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

AU2017267983B2 Method and system for performing convolutional image transformation estimation 未知
公开(公告)号：AU2017267983B2
公开(公告)日：2022-03-31
申请号：AU2017267983
申请日：2017-05-19
申请人： MAGIC LEAP INC
发明人： DETONE DANIEL , MALISIEWICZ TOMASZ JAN , RABINOVICH ANDREW
IPC分类号： G06T3/20 , G06K7/01 , G06K9/62 , G06N3/02 , G06N3/06
摘要： A method for generating inputs for a neural network based on an image includes receiving the image, identifying a position within the image, and identifying a subset of the image at the position. The subset of the image is defined by a first set of corners. The method also includes perturbing at least one of the first set of corners to form a second set of corners. The second set of corners defines a modified subset of the image. The method further includes determining a homography based on a comparison between the subset of the image and the modified subset of the image, generating a transformed image by applying the homography to the image, and identifying a subset of the transformed image at the position.

2. 发明专利

AU2022201949A1 Augmented reality display device with deep learning sensors 未知
公开(公告)号：AU2022201949A1
公开(公告)日：2022-04-14
申请号：AU2022201949
申请日：2022-03-21
申请人： MAGIC LEAP INC
发明人： RABINOVICH ANDREW , MALISIEWICZ TOMASZ JAN , DETONE DANIEL
IPC分类号： G06F3/01 , G02B27/01 , G06N3/02 , G06N3/04 , G06T19/00
摘要： The present invention provides a system comprising non-transitory computer-readable memory storing executable instructions and one or more processors programmed by the executable instructions to at least train a neural network based on a training set comprising a plurality of sensor data as input data and a plurality of corresponding types of events as output data, wherein the neural network comprises an input layer for receiving input of the neural network, a plurality of intermediate layers including a first intermediate layer of the plurality of intermediate layers coupled to the input layer, and a plurality of head components including a head output node coupled to a last intermediate layer of the plurality of intermediate layers through a plurality of head component layers. Fig. 29 WO 2018/039269 PCT/US2017/048068 "Heads" (264) Face Visual Gesture I.D. Semantic Object Lighting SLAM Relocalization Depth Recognition Search Segmentation Detection Estimation Middle Layers (266) Lower Layers (268) Ou tw ard -f ac ing IMU ("world") Depth Sensor Sound, Voice cameras Inputs (270) Hydra Architecture (272) FIG 29

3. 发明专利

NZ743271A Relocalization systems and methods 未知
公开(公告)号：NZ743271A
公开(公告)日：2021-06-25
申请号：NZ74327116
申请日：2016-12-05
申请人： MAGIC LEAP INC
发明人： SCHROEDER BRIGIT , MALISIEWICZ TOMASZ , RABINOVICH ANDREW
IPC分类号： G06T7/80 , G06F3/03 , G06K9/20 , G06K9/52 , G06K9/60 , G06K9/70
摘要： The present disclosure relates to the localisation of pose-sensitive systems. One disclosed embodiment relates to a method of determining a pose of an image capture device. The method includes capturing an image using an image capture device. The method also includes generating a data structure corresponding to the captured image. The method further includes comparing the data structure with a plurality of known data structures to identify a most similar known data structure. The method further includes reading metadata corresponding to the most similar known data structure to determine a pose of the image capture device. The method further includes training a neural network by mapping a plurality of known images to the plurality of known data structures. The data structure is an N dimensional vector. The step of generating the data structure corresponding to the captured image comprises using a neural network to map the captured image to the N dimensional vector. Each known image of the plurality has respective metadata including pose data. The step of training the neural network comprises accessing a database of the known images annotated with the respective metadata, decreasing a first Euclidean distance between first and second known N dimensional vectors respectively corresponding to matching first and second known images in an N dimensional space, and increasing a second Euclidean distance between first and third known N dimensional vectors respectively corresponding to non-matching first and third known images in the N dimensional space.

4. 发明专利

AU2018292610A1 Method and system for performing simultaneous localization and mapping using convolutional image transformation 未知
公开(公告)号：AU2018292610A1
公开(公告)日：2019-12-19
申请号：AU2018292610
申请日：2018-06-27
申请人： MAGIC LEAP INC
发明人： DETONE DANIEL L , MALISIEWICZ TOMASZ JAN , RABINOVICH ANDREW
IPC分类号： G06K9/46 , G06K9/62
摘要： Augmented reality devices and methods for computing a homography based on two images. One method may include receiving a first image based on a first camera pose and a second image based on a second camera pose, generating a first point cloud based on the first image and a second point cloud based on the second image, providing the first point cloud and the second point cloud to a neural network, and generating, by the neural network, the homography based on the first point cloud and the second point cloud. The neural network may be trained by generating a plurality of points, determining a 3D trajectory, sampling the 3D trajectory to obtain camera poses viewing the points, projecting the points onto 2D planes, comparing a generated homography using the projected points to the ground-truth homography and modifying the neural network based on the comparison.

5. 发明专利

AU2018236433A1 Room layout estimation methods and techniques 未知
公开(公告)号：AU2018236433A1
公开(公告)日：2019-09-12
申请号：AU2018236433
申请日：2018-03-16
申请人： MAGIC LEAP INC
发明人： LEE CHEN-YU , BADRINARAYANAN VIJAY , MALISIEWICZ TOMASZ , RABINOVICH ANDREW
IPC分类号： G06N3/02
摘要： Systems and methods for estimating a layout of a room are disclosed. The room layout can comprise the location of a floor, one or more walls, and a ceiling, in one aspect, a neural network can analyze an image of a portion of a room to determine the room layout. The neural network can comprise a convolutional neural network having an encoder sub-network, a decoder sub-network, and a side sub-network. The neural network can determine a three-dimensional room layout using two-dimensional ordered keypoints associated with a room type. The room layout can be used in applications such as augmented or mixed reality, robotics, autonomous indoor navigation, etc.

6. 发明专利

AU2017361061A1 Deep learning system for cuboid detection 未知
公开(公告)号：AU2017361061A1
公开(公告)日：2019-05-23
申请号：AU2017361061
申请日：2017-11-14
申请人： MAGIC LEAP INC
发明人： MALISIEWICZ TOMASZ , RABINOVICH ANDREW , BADRINARAYANAN VIJAY , DWIBEDI DEBIDATTA
IPC分类号： G06F3/01 , G06F3/0346 , G06K9/66 , G06N3/04 , G06T7/215
摘要： Systems and methods for cuboid detection and keypoint localization in images are disclosed. In one aspect, a deep cuboid detector can be used for simultaneous cuboid detection and keypoint localization in monocular images. The deep cuboid detector can include a plurality of convolutional layers and non-convolutional layers of a trained convolution neural network for determining a convolutional feature map from an input image. A region proposal network of the deep cuboid detector can determine a bounding box surrounding a cuboid in the image using the convolutional feature map. The pooling layer and regressor layers of the deep cuboid detector can implement iterative feature pooling for determining a refined bounding box and a parameterized representation of the cuboid.

7. 发明专利

AU2017317599A1 Augmented reality display device with deep learning sensors 未知
公开(公告)号：AU2017317599A1
公开(公告)日：2019-03-21
申请号：AU2017317599
申请日：2017-08-22
申请人： MAGIC LEAP INC
发明人： RABINOVICH ANDREW , MALISIEWICZ TOMASZ JAN , DETONE DANIEL
IPC分类号： G06F3/01 , G02B27/01 , G06N3/02 , G06N3/04 , G06T19/00
摘要： A head-mounted augmented reality (AR) device can include a hardware processor programmed to receive different types of sensor data from a plurality of sensors (e.g., an inertial measurement unit, an outward-facing camera, a depth sensing camera, an eye imaging camera, or a microphone); and determining an event of a plurality of events using the different types of sensor data and a hydra neural network (e.g., face recognition, visual search, gesture identification, semantic segmentation, object detection, lighting detection, simultaneous localization and mapping, relocalization).

8. 发明专利

CA3021085A1 METHOD AND SYSTEM FOR PERFORMING CONVOLUTIONAL IMAGE TRANSFORMATION ESTIMATION 未知
公开(公告)号：CA3021085A1
公开(公告)日：2017-11-23
申请号：CA3021085
申请日：2017-05-19
申请人： MAGIC LEAP INC
发明人： DETONE DANIEL , MALISIEWICZ TOMASZ JAN , RABINOVICH ANDREW
IPC分类号： G06K7/01 , G06K9/40 , G06K9/62 , G06N3/02 , G06N3/06 , G06T3/20
摘要： A method for generating inputs for a neural network based on an image includes receiving the image, identifying a position within the image, and identifying a subset of the image at the position. The subset of the image is defined by a first set of corners. The method also includes perturbing at least one of the first set of corners to form a second set of corners. The second set of corners defines a modified subset of the image. The method further includes determining a homography based on a comparison between the subset of the image and the modified subset of the image, generating a transformed image by applying the homography to the image, and identifying a subset of the transformed image at the position.

9. 发明专利

CA3015658A1 STRUCTURE LEARNING IN CONVOLUTIONAL NEURAL NETWORKS 未知
公开(公告)号：CA3015658A1
公开(公告)日：2017-09-14
申请号：CA3015658
申请日：2017-03-13
申请人： MAGIC LEAP INC
发明人： RABINOVICH ANDREW , BADRINARAYANAN VIJAY , DETONE DANIEL , RAJENDRAN SRIVIGNESH , LEE DOUGLAS BERTRAM , MALISIEWICZ TOMASZ J
IPC分类号： G06N3/02
摘要： The present disclosure provides an improved approach to implement structure learning of neural networks by exploiting correlations in the data/problem the networks aim to solve. A greedy approach is described that finds bottlenecks of information gain from the bottom convolutional layers all the way to the fully connected layers. Rather than simply making the architecture deeper, additional computation and capacitance is only added where it is required.

10. 发明专利

CA3007367A1 RELOCALIZATION SYSTEMS AND METHODS 未知
公开(公告)号：CA3007367A1
公开(公告)日：2017-06-08
申请号：CA3007367
申请日：2016-12-05
申请人： MAGIC LEAP INC
发明人： SCHROEDER BRIGIT , MALISIEWICZ TOMASZ J , RABINOVICH ANDREW
IPC分类号： G06T7/80 , G06F3/03 , G06F15/18 , G06F17/30 , G06K9/20 , G06K9/52 , G06K9/60 , G06K9/70
摘要： A method of determining a pose of an image capture device includes capturing an image using an image capture device. The method also includes generating a data structure corresponding to the captured image. The method further includes comparing the data structure with a plurality of known data structures to identify a most similar known data structure. Moreover, the method includes reading metadata corresponding to the most similar known data structure to determine a pose of the image capture device.

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