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. 发明授权

US11482007B2 Event-based vehicle pose estimation using monochromatic imaging 有权
公开(公告)号：US11482007B2
公开(公告)日：2022-10-25
申请号：US17172631
申请日：2021-02-10
申请人： Ford Global Technologies, LLC
发明人： Shubham Shrivastava
IPC分类号： G06V20/54 , G06T7/207 , G06T7/70 , G06T7/62 , G06V10/56 , G06V10/75
摘要： A computer-implemented method for estimating a vehicle pose for a moving vehicle is described includes obtaining, via a processor disposed in communication with a monochromatic camera, a monochromatic image of an operating environment, and detecting in the monochromatic image an event patch showing a plurality of pixels associated with the moving vehicle. The method further includes generating an optical flow map using an unsupervised optical flow prediction network to predict an optical flow for each pixel in the monochromatic image. The optical flow map includes a Red-Green-Blue (RGB) patch having color information associated with a velocity for the moving vehicle. The system generates a pixel-level event mask that includes the RGB patch, and estimates the vehicle pose for the moving vehicle.

2. 发明申请

US20220301185A1 INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND STORAGE MEDIUM FOR ESTIMATING MOVEMENT AMOUNT OF MOVING OBJECT 有权
公开(公告)号：US20220301185A1
公开(公告)日：2022-09-22
申请号：US17689066
申请日：2022-03-08
申请人： HONDA MOTOR CO., LTD.
发明人： Yuji Yasui
IPC分类号： G06T7/207 , B60W40/105 , G06T3/40 , G06V10/25 , G06V20/58 , B60W50/14
摘要： An information processing apparatus, for estimating a movement amount of a moving object to which the information processing apparatus is attached, captures an image taken of an exterior view seen from the moving object. The apparatus estimates the movement amount of the moving object based on a first taken image taken at a first time and a second taken image taken at a second time earlier than the first time. The apparatus estimates the movement amount of the moving object based on a difference between image information on a predetermined region of each manipulated image obtained by manipulating the second taken image based on mutually different predicted movement amounts and image information on a predetermined region cut out from the first taken image.

3. 发明申请

US20220253634A1 EVENT-BASED VEHICLE POSE ESTIMATION USING MONOCHROMATIC IMAGING 有权
公开(公告)号：US20220253634A1
公开(公告)日：2022-08-11
申请号：US17172631
申请日：2021-02-10
申请人： Ford Global Technologies, LLC
发明人： Shubham Shrivastava
IPC分类号： G06K9/00 , G06K9/46 , G06K9/62 , G06T7/207 , G06T7/62 , G06T7/70
摘要： A computer-implemented method for estimating a vehicle pose for a moving vehicle is described includes obtaining, via a processor disposed in communication with a monochromatic camera, a monochromatic image of an operating environment, and detecting in the monochromatic image an event patch showing a plurality of pixels associated with the moving vehicle. The method further includes generating an optical flow map using an unsupervised optical flow prediction network to predict an optical flow for each pixel in the monochromatic image. The optical flow map includes a Red-Green-Blue (RGB) patch having color information associated with a velocity for the moving vehicle. The system generates a pixel-level event mask that includes the RGB patch, and estimates the vehicle pose for the moving vehicle.

4. 发明申请

US20220189154A1 CONNECTION WEIGHT LEARNING FOR GUIDED ARCHITECTURE EVOLUTION 有权
公开(公告)号：US20220189154A1
公开(公告)日：2022-06-16
申请号：US17605783
申请日：2020-05-22
申请人： Google LLC
发明人： Michael Sahngwon Ryoo , Anthony Jacob Piergiovanni , Mingxing Tan , Anelia Angelova
IPC分类号： G06V10/82 , G06N3/04 , G06T7/207 , G06T1/20 , G06T3/40 , G06V10/776
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining one or more neural network architectures of a neural network for performing a video processing neural network task. In one aspect, a method comprises: at each of a plurality of iterations: selecting a parent neural network architecture from a set of neural network architectures; training a neural network having the parent neural network architecture to perform the video processing neural network task, comprising determining trained values of connection weight parameters of the parent neural network architecture; generating a new neural network architecture based at least in part on the trained values of the connection weight parameters of the parent neural network architecture; and adding the new neural network architecture to the set of neural network architectures.

5. 发明申请

US20220084236A1 DETECTOR FOR DETERMINING A POSITION OF AT LEAST ONE OBJECT 有权
公开(公告)号：US20220084236A1
公开(公告)日：2022-03-17
申请号：US17421583
申请日：2020-01-08
申请人： trinamiX GmbH
发明人： Robert Send , Patrick Schindler , Celal Mohan Oeguen , Peter Schillen , Christian Lennartz
IPC分类号： G06T7/70 , G06T7/521 , G06T7/571 , G06T7/207 , G06T5/00 , G06V10/141 , G06V10/25
摘要： Described herein is a detector for determining a position of an object. The detector includes a sensor element having a matrix of optical sensors, each designed to generate a sensor signal in response to an illumination of its light-sensitive area by a light beam propagating from the object to the detector. The detector also includes an evaluation device configured to select a region of interest of the matrix, respectively determine a sensor signal of at least two optical sensors of the region of interest, and determine a longitudinal coordinate zDPR of the object by evaluating a combined sensor signal Q. The evaluation device is also configured to determine an image of the region of interest from the sensor signals, determine a longitudinal coordinate zDFD of the object by optimizing at least one blurring function fa, and determine combined distance information z considering the longitudinal coordinates zDPR and zDFD.

6. 发明授权

US11195285B2 Moving object detection using a digital read-out integrated circuit and degree of polarization and angle of polarization at the pixel level 有权
公开(公告)号：US11195285B2
公开(公告)日：2021-12-07
申请号：US16837390
申请日：2020-04-01
申请人： BAE SYSTEMS Information and Electronic Systems Integration Inc.
发明人： Michael J. Choiniere
IPC分类号： G06T7/254 , G06T7/207 , G06T7/285
摘要： An object detection system comprises a polarizer configured to polarize an incoming image scene, a motor controller configured to control a spin rate of the polarizer, a lens configured to collect scene data from the polarized image scene, a first integrated circuit configured to measure the collected scene data at two different and orthogonal polarizations, a second integrated circuit configured to determine a degree of polarization (DoP) and an angle of polarization (AoP) for each image frame pair and to generate pre-processed data, and a processor configured to match the pre-processed data to target criteria. The first integrated circuit can be a DROIC imager and the second integrated circuit can be a FPGA. The AoP and DoP can be determined at a pixel level. The second integrated circuit is configured to apply spatial filtering having a DoP greater than 70% or where AoP is unique to immediate surroundings of AoP.

7. 发明申请

US20210348920A1 Object Position Estimation Device and Method Therefor 有权
公开(公告)号：US20210348920A1
公开(公告)日：2021-11-11
申请号：US17278090
申请日：2019-09-10
申请人： Hitachi, Ltd.
发明人： Takumi NITO , Qingzhu DUAN
IPC分类号： G01C5/00 , G06T7/73 , G06T7/207 , G06T7/292 , G06T7/62 , G06K9/00
摘要： The purpose of this invention is to reduce the ambiguity in position caused by height differences in an object, and to estimate the position of an object with a high degree of accuracy. This object position estimation device comprises: a first processing unit which detects the position of a position reference point on a moving object from an image of the moving object obtained by a camera; a second processing unit for estimating the height of the moving object detected; a third processing unit for estimating the height of the position reference point on the basis of the estimated height estimated by the second processing unit and the image of the moving object; a fourth processing unit which calculates an estimated position candidate for the moving object on the basis of the height of the position reference point estimated by the third processing unit, the position of the position reference point, and the height of the point in the area; a fifth processing unit which calculates the likelihood of the estimated position candidate on the basis of the estimated position candidate calculated by the fourth processing unit, the height of the position reference point estimated by the third processing unit, and the height in the area; and a sixth processing unit which determines the estimated position of the moving object on the basis of the likelihood of the estimated position candidate calculated by the fifth processing unit.

8. 发明申请

US20210312639A1 MOVING OBJECT DETECTION USING A DIGITAL READ-OUT INTEGRATED CIRCUIT AND DEGREE OF POLARIZATION AND ANGLE OF POLARIZATION AT THE PIXEL LEVEL 有权
公开(公告)号：US20210312639A1
公开(公告)日：2021-10-07
申请号：US16837390
申请日：2020-04-01
申请人： BAE SYSTEMS Information and Electronic Systems Integration Inc.
发明人： Michael J. CHOINIERE
IPC分类号： G06T7/207 , G06T7/285 , G06T7/254
摘要： An object detection system comprises a polarizer configured to polarize an incoming image scene, a motor controller configured to control a spin rate of the polarizer, a lens configured to collect scene data from the polarized image scene, a first integrated circuit configured to measure the collected scene data at two different and orthogonal polarizations, a second integrated circuit configured to determine a degree of polarization (DoP) and an angle of polarization (AoP) for each image frame pair and to generate pre-processed data, and a processor configured to match the pre-processed data to target criteria. The first integrated circuit can be a DROIC imager and the second integrated circuit can be a FPGA. The AoP and DoP can be determined at a pixel level. The second integrated circuit is configured to apply spatial filtering having a DoP greater than 70% or where AoP is unique to immediate surroundings of AoP.

9. 发明申请

US20210266478A1 IMAGE PROCESSING APPARATUS AND METHOD 有权
公开(公告)号：US20210266478A1
公开(公告)日：2021-08-26
申请号：US17058084
申请日：2019-05-17
申请人： SONY CORPORATION
发明人： TAKEFUMI NAGUMO , TOSHINORI IHARA , TAKUYA KITAMURA
IPC分类号： H04N5/357 , G06T7/207
摘要： The present disclosure relates to image processing apparatus and method that can suppress the increase in the load of processing multi-wavelength data. A subject is imaged to generate multi-wavelength data that is image data including four or more wavelength components, the generated multi-wavelength data is encoded to generate encoded data of the multi-wavelength data, and the generated encoded data is transmitted. The present disclosure can be applied to, for example, an image processing apparatus, an image encoding apparatus, an image decoding apparatus, an imaging element, an imaging apparatus, or the like.

10. 发明申请

US20210248378A1 SPATIOTEMPORAL ACTION DETECTION METHOD 有权
公开(公告)号：US20210248378A1
公开(公告)日：2021-08-12
申请号：US16965015
申请日：2020-01-07
申请人： HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY
发明人： Nong SANG , Shiwei ZHANG , Zhiyuan LI , Changxin GAO , Yuanjie SHAO
IPC分类号： G06K9/00 , G06T3/00 , G06T7/207 , G06T7/215 , G06T3/40
摘要： A spatiotemporal action detection method includes performing object detection on all frames of a sample video to obtain a candidate object set; calculating all interframe optical flow information on the sample video to obtain a motion set; constructing a spatiotemporal convolution-deconvolution network of an attention mechanism and a motion attention mechanism of an additional object; adding both a corresponding sparse variable and a sparse constraint to obtain a network structure S after performing spatiotemporal convolution processing on each time segment of the sample video; training the network structure S with an objective function based on classification loss and loss of the sparse constraint of cross entropy; and calculating an action category and a sparse coefficient corresponding to each time segment of a test sampled video to obtain an object action spatiotemporal location.

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