object detection system. The method comprises capturing an image with a camera and then recognizing an object in the image with the object detection. In next steps, the method includes defining the recognized object as a target object and operating the work machine wherein the object detection system is configured to execute a function of the work machine when the object is recognized. Finally, the method includes overriding the execution of the function of the object detection system when the object is defined as the target object.

公开(公告)号：US11794731B2

公开(公告)日：2023-10-24

申请号：US17308688

申请日：2021-05-05

Applicant: FORD GLOBAL TECHNOLOGIES, LLC

Inventor： Siddhesh Shyam Khandelwal ,  William Junbo Qi ,  Jagjeet Singh ,  Andrew T. Hartnett ,  Deva Ramanan

IPC: B60W30/09 ,  B60W60/00 ,  B60W30/095 ,  G06V40/20 ,  G06V20/56

CPC classification number: B60W30/09 ,  B60W30/0953 ,  B60W30/0956 ,  B60W60/0015 ,  G06V20/56 ,  G06V40/25 ,  B60W2420/42 ,  B60W2420/52 ,  B60W2554/4029 ,  B60W2554/4044 ,  B60W2554/4045 ,  B60W2554/4046 ,  G06V2201/07

Abstract: Systems and methods of determining trajectories of an actor in an environment in which a vehicle is operating are provided. The method includes, by an object detection system of a vehicle in an environment, detecting an actor that may move within a scene in the environment. The method further includes using context of the scene to determine a reference polyline for the actor and determining a kinematic history of the actor. The method additionally includes using the kinematic history to predict a waypoint, which is a predicted position of the actor at a conclusion of a waypoint time period, and identifying a segment of the reference polyline, the segment extending from a current location to a point along the reference polyline that is closest to the waypoint and determining a trajectory for the actor conditioned by the segment of the reference polyline.

公开(公告)号：US20230334928A1

公开(公告)日：2023-10-19

申请号：US18214253

申请日：2023-06-26

Applicant: NEC Corporation

Inventor： Taketo KOCHI ,  Kenji Saito

IPC: G07C9/37 ,  G07C9/10 ,  G06V40/16 ,  G06V10/22 ,  G06V20/52

CPC classification number: G07C9/37 ,  G07C9/10 ,  G06V40/171 ,  G06V40/165 ,  G06V10/22 ,  G06V20/52 ,  G06V40/166 ,  G06V40/172 ,  G06V2201/07

Abstract: A collation system of the present invention includes imaging means for acquiring a captured image of a pre-passage side area with respect to each of gates arranged in parallel with each other, and collation means for performing a collation process on the captured image of the pre-passage side area for each of the gates, between a previously registered target and a target included in the captured image. The collation means performs the collation process on the basis of a target in the captured image corresponding to one of the gates and a target in the captured image corresponding to another one of the gates.

公开(公告)号：US11790656B2

公开(公告)日：2023-10-17

申请号：US17359200

申请日：2021-06-25

Applicant: COGNEX CORPORATION

Inventor： Torsten Kempf ,  Saul Sanz Rodriguez ,  Pepe Fernandez-Dorado ,  Laurens Nunnink

IPC: G06V20/52 ,  G05D1/02 ,  G02B26/08 ,  G05D1/00 ,  G06V20/56 ,  G06V10/147

CPC classification number: G06V20/52 ,  G02B26/0833 ,  G05D1/0094 ,  G05D1/0231 ,  G06V10/147 ,  G06V20/56 ,  G06V2201/07

Abstract: A computer-implemented method for scanning a side of an object to identify a region of interest is provided. The method can include determining, using one or more computing devices, a distance between a side of an object and an imaging device, determining, using the one or more computing devices, a scanning pattern for an imaging device that includes a controllable mirror, based on the distance between the side of the object and the imaging device, moving a controllable mirror according to the scanning pattern to acquire, using the one or more computing device and the imaging device, a plurality of images of the side of the object, and identifying, using the one or more computing devices, the region of interest based on the plurality of images.