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

WO2019224164A1 METHODS, SYSTEMS, ARTICLES OF MANUFACTURE AND APPARATUS TO RECONSTRUCT SCENES USING CONVOLUTIONAL NEURAL NETWORKS 审中-公开
公开(公告)号：WO2019224164A1
公开(公告)日：2019-11-28
申请号：PCT/EP2019/063006
申请日：2019-05-20
申请人： MOVIDIUS LTD.
发明人： PALLA, Alessandro , BYRNE, Jonathan , MOLONEY, David
IPC分类号： G06K9/62
摘要： Methods, apparatus, systems and articles of manufacture to reconstruct scenes using convolutional neural networks are disclosed. An example apparatus includes a sensor data acquirer to acquire ground truth data representing an environment, an environment detector to identify an environmental characteristic of the environment, a synthetic database builder to apply noise to the ground truth data to form a training set, a model builder to train a machine learning model using the training set and the ground truth data, and a model adjustor to modify the machine learning model to include residual OR-gate connections intermediate respective layers of the machine learning model. The synthetic database builder is further to store the machine learning model in association with the environmental characteristic of the environment.

2. 发明申请

WO2019185852A3 METHODS, SYSTEMS, ARTICLES OF MANUFACTURE AND APPARATUS TO GENERATE DIGITAL SCENES 审中-公开
公开(公告)号：WO2019185852A3
公开(公告)日：2019-10-03
申请号：PCT/EP2019/057961
申请日：2019-03-28
申请人： MOVIDIUS LTD.
发明人： LEE, Kevin , SHMATOV, Anton , BYRNE, Jonathan , MOLONEY, David
IPC分类号： G06K9/00 , G06K9/62
摘要： Methods, systems, articles of manufacture and apparatus to generate digital scenes are disclosed. An example apparatus to generate labelled models includes a map builder to generate a three-dimensional (3D) model of an input image, a grouping classifier to identify a first zone of the 3D model corresponding to a first type of grouping classification, a human model builder to generate a quantity of placeholder human models corresponding to the first zone, a coordinate engine to assign the quantity of placeholder human models to respective coordinate locations of the first zone, the respective coordinate locations assigned based on the first type of grouping classification, a model characteristics modifier to assign characteristics associated with an aspect type to respective ones of the quantity of placeholder human models, and an annotation manager to associate the assigned characteristics as label data for respective ones of the quantity of placeholder human models.

3. 发明申请

WO2018211129A1 METHODS, SYSTEMS AND APPARATUS TO IMPROVE CONVOLUTION EFFICIENCY 审中-公开
公开(公告)号：WO2018211129A1
公开(公告)日：2018-11-22
申请号：PCT/EP2018/063231
申请日：2018-05-18
申请人： MOVIDIUS LTD.
发明人： POWER, Sean , MOLONEY, David , BARRY, Brendan , CONNOR, Fergal
IPC分类号： G06N3/063 , G06N3/04 , G06K9/62 , G06K9/00
摘要： Methods, apparatus, systems, and articles of manufacture are disclosed to improve convolution efficiency of a convolution neural network (CNN) accelerator. An example apparatus includes a data processing element (DPE) inventory engine to identify DPEs included in a DPE array available to a platform, a mode selector to determine a convolution arrangement of identified ones of the DPEs, a DPE configuration optimizer to determine a DPE utilization based on the identified ones of the DPEs, and a convolution engine to facilitate a convolution operation using the identified ones of the DPEs when the DPE utilization satisfies a DPE utilization threshold.

4. 发明申请

WO2020064326A1 METHODS AND APPARATUS TO GENERATE MASKED IMAGES BASED ON SELECTIVE PRIVACY AND/OR LOCATION TRACKING 审中-公开
公开(公告)号：WO2020064326A1
公开(公告)日：2020-04-02
申请号：PCT/EP2019/074126
申请日：2019-09-10
申请人： MOVIDIUS LTD.
发明人： MOLONEY, David
IPC分类号： G06K9/00 , G06K9/46 , G06K9/62
摘要： Examples to selectively generate a masked image include: a convolutional neural network detector to detect a first feature and a second feature in an image captured by a camera; a feature recognizer to determine the first feature is a displayable feature and the second feature is a non-displayable feature by comparing the first and second features of the image to reference feature images stored in a memory; and a blur generator to generate the masked image to display the displayable feature and mask the non-displayable feature.

5. 发明申请

WO2019137967A1 METHODS AND APPARATUS TO OPERATE A MOBILE CAMERA FOR LOW-POWER USAGE 审中-公开
公开(公告)号：WO2019137967A1
公开(公告)日：2019-07-18
申请号：PCT/EP2019/050462
申请日：2019-01-09
申请人： MOVIDIUS LTD.
发明人： MOLONEY, David , DEHGHANI, Alireza
IPC分类号： H04N5/232 , H04N5/225 , G10L15/16 , G06K9/00 , G06K9/62
摘要： An example mobile camera includes a first convolutional neural network to recognize a first feature in first sensor data in response to the first feature being detected in the first sensor data; a state transitioner to transition the mobile camera from a first feature detection state to a second feature detection state in response to the first convolutional neural network recognizing the first feature, the mobile camera to operate using higher power consumption in the second feature detection state than in the first feature detection state; a second convolutional neural network to recognize a second feature in second sensor data in the second feature detection state; and a communications interface to send to an external device at least one of first metadata corresponding to the first feature or second metadata corresponding to the second feature.

6. 发明申请

WO2020008025A1 VIDEO SURVEILLANCE WITH NEURAL NETWORKS 审中-公开
公开(公告)号：WO2020008025A1
公开(公告)日：2020-01-09
申请号：PCT/EP2019/068085
申请日：2019-07-05
申请人： MOVIDIUS LTD.
发明人： MOLONEY, David
IPC分类号： G06K9/00 , G06K9/46
摘要： Example methods, apparatus, systems and articles of manufacture (e.g., physical storage media) to implement video surveillance with neural networks are disclosed. Example systems disclosed herein include a database to store records of operator-labeled video segments (e.g., as records of operator-labeled video segments). The operator-labeled video segments include reference video segments and corresponding reference event labels describing the video segments. Disclosed example systems also include a neural network including a first instance of an inference engine, and a training engine to train the first instance of the inference engine based on a training set of the operator-labeled video segments obtained from the database, the first instance of the inference engine to infer events from the operator-labeled video segments included in the training set. Disclosed example systems further include a second instance of the inference engine to infer events from monitored video feeds, the second instance of the inference engine being based on the first instance of the inference engine.

7. 发明申请

WO2019185852A2 METHODS, SYSTEMS, ARTICLES OF MANUFACTURE AND APPARATUS TO GENERATE DIGITAL SCENES 审中-公开
公开(公告)号：WO2019185852A2
公开(公告)日：2019-10-03
申请号：PCT/EP2019/057961
申请日：2019-03-28
申请人： MOVIDIUS LTD.
发明人： LEE, Kevin , SHMATOV, Anton , BYRNE, Jonathan , MOLONEY, David
IPC分类号： G06K9/00 , G06K9/62
摘要： Methods, systems, articles of manufacture and apparatus to generate digital scenes are disclosed. An example apparatus to generate labelled models includes a map builder to generate a three-dimensional (3D) model of an input image, a grouping classifier to identify a first zone of the 3D model corresponding to a first type of grouping classification, a human model builder to generate a quantity of placeholder human models corresponding to the first zone, a coordinate engine to assign the quantity of placeholder human models to respective coordinate locations of the first zone, the respective coordinate locations assigned based on the first type of grouping classification, a model characteristics modifier to assign characteristics associated with an aspect type to respective ones of the quantity of placeholder human models, and an annotation manager to associate the assigned characteristics as label data for respective ones of the quantity of placeholder human models.

8. 发明申请

WO2019170785A1 DETERMINING WEIGHTS OF CONVOLUTIONAL NEURAL NETWORKS 审中-公开
公开(公告)号：WO2019170785A1
公开(公告)日：2019-09-12
申请号：PCT/EP2019/055626
申请日：2019-03-06
申请人： MOVIDIUS LTD.
发明人： MOLONEY, David , DEHGHANI, Alireza , DUNNE, Aubrey, Keith
IPC分类号： G06K9/00 , G06K9/62 , G06K9/46 , G06N3/04
摘要： An example includes sending (502) first weight values to first client devices; accessing (504) sets of updated weight values provided by the first client devices, the updated weight values generated by the first client devices training respective first convolutional neural networks, CNNs, based on: the first weight values, and sensor data generated at the client devices; testing (506) performance in a second CNN of at least one of: the sets of the updated weight values, or a combination of ones of the updated weight values from the sets of the updated weight values; selecting (512) server-synchronized weight values from the at least one of: the sets of the updated weight values, or a combination of ones of the updated weight values from the sets of the updated weight values; and sending (518) the server- synchronized weight values to at least one of: at least some of the first client devices, or second client devices.

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