专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

DE112020006045T5 FORMAL SICHERES SYMBOLISCHES BESTÄRKENDES LERNEN ANHAND VON VISUELLEN EINGABEN 未知
公开(公告)号：DE112020006045T5
公开(公告)日：2022-10-06
申请号：DE112020006045
申请日：2020-12-07
申请人： IBM
发明人： DAS SUBHRO , HUNT NATHAN , FULTON NATHANIEL RYAN , HOANG TRONG NGHIA
IPC分类号： G06V20/50 , G05D1/00 , G06N20/00 , G06V10/70
摘要： Ein Verfahren zum Trainieren von Steuerungs-Software zum Bestärken von Sicherheitseinschränkungen mithilfe von visuellen Eingaben enthält ein Durchführen eines Vorlagenabgleichs für jedes Objekt in einem Bild eines Aktionsraums eines Agenten für bestärkendes Lernen (RL) mithilfe einer visuellen Vorlage für jedes Objekt, wobei jedes Objekt in dem Aktionsraum des RL-Agenten erkannt wird, ein Zuordnen jedes erkannten Objekts zu einem Satz von planaren Koordinaten für jedes Objekt in dem Aktionsraum des RL-Agenten, ein Ermitteln eines Satzes von sicheren Aktionen für den RL-Agenten durch Anwenden einer Sicherheitsspezifikation für den Aktionsraum des RL-Agenten auf den Satz von Variablen für Koordinaten für jedes Objekt in dem Aktionsraum des RL-Agenten, ein Ausgeben des Satzes von sicheren Aktionen an den RL-Agenten für einen aktuellen Zustand einer RL-Prozedur, und ein Verhindern, dass der RL-Agent eine Aktion ausführt, die unsicher ist, bevor der RL-Agent eine Aktion durchführt.

2. 发明专利

CA3143837A1 AUTOMATED USABILITY ASSESSMENT OF BUILDINGS USING VISUAL DATA OF CAPTURED IN-ROOM IMAGES 未知
公开(公告)号：CA3143837A1
公开(公告)日：2022-08-25
申请号：CA3143837
申请日：2021-12-23
申请人： ZILLOW INC
发明人： STOEVA VIKTORIYA , KANG SING BING , KHOSRAVAN NAJI , WIXSON LAMBERT E
IPC分类号： G06V20/50 , G06N3/02 , G06Q50/16 , G06V10/10 , G06V20/60
摘要： Techniques are described for automated operations related to analyzing visual data from images captured in rooms of a building and optionally additional captured data about the rooms to assess room layout and other usability information for the building's rooms and optionally for the overall building, and to subsequently using the assessed usability information in one or more further automated manners, such as to improve navigation of the building. The automated operations may include identifying one or more objects in each of the rooms to assess, evaluating one or more target attributes of each object, assessing usability of each object using its target attributes' evaluations and each room using its objects' assessment and other room information with respect to an indicated purpose, and combining the assessments of multiple rooms in a building and other building information to assess usability of the building with respect to its indicated purpose.

3. 发明专利

AU2020393199B2 Crowdsourced on-demand AI data annotation, collection and processing 未知
公开(公告)号：AU2020393199B2
公开(公告)日：2022-07-28
申请号：AU2020393199
申请日：2020-11-27
申请人： RATTI JAYANT
发明人： RATTI JAYANT , BOSE ABHISHEK , KASHYAP PUNEET
IPC分类号： G06V20/50 , G06K9/62 , G06V10/20 , G06V20/70
摘要： In an aspect of the present disclosure relates to a network involving humans and AI based systems working in conjunction to perform tasks such as traffic violation detection, infrastructure monitoring, traffic flow management, crop monitoring etc. from visual data acquired from numerous data acquisition sources. The system includes a network of electronic mobile devices with AI capabilities, connected to a decentralized network working towards capturing high quality data for finding events or objects of interest in the real world, retraining AI models, for processing the high volumes of data on decentralized or centralized processing units and also being used for the verification of the outputs of the AI models. The system talks about many annotation techniques on smartphones for crowdsourced AI Data Labeling for AI Training.

4. 发明专利

LU501360B1 COOPERATIVE DRIVING CONTROL SYSTEM FOR INTELLIGENT VEHICLE AND MULTI-VEHICLE COOPERATIVE DRIVING CONTROL SYSTEM 未知
公开(公告)号：LU501360B1
公开(公告)日：2022-08-10
申请号：LU501360
申请日：2022-01-28
申请人： UNIV SHENZHEN TECHNOLOGY
发明人： LI DAI , CHENG TAO , CAI YONGWEI
IPC分类号： H04W4/40 , B60W50/00 , G06V20/50
摘要： The embodiment of the present disclosure discloses a cooperative driving control system for intelligent vehicle and a multi-vehicle cooperative driving control system. The cooperative driving control system for intelligent vehicle comprises: an on-board controller, an environment sensing device, a positioning device, an on-vehicle wireless communication module, and a cloud communication module. The on-board controller is electrically connected with the environment sensing device, the positioning device, the on-vehicle wireless communication module and the cloud communication module respectively. The on-board controller is further configured to control a driving of the intelligent vehicle based on an artificial fish algorithm and according to vehicle external environment information, location and attitude information, other vehicle external environment information and other location and attitude information. In an embodiment of the present disclosure, the vehicle external environment information and the location and attitude information of the intelligent vehicle are obtained, and the other vehicle external environment information and the other location and attitude information of the other intelligent vehicle needing a cooperative driving are also obtained, such that an intelligent driving control for the intelligent vehicle is performed, and the cooperative driving with other intelligent vehicle is carried out, therefore the embodiment has the advantages of good cooperation, high intelligence, and high safety.

5. 发明专利

DE112020004377T5 BILDERKENNUNGSVORRICHTUNG 未知
公开(公告)号：DE112020004377T5
公开(公告)日：2022-07-07
申请号：DE112020004377
申请日：2020-09-08
申请人： HITACHI ASTEMO LTD
发明人： USHIBA HIROYUKI , TOKI RYOSUKE
IPC分类号： G06T7/70 , G06V20/50
摘要： Es wird eine Bilderkennungsvorrichtung geschaffen, die einen dreidimensionalen Gegenstand genau detektieren und eine Erkennungsleistung verbessern kann, während eine Kostenerhöhung unterbunden wird. Eine Erkennung, bei der Pixelinformationen und Abstandsinformationen oder Parallaxeninformationen kombiniert werden, ist implementiert durch Normieren der Abstandsinformationen oder der Parallaxeninformationen des dreidimensionalen Gegenstands, der ein Erkennungsziel ist, durch Maskieren der von jenen des Erkennungsziels verschiedenen Abstandsinformationen oder Parallaxeninformationen, Ändern einer Gewichtung für die Pixelinformationen und die Abstandsinformationen oder die Parallaxeninformationen oder Kombinieren der Pixelinformationen und der Abstandsinformationen oder der Parallaxeninformationen, für Informationen von jedem Pixel, die von den Kameras 101 und 102 oder einer Kamera 1101 erhalten werden, und Informationen über einen Abstand oder eine Parallaxe, die diesem entsprechen.

6. 发明专利

FI13286Y1 Konenäköön ja -kuuloon perustuva vaikuttamisalusta 未知
公开(公告)号：FI13286Y1
公开(公告)日：2022-10-27
申请号：FIU20220046
申请日：2022-06-10
申请人： RIIHIMAEKI MATTI RAINER
发明人： RIIHIMÄKI MATTI RAINER
IPC分类号： F41F3/00 , F41A23/00 , G06V20/50 , G06V20/56 , G10L25/78
摘要： 1. Vaikuttamisalusta, johon kuuluu kiinnitysosaan (6) kiinnitetty havainto-osa (5), tunnettu siitä, että kiinnitysosa (6), jonka keskilinja on yhdensuuntainen havainto-osan (5) keskilinjan kanssa, suunnataan kohteeseen moottoroidussa alustassa (7) olevilla kääntömekanismeilla konenäkö- ja kuulolaitteet (4) sisältävän havainto-osan (5) tuottaman tiedon perusteella, jolloin kiinnitysosaan (6) kytketty torjuntalaite (9) voidaan laukaista kohteeseen laukaisumekanismilla (8). Lisäksi suojavaatimukset 2-5.

7. 发明专利

CA3173451A1 SYSTEM FOR WELDING AT LEAST A PORTION OF A PIECE AND RELATED METHODS 未知
公开(公告)号：CA3173451A1
公开(公告)日：2022-09-29
申请号：CA3173451
申请日：2022-03-29
申请人： POLY ROBOTICS INC
发明人： BERARD LOUIS , DALLAIRE MATS , DALLAIRE JOLAIN
IPC分类号： B23K37/00 , B23K26/03 , B23K26/042 , B23K26/08 , B25J9/16 , B25J19/02 , B25J19/04 , G01B11/00 , G06T5/00 , G06T7/00 , G06V20/50 , H04N7/18
摘要： The present disclosure concerns a system and associated method for welding a piece. The system includes a 6-axis welding robot including a robotized arm, a vision module and a computing device. The vision module is mounted to a fourth axis of the robotized arm and includes optical sources and a camera. The optical sources are operable to irradiate the piece along irradiation paths. The camera is configured to receive irradiated light from the piece and to generate image data. The computing device is operatively connected to the camera and includes non-transitory computer readable storage medium having stored instructions that, when executed by a processor causes the processor to receive the image data; obtain a reference welding path to be followed by the welding robot for welding the piece; send instructions to the welding robot to weld the piece according to the reference welding path.

8. 发明专利

CA3143792A1 AUTOMATED DIRECTION OF CAPTURING IN-ROOM INFORMATION FOR USE IN USABILITY ASSESSMENT OF BUILDINGS 未知
公开(公告)号：CA3143792A1
公开(公告)日：2022-08-25
申请号：CA3143792
申请日：2021-12-23
申请人： ZILLOW INC
发明人： WIXSON LAMBERT E , BUEHLER CHRISTOPHER
IPC分类号： G06V20/50 , G06N3/02 , G06Q50/16 , G06V10/10 , G06V20/60
摘要： Techniques are described for automated operations related to analyzing visual data from images captured in rooms of a building and optionally additional captured data about the rooms to assess room layout and other usability information for the building's rooms and optionally for the overall building, and to subsequently using the assessed usability information in one or more further automated manners, such as to improve navigation of the building. The automated operations may include identifying one or more objects in each of the rooms to assess and one or more target attributes of each object, and generating and providing instructions to cause the capture of images and optionally additional data about those objects and target attributes for further automated analysis, such as instructions provided to an automated image acquisition device in the room and/or an associated user. Once received, the captured images and other data is then analyzed accordingly.

9. 发明公开

CN118968038A 目标检测方法、装置、设备、存储介质及产品审中-公开
公开(公告)号：CN118968038A
公开(公告)日：2024-11-15
申请号：CN202411428765.5
申请日：2024-10-14
申请人：杭州海康威视数字技术股份有限公司
发明人：徐秉政 , 付艳红 , 蒋煜华 , 张睿轩
IPC分类号： G06V10/25 , G06V20/50 , G06V10/764 , G06V10/774 , G06V10/82 , G06N3/0464 , G06N3/0455
摘要：本申请涉及图像检测技术领域，公开了目标检测方法、装置、设备、存储介质及产品，包括：获取目标检测区域的场景图像；通过二级检测模型对场景图像中的场景特征进行检测，获得场景图像对应的场景划分信息；将场景划分信息发送至前端设备，以使前端设备基于场景划分信息将目标检测区域划分为多个场景区域，并根据各场景区域的场景类型获取各场景区域对应的模型参数，通过一级检测模型根据各场景区域对应的模型参数分别对各场景区域进行目标检测。由于可以针对不同的场景采用不同的模型参数分别进行检测，实现小模型的参数自适应，保证检测时可以根据场景区域的差异进行针对性检测，从而提高检测的性能。

10. 发明公开

CN118942021A 一种两栖跨介质环境下的机器人自主定位方法及设备与应用审中-公开
公开(公告)号：CN118942021A
公开(公告)日：2024-11-12
申请号：CN202410983378.1
申请日：2024-07-22
申请人：华中科技大学
发明人：龚泽宇 , 冯慧 , 陶波 , 顾振峰 , 周颐 , 陈超 , 胡瑞文
IPC分类号： G06V20/50 , G06V10/764 , G06T5/80 , G06T1/00
摘要：本发明属于机器人应用相关技术领域，其公开了一种两栖跨介质环境下的机器人自主定位方法及设备与应用，该方法包括以下步骤：将水下、水上、中间态三种环境下的多张单通道的深度图转化为与其深度值有对应关系的带三通道的具有RGB颜色信息的伪深度图，并基于伪深度图构建图像分类模型；采用所述图像分类模型区分出采集到的图像所处的状态，并对水下状态的RGB图像和左右目图像进行畸变校正；将校正后的图像传入视觉惯性里程计中，继而实现两栖跨介质环境下的机器人自主定位。本发明可以仅依靠相机获取的图像判断图像所处状态为水上还是水下，无需引入湿度传感器等外界电路部分，降低了成本，并且避免了电信号转成相机图像状态判别的繁琐过程。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式