公开(公告)号：WO2023059962A1

公开(公告)日：2023-04-13

申请号：PCT/US2022/075542

申请日：2022-08-26

Applicant: QUALCOMM INCORPORATED

Inventor： PARK, Hee Jun ,  GOEL, Abhinav ,  KANG, Young Hoon

IPC: G06V10/44 ,  G06V10/62 ,  G06V10/82 ,  G06V10/96 ,  G06V10/20 ,  G06V10/255 ,  G06V10/454

Abstract: Systems and techniques are provided for vision perception processing. An example method can include determining an attention demand score or characteristic per region of a frame from a sequence of frames; generating attention votes per region of the frame based on the attention demand score or characteristic per region, the attention votes per region providing attention demands and/or attention requests; determining an attention score or characteristic per region of the frame based on a number of attention votes from one or more computer vision functions; based on the attention score or characteristic per region of the frame, selecting one or more regions of the frame for processing using a neural network; and detecting or tracking one or more objects in the one or more regions of the frame based on processing of the one or more regions using the neural network.

公开(公告)号：WO2023012050A1

公开(公告)日：2023-02-09

申请号：PCT/EP2022/071316

申请日：2022-07-29

Applicant: CONTINENTAL AUTONOMOUS MOBILITY GERMANY GMBH

Inventor： DHIMAN, Ashish ,  REDDY, Deepak ,  RAMACHANDRAN, Radhika ,  PONKUMAR, Senthil

IPC: G06V10/20 ,  G06V10/764 ,  G06V20/58

Abstract: A method and road sign recognition system (101) for recognizing and classifying restricted road signs for vehicle automation system is disclosed. The road sign recognition system (101) obtains plurality of images from predefined regions of restricted road sign image. The road sign recognition system (101) identifies one of presence or absence of predefined pattern in plurality of images at predefined regions. On identifying presence of predefined pattern, road sign image is classified as one of height restricted sign or width restricted sign depending on position of predefined pattern. On identifying absence of predefined pattern, segments are extracted from predefined areas of road sign image and road sign image is classified as either speed limit sign or weight restricted sign based on the number of valid segments.

公开(公告)号：WO2023003646A1

公开(公告)日：2023-01-26

申请号：PCT/US2022/032588

申请日：2022-06-08

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： WANG, Lijuan ,  LIU, Zicheng ,  JIN, Ying ,  DENG, Hongli ,  LUO, Kun ,  YU, Pei ,  CHEN, Yinpeng

IPC: G06V10/20 ,  G06V10/422 ,  G06V10/82 ,  G06V40/10

Abstract: To improve the accuracy and efficiency of object detection through computer digital image analysis, the detection of some objects can inform the sub-portion of the digital image to which subsequent computer digital image analysis is directed to detect other objects. In such a manner object detection can be made more efficient by limiting the image area of a digital image that is analyzed. Such efficiencies can represent both computational efficiencies and communicational efficiencies arising due to the smaller quantity of digital image data that is analyzed. Additionally, the detection of some objects can render the detection of other objects more accurate by adjusting confidence thresholds based on the detection of those related objects. Relationships between objects can be utilized to inform both the image area on which subsequent object detection is performed and the confidence level of such subsequent object detection.

公开(公告)号：WO2023277473A1

公开(公告)日：2023-01-05

申请号：PCT/KR2022/009095

申请日：2022-06-27

Applicant: 주식회사 펫나우

Inventor： 박대현 ,  임준호

IPC: G06V40/10 ,  G06V10/764 ,  G06V10/40 ,  G06V10/10 ,  G06V10/20 ,  G06V10/82 ,  G06V10/84 ,  G06N3/08 ,  G06N3/04

Abstract: 본 발명은 연산 복잡도를 감소시키면서 반려 동물의 식별을 위한 객체를 효과적으로 검출할 수 있는 영상 처리 방법 및 전자 장치를 제공한다. 본 발명에 따른 반려 동물의 식별을 위한 객체를 검출하기 위한 방법은, 상기 반려 동물이 포함된 원본 영상을 획득하는 단계와, 상기 원본 영상에 대한 영상 처리를 통해 제1 특징 영역과 상기 반려 동물의 종(種)을 결정하는 단계와, 상기 결정된 반려 동물의 종에 기초하여 상기 제1 특징 영역 내에서 상기 반려 동물의 식별을 위한 객체를 검출하는 단계를 포함한다.

公开(公告)号：WO2022250740A1

公开(公告)日：2022-12-01

申请号：PCT/US2021/071251

申请日：2021-08-23

Applicant: BRPH ARCHITECTS ENGINEERS, INC.

Inventor： MYERS, Mark ,  MAROQUIN, Henry

IPC: G06F30/13 ,  G06V10/20 ,  G06F119/20

Abstract: A method for generating computer-readable instructions to automatically generate a three-dimensional architectural model Including: receiving a human-readable text file comprising a description of functional elements of a structure, parsing the text file to identify keywords comprised by the text file, generating a plurality of datasets responsive to the key words; generating instructions to create level objects responsive to the datasets, instructions to create floor objects responsive to the datasets and the level objects, instructions to create exterior wall objects responsive to the plurality of datasets and the one or more level objects, instructions to create interior wall objects responsive to the and level objects, instructions to create room objects responsive to the datasets, level objects, exterior wall objects, and interior wall objects, and providing the instructions to architectural modeling software.

公开(公告)号：WO2022236277A1

公开(公告)日：2022-11-10

申请号：PCT/US2022/072101

申请日：2022-05-04

Applicant: BAKER HUGHES HOLDINGS LLC

Inventor： QIAN, Weiwei ,  HARE, John ,  SHAPIRO, Vladimir ,  DHANANI, Taufiq ,  HUNTER, Rick ,  HOANG, Thai ,  WHITING, Ozge Can

IPC: G06T17/20 ,  G06T7/60 ,  G06V10/20 ,  G06Q50/10

Abstract: A method for determining a change in an asset and/or a characterization of an asset is provided. In an embodiment, the method can include receiving first data characterizing a target site including one or more assets. The method can also include generating a three-dimensional model of the target site based on the first data. The method can further include registering the first data with the three-dimensional model. The method can also include generating at least one three-dimensional projection onto at least one asset of the one or more assets included in the first data. The method can further include determining second data characterizing the at least one asset based on the at least on three-dimensional projection and providing the second data. In some embodiments, the method can be performed by systems or stored as instructions on computer readable mediums described herein.

公开(公告)号：WO2022212577A1

公开(公告)日：2022-10-06

申请号：PCT/US2022/022643

申请日：2022-03-30

Applicant: SNAP INC.

Inventor： SAINT-PREUX, Bertrand

IPC: H04N5/232 ,  G06V10/20 ,  H04N5/262 ,  G06T5/00 ,  G06F3/04845 ,  G06F3/0482 ,  G06F3/04847 ,  G06V40/161 ,  H04N17/002 ,  H04N5/23216 ,  H04N5/23219 ,  H04N5/23222 ,  H04N5/23229 ,  H04N5/232933 ,  H04N5/232935 ,  H04N5/2621

Abstract: Method of generating modified media content item based on user's setting selection starts with a processor causing a camera personalization interface to be displayed by a display of a client device. The processor receives a setting selection from the client device via the camera personalization interface. The processor determines a pre-capture setting and a post-processing setting based on the setting selection. The processor calibrates a camera of the client device using the pre-capture setting. The processor receives a media content item including an image captured using the camera and generates a modified media content item by modifying the media content item using the post-processing setting. Other embodiments are described herein.

公开(公告)号：WO2022198190A1

公开(公告)日：2022-09-22

申请号：PCT/US2022/071129

申请日：2022-03-14

Applicant: SENSORMATIC ELECTRONICS, LLC

Inventor： SUBRAMANIAN, Gopi ,  CELI, Joseph

IPC: G06V10/20 ,  G06T7/246 ,  G06V10/75 ,  G06V20/52

Abstract: A system may be configured to perform object counting in high volume traffic. In some aspects, the system may detect a candidate object within the region of interest in a current video frame, and determine that the candidate object is a detected object based at least in part on comparing an attribute value of the candidate object to historic attribute information determined during a plurality of previous video frames. Further, the system may determine track information based on the detected object and determine an object count representing a number of the objects that have entered the region of interest and/or a number of the objects that have exited the region of interest.

公开(公告)号：WO2022198185A1

公开(公告)日：2022-09-22

申请号：PCT/US2022/071124

申请日：2022-03-14

Applicant: SENSORMATIC ELECTRONICS, LLC

Inventor： SUBRAMANIAN, Gopi ,  CELI, Joseph

IPC: G06V10/20 ,  G06T7/246 ,  G06V10/75 ,  G06V20/52

Abstract: A system may be configured to perform object counting in high volume traffic. In some aspects, the system may determine object detection information defining an absence of an object within the region of interest in a current video frame, and determine that a location associated with the object is within a placeholder-eligible area within the region of interest based on first tracker information determined in a previous video frame. Further, the system may determine second tracker information including a bounding representation for the object based at least in part on the location and object detection information, and determine, based on the second tracker information, an object count representing a number of the objects that have entered the region of interest and/or a number of the objects that have exited the region of interest.

公开(公告)号：WO2021243743A1

公开(公告)日：2021-12-09

申请号：PCT/CN2020/095549

申请日：2020-06-11

Applicant: 青岛理工大学

Inventor： 曹金凤 ,  郭继鸿 ,  安伟 ,  李建伟 ,  撒占友

IPC: G06K9/00 ,  G06K9/6273 ,  G06V10/20 ,  G06V10/267 ,  G06V20/10

Abstract: 本发明涉及沉底油探测技术领域，具体涉及基于深度卷积神经网络的沉底油声呐探测图像识别方法。包含声呐探测图像预处理模块和深度卷积神经网络沉底油目标识别模块。本发明将深度卷积神经网络算法引入沉底油探测与识别，解决沉底油目标识别自动化、泄漏位置定位自动化、估算沉底油污染面积自动化等关键难题，为海洋溢油事故应急决策及处置提供依据，提高我国沉底油探测与识别技术的水平，为国家海洋安全和石油安全提供技术支持，具有重要的工程意义和应用价值。