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. 发明申请

WO2023059962A1 EFFICIENT VISION PERCEPTION 审中-公开
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
申请人： QUALCOMM INCORPORATED
发明人： PARK, Hee Jun , GOEL, Abhinav , KANG, Young Hoon
IPC分类号： G06V10/44 , G06V10/62 , G06V10/82 , G06V10/96 , G06V10/20 , G06V10/255 , G06V10/454
摘要： 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.

2. 发明申请

WO2023009557A1 IMPROVED INFERENCING USING NEURAL NETWORKS 审中-公开
公开(公告)号：WO2023009557A1
公开(公告)日：2023-02-02
申请号：PCT/US2022/038402
申请日：2022-07-26
申请人： NVIDIA CORPORATION
发明人： KHINVASARA, Tushar Santosh , PURANDARE, Kaustubh Shriharsh
IPC分类号： G06V20/58 , G06V10/82 , G06V10/94 , G06V10/96
摘要： Apparatuses, systems, and techniques to use data obtained from an inferred object to determine whether to re-infer the same inferred object. In at least one embodiment, data obtained from inferencing a tracked object among a set of images is used to adjust a set of conditions.

3. 发明申请

WO2023017317A1 ENVIRONMENTALLY AWARE PREDICTION OF HUMAN BEHAVIORS 审中-公开
公开(公告)号：WO2023017317A1
公开(公告)日：2023-02-16
申请号：PCT/IB2022/000458
申请日：2022-08-15
申请人： HUMANISING AUTONOMY LIMITED
发明人： NOOTEBOOM, Leslie, Cees , BOSE, Raunaq , PINDEUS, Maya, Audrey, Lara , NOY, Dominic , EVERARD, James, Over , PRADEEP, Yazhini, Chitra
IPC分类号： G06V20/58 , G06V20/40 , G06V10/96 , B60W60/00
摘要： A behavior prediction system predicts human behaviors based on environment-aware information such as camera movement data and geospatial data. The system receives sensor data of a vehicle reflecting a state of the vehicle at a given time and a given location. The system determines a field of concern in images of a video stream and determines one or more portions of images of the video stream that correspond to the field of concern. The system may apply different levels of processing powers to objects in the images based on whether an object is in the field of concern. The system then generates features of objects and identify VRUs from the objects of the video stream. For the identified VRUs, the system inputs a representation of the VRUs and the features into a machine learning model, and outputs from the machine learning model a behavioral risk assessment of the VRUs.

4. 发明申请

WO2022094621A1 REMOTE VEHICLE DAMAGE ASSESSMENT 审中-公开
公开(公告)号：WO2022094621A1
公开(公告)日：2022-05-05
申请号：PCT/US2021/072151
申请日：2021-11-01
申请人： TRACTABLE, INC. , TRACTABLE LTD
发明人： CHATFIELD, Ken , RANCA, Razvan
IPC分类号： G06V10/40 , G06N3/02 , G06V10/764 , G06V10/96 , H04N5/225 , H04N5/247
摘要： A user device includes a camera configured to capture a series of images of a vehicle and a processor configured to receive a first image of the vehicle from a first viewpoint, classify, for the first image, one or more parts of the vehicle captured in the first image, generate, for the first image, a first graphic indicating the parts of the vehicle being displayed in the first image and a display configured to receive the first image and the first graphic from the processor and display the first image of the vehicle with the first graphic indicating the parts of the vehicle being displayed in the first image

5. 发明申请

WO2023049709A1 SECURE EDGE PLATFORM USING IMAGE CLASSIFICATION MACHINE LEARNING MODELS 审中-公开
公开(公告)号：WO2023049709A1
公开(公告)日：2023-03-30
申请号：PCT/US2022/076725
申请日：2022-09-20
申请人： SANDOVAL CUSTOM CREATIONS, INC.
发明人： SANDOVAL, Shaun , CARPENTER, Chad , SMOLENAK, Joshua , STRAATMEYER, James , SCHOBORG, Tony
IPC分类号： G06V10/764 , G06V20/52 , G06V40/16 , G06V10/74 , G06K9/62 , G06V20/62 , G06V10/94 , G06V10/96
摘要： Methods, systems, and apparatus, including medium-encoded computer program products, for a secure edge platform that uses image classification machine learning models. An edge platform can include at least one camera and can identify image classification models that generate classification output data from image data generated by the cameras. The edge platform can receive image data generated by the camera, and provide the image data to the models. In response to providing the image data classification models, the edge platform can receive classification output data. In response to receiving the classification output data from the image classification models, the edge platform can generate augmentation data that is associated with the image data, then transmit detection data to a central server platform. The detection data, can include (i) the classification output data and (li) the augmentation data associated with the image data.. Data can be made recordable, reportable, searchable, and alarmable.

6. 发明申请

WO2023284982A1 A METHOD FOR CONTROLLING A MAXIMUM ALLOWED SPEED OF AN AUTONOMOUS VEHICLE 审中-公开
公开(公告)号：WO2023284982A1
公开(公告)日：2023-01-19
申请号：PCT/EP2021/070027
申请日：2021-07-16
申请人： VOLVO AUTONOMOUS SOLUTIONS AB
发明人： BERGQUIST, Stefan , HAGVALL, Linus
IPC分类号： B60W60/00 , B60W30/09 , G06V20/56 , G06V10/96 , G06V10/94
摘要： The invention relates to a method for controlling a maximum allowed speed of an autonomous vehicle (100), wherein the autonomous vehicle (100) comprises at least one object detection sensor (120) which is configured to detect objects around the vehicle, such as ahead of the vehicle, when the vehicle is driving autonomously, and wherein the at least one object detection sensor (120) is configured to utilize at least two different sensor performance levels, wherein each sensor performance level is associated with a maximum allowed speed for the autonomous vehicle, the method comprising: - utilizing (S1) a first sensor performance level (PL1) during driving where the vehicle is allowed to drive with a first maximum allowed speed, - while utilizing the first sensor performance level (PL1), simultaneously evaluating (S2) at least a second sensor performance level (PL2) which is associated with a second maximum allowed speed which is higher than the first maximum allowed speed and which is a less restrictive sensor performance level, wherein a less restrictive sensor performance level is a sensor performance level with a higher probability of false positive object detections, wherein evaluating the second sensor performance level (PL2) comprises monitoring (S21) a rate of false positive object detections for the second sensor performance level (PL2), - when the rate of false positive object detections for the second sensor performance level (PL2) is below a first false positive error threshold, utilizing (S3) a less restrictive sensor performance level which is associated with a higher maximum allowed speed, thereby increasing the maximum allowed speed from the first maximum allowed speed to a speed which is equal to or below the second maximum allowed speed. The invention also relates to a control unit (110), an autonomous vehicle (100), a computer program and to a computer readable medium.

7. 发明申请

WO2022271084A1 METHOD AND SYSTEM FOR GATHERING IMAGE TRAINING DATA FOR A MACHINE LEARNING MODEL 审中-公开
公开(公告)号：WO2022271084A1
公开(公告)日：2022-12-29
申请号：PCT/SG2022/050290
申请日：2022-05-10
申请人： GRABTAXI HOLDINGS PTE. LTD
发明人： KANDAL, Philipp Wolfgang Josef , LIANG, Chen , MARGIN, Adrian Ioan , KRUPPA, Hannes Martin
IPC分类号： G01C21/00 , G06V20/58 , G06N20/00 , G06V10/96
摘要： Aspects concern a method for gathering image training data for training a machine learning model to detect features for vehicle navigation or vehicle control, comprising mounting a camera onto a vehicle or the driver of a vehicle, determining a location of the vehicle, determining a relevancy of the determined location for map data generation or vehicle control and recording a video with the camera if the determined relevancy is above a predetermined threshold and recording single images if the determined relevancy is below the predetermined threshold.

8. 发明申请

WO2023009501A1 SYSTEM AND METHOD FOR AUTOMATIC DETECTION OF VISUAL EVENTS IN TRANSPORTATION ENVIRONMENTS 审中-公开
公开(公告)号：WO2023009501A1
公开(公告)日：2023-02-02
申请号：PCT/US2022/038315
申请日：2022-07-26
申请人： SHIPIN SYSTEMS INC.
发明人： NASLAVSKY, Ilan , GUPTE, Aditya , COHEN, Moran , MICHAEL, David, J.
IPC分类号： G06Q10/08 , G06V10/94 , G06V10/96 , G06V20/00 , G06V20/52
摘要： This invention provides a system and method that uses a hybrid model for transportation-based (e.g. maritime) visual event detection of events. In operation, video data is reduced by detecting change and exclusively transmitting images to the deep learning model when changes are detected, or alternatively, based upon a timer that samples at selected intervals. Relatively straightforward deep learning models are used, which operate on sparse individual frames, instead of employing complex deep learning models that operate on multiple frames/videos. This approach reduces the need for specialized models. Independent, rule-based classifiers are used, based on the output of the deep learning model into visual events that, in turn, allows highly specialized events to be constructed. For example, multiple detections can be combined into higher-level single events, and thus, the existence maintenance procedures, cargo activities, and/or inspection rounds can be derived from combining multiple events or multiple detections.

9. 发明申请

WO2023283367A1 DYNAMIC SYMBOL-BASED SYSTEM FOR OBJECTS-OF-INTEREST VIDEO ANALYTICS DETECTION 审中-公开
公开(公告)号：WO2023283367A1
公开(公告)日：2023-01-12
申请号：PCT/US2022/036400
申请日：2022-07-07
申请人： MUTUALINK, INC.
发明人： MAZZARELLA, Joseph R. , WENGROVITZ, Michael S.
IPC分类号： G06V20/40 , G06V10/96
摘要： Disclosed herein are system, method, and computer program product embodiments for a dynamic symbol-based system for objects-of-interest (OOI) video analytics detection. Some embodiments include instantiating one or more symbolic objects associated with one or more real world rules, defining an area of interest, associating one or more CV functions with the one or more symbolic objects, and identifying one or more video sources for which to apply the one or more CV functions. Some embodiments further include executing the one or more CV functions associated with the one or more symbolic objects to process the one or more video sources.

10. 发明申请

WO2023277829A1 POSITION AND TIME TRACKING SYSTEM BASED ON PHOTOGRAPHS 审中-公开
公开(公告)号：WO2023277829A1
公开(公告)日：2023-01-05
申请号：PCT/TH2022/000027
申请日：2022-07-01
申请人： CHINWATANAKIT, Worapot , KHAOLAORR, Suprasert
发明人： CHINWATANAKIT, Worapot , KHAOLAORR, Suprasert
IPC分类号： G08B13/196 , G06V20/52 , G06V10/96
摘要： The position and time tracking system based on photographs comprises a host and a client connected via network. The client's memory is saved in with an input unit, which controls at least two imaging devices together with a variable-checking device. At least the client's position and time tracking variables are compared with rules that are input from the host via a user interface unit in authorising the imaging devices to take image input, where acquired images are compressed with the checked variables, and a data storage unit checks network connection's stability and transmits data to the host once the connection is stable. Conversely, if the connection is unstable, images are saved into the client' s memory, and data are transmitted to the host when the connection has been stable.

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