-
公开(公告)号:US20170329335A1
公开(公告)日:2017-11-16
申请号:US15365210
申请日:2016-11-30
Inventor: Stephen P. DelMarco , Victor T. Tom
CPC classification number: G05D1/02 , B64C39/024 , G01C21/005 , G05D1/10 , G06F17/30256 , G06F17/3028 , G06K9/52 , G06T7/30 , G06T7/32 , G06T7/70 , G06T2200/28
Abstract: A method for vision-aided navigation which utilizes an image registration system to update a navigation control system. One exemplary feature of the method includes the use of Enhanced Phase Correlation techniques to create a reference imagery database and register images against the created database. The method may be operated on a non-transitory computer-readable medium storing a plurality of instructions which when executed by one or more processors causes the one or more processors to perform the method for vision-aided navigation which utilizes an image registration system to update a navigation control system.
-
公开(公告)号:US20220198692A1
公开(公告)日:2022-06-23
申请号:US17131219
申请日:2020-12-22
Inventor: Stephen P. DelMarco , Victor T. Tom
Abstract: Techniques are provided for vision-based altitude estimation using one or more platform mounted cameras. An embodiment includes generating projected ground imagery of imagery provided by cameras of the platform, the projection based on a hypothesized altitude. The method also includes obtaining reference ground imagery based on the location of the platform, the location based on platform navigation data. The method further includes registering the projected ground imagery to the reference ground imagery and generating a match score associated with the registration. The method further includes selecting the hypothesized altitude as the estimated altitude based on the match score (e.g., if the match score exceeds a threshold value or is maximized over a set of hypothesized altitudes. The method may further include otherwise adjusting the hypothesized altitude and repeating the altitude estimation process based on the adjusted hypothesized altitude to search for an improved estimated altitude based on the match score.
-
公开(公告)号:US10274958B2
公开(公告)日:2019-04-30
申请号:US15365210
申请日:2016-11-30
Inventor: Stephen P. DelMarco , Victor T. Tom
IPC: G05D1/02 , G06T7/30 , G06T7/70 , G01C21/00 , G05D1/10 , G06F16/51 , G06T7/32 , B64C39/02 , G06K9/52 , G06F16/583
Abstract: A method for vision-aided navigation which utilizes an image registration system to update a navigation control system. One exemplary feature of the method includes the use of Enhanced Phase Correlation techniques to create a reference imagery database and register images against the created database. The method may be operated on a non-transitory computer-readable medium storing a plurality of instructions which when executed by one or more processors causes the one or more processors to perform the method for vision-aided navigation which utilizes an image registration system to update a navigation control system.
-
公开(公告)号:US20240428399A1
公开(公告)日:2024-12-26
申请号:US18337827
申请日:2023-06-20
Inventor: Tao Wang , Helen Vo , Helen F. Webb , Victor T. Tom
IPC: G06T7/00 , G06V10/44 , G06V10/774 , G06V10/82
Abstract: Hybrid MB/ML techniques for automated printed circuit board (PCB) defect detection. In one example, a PCB inspection system implements a hybrid solution using model based (MB) and machine learning (ML) technologies to detect possible defects in a PCB via an automated image capture device and processing methodology. The processing methodology fuses features from MB and ML at the latent representation. An autoencoder can be used to learn the fused data by training a neural network to produce a reconstructed image that can be compared to an original image to generate a reconstruction error value. The system produces an output indicating detection of a defect in one or more features of interest based on the reconstruction error value transgressing a threshold value.
-
公开(公告)号:US10445616B2
公开(公告)日:2019-10-15
申请号:US15004029
申请日:2016-01-22
Inventor: Victor T. Tom , Stephen P. Delmarco , Helen F. Webb
Abstract: An image registration system and method for matching images having fundamentally different characteristics. One exemplary feature of the system and method includes the use of an enhanced phase correlation method combined with a coarse sensor model to hypothesize and match a custom match metric to determine a best solution. The system and method may be operated on a non-transitory computer-readable medium storing a plurality of instructions which when executed by one or more processors causes the one or more processors to perform the image registration method utilizing the enhanced phase correlation.
-
公开(公告)号:US11810309B2
公开(公告)日:2023-11-07
申请号:US17131219
申请日:2020-12-22
Inventor: Stephen P. DelMarco , Victor T. Tom
CPC classification number: G06T7/55 , G01C5/005 , G01C21/04 , G06T7/30 , G06T7/70 , H04N23/90 , G06T2207/10032 , G06T2207/30244
Abstract: Techniques are provided for vision-based altitude estimation using one or more platform mounted cameras. An embodiment includes generating projected ground imagery of imagery provided by cameras of the platform, the projection based on a hypothesized altitude. The method also includes obtaining reference ground imagery based on the location of the platform, the location based on platform navigation data. The method further includes registering the projected ground imagery to the reference ground imagery and generating a match score associated with the registration. The method further includes selecting the hypothesized altitude as the estimated altitude based on the match score (e.g., if the match score exceeds a threshold value or is maximized over a set of hypothesized altitudes. The method may further include otherwise adjusting the hypothesized altitude and repeating the altitude estimation process based on the adjusted hypothesized altitude to search for an improved estimated altitude based on the match score.
-
公开(公告)号:US20160217577A1
公开(公告)日:2016-07-28
申请号:US15004029
申请日:2016-01-22
Inventor: Victor T. Tom , Stephen P. Delmarco , Helen F. Webb
CPC classification number: G06K9/52 , G06T7/32 , G06T2200/28
Abstract: An image registration system and method for matching images having fundamentally different characteristics. One exemplary feature of the system and method includes the use of an enhanced phase correlation method combined with a coarse sensor model to hypothesize and match a custom match metric to determine a best solution. The system and method may be operated on a non-transitory computer-readable medium storing a plurality of instructions which when executed by one or more processors causes the one or more processors to perform the image registration method utilizing the enhanced phase correlation.
Abstract translation: 一种用于匹配具有根本不同特征的图像的图像配准系统和方法。 该系统和方法的一个示例性特征包括使用与粗糙传感器模型结合的增强相位相关方法来假设和匹配自定义匹配度量以确定最佳解决方案。 系统和方法可以在存储多个指令的非暂时计算机可读介质上操作,当多个指令执行时,一个或多个处理器使一个或多个处理器利用增强的相位相关来执行图像配准方法。
-
-
-
-
-
-