专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明授权

US07646887B2 Optical flow for object recognition 有权
标题翻译：用于对象识别的光流
公开(公告)号：US07646887B2
公开(公告)日：2010-01-12
申请号：US11324957
申请日：2006-01-03
申请人： Luis Goncalves , Isaac Gremmer
发明人： Luis Goncalves , Isaac Gremmer
IPC分类号： G06K9/00 , G06K15/00
CPC分类号： G06K9/3233 , G06K2209/17
摘要： Disclosed is a system and method for using optical flow to detect objects moving past a camera and to select images of the moving objects. A shopping cart, for example, may be detected by subdividing an image into a plurality of image blocks; comparing the blocks to a preceding image to determine the motion of the portion of the object pictured; associating the most common motion with the shopping cart. The motion of the cart may also be integrated over time for purposes of tracking cart motion and selecting a subset of the captured images for object recognition processing. Detection of the cart and image selection improves computational efficiency an increase merchandise throughput.
摘要翻译：公开了一种使用光流来检测通过相机移动的物体并选择移动物体的图像的系统和方法。例如，可以通过将图像细分为多个图像块来检测购物车; 将块与先前图像进行比较以确定所描绘的对象的部分的运动; 将最常见的动作与购物车关联起来。为了跟踪车厢运动和选择用于对象识别处理的所捕获的图像的子集，推车的运动也可随时间而被集成。购物车和图像选择的检测提高了计算效率，从而提高了商品吞吐量。

12. 发明申请

US20130018741A1 SYSTEMS AND METHODS FOR MERCHANDISE CHECKOUT 审中-公开
标题翻译：用于商品检验的系统和方法
公开(公告)号：US20130018741A1
公开(公告)日：2013-01-17
申请号：US13610783
申请日：2012-09-11
申请人： Jim Ostrowski , Luis Goncalves , Michael Cremean , Alex Simonini , Alec Hudnut
发明人： Jim Ostrowski , Luis Goncalves , Michael Cremean , Alex Simonini , Alec Hudnut
IPC分类号： G06Q20/20
CPC分类号： G07F7/02 , A47F9/045 , G06Q20/343 , G07G1/0036 , G07G1/0063 , G07G3/00 , G07G3/003 , G08B13/1961 , G08B13/19671
摘要： Systems and methods for recognizing and identifying items located on the lower shelf of a shopping cart in a checkout lane of a retail store environment for reducing or preventing loss or fraud and increasing the efficiency of a checkout process efficiency. The system includes one or more visual sensors that can take images of items and a computer system that receives the images and automatically identifies the items. The system can be trained to recognize the items using images taken of the items. The system relies on matching visual features from training images to match against features extracted from images taken at the checkout lane. Using the scale-invariant feature transformation (SIFT) method, for example, the system can compare extracted visual features of the images to the features stored in a database to find one or more matches, where the found one or more matches are used to identify the items.
摘要翻译：用于识别和识别位于零售商店环境的结帐通道中的购物车的下架上的物品的系统和方法，用于减少或防止损失或欺诈，并提高结算过程效率的效率。该系统包括可以拍摄物品图像的一个或多个视觉传感器和接收图像并自动识别物品的计算机系统。可以使用拍摄的项目的图像来训练系统来识别物品。系统依赖于训练图像的匹配视觉特征，以匹配从结帐通道上拍摄的图像提取的特征。使用比例不变特征变换（SIFT）方法，例如，系统可以将图像的提取的视觉特征与存储在数据库中的特征进行比较，以找到一个或多个匹配，其中发现的一个或多个匹配用于识别的项目。

13. 发明授权

US08267316B2 Systems and methods for merchandise checkout 有权
标题翻译：商品结帐的系统和方法
公开(公告)号：US08267316B2
公开(公告)日：2012-09-18
申请号：US11466371
申请日：2006-08-22
申请人： Jim Ostrowski , Luis Goncalves , Michael Cremean , Alex Simonini , Alec Hudnut
发明人： Jim Ostrowski , Luis Goncalves , Michael Cremean , Alex Simonini , Alec Hudnut
IPC分类号： G06K15/00
CPC分类号： G07F7/02 , A47F9/045 , G06Q20/343 , G07G1/0036 , G07G1/0063 , G07G3/00 , G07G3/003 , G08B13/1961 , G08B13/19671
摘要： Systems and methods for recognizing and identifying items located on the lower shelf of a shopping cart in a checkout lane of a retail store environment for the purpose of reducing or preventing loss or fraud and increasing the efficiency of a checkout process. The system includes one or more visual sensors that can take images of items and a computer system that receives the images from the one or more visual sensors and automatically identifies the items. The system can be trained to recognize the items using images taken of the items. The system relies on matching visual features from training images to match against features extracted from images taken at the checkout lane. Using the scale-invariant feature transformation (SIFT) method, for example, the system can compare the visual features of the images to the features stored in a database to find one or more matches, where the found one or more matches are used to identify the items.
摘要翻译：为了减少或防止丢失或欺诈以及增加结帐过程的效率，识别和识别位于零售商店环境的结帐通道中的购物车的下架上的物品的系统和方法。该系统包括可以拍摄物品图像的一个或多个视觉传感器和从一个或多个视觉传感器接收图像并自动识别物品的计算机系统。可以使用拍摄的项目的图像来训练系统来识别物品。系统依赖于训练图像的匹配视觉特征，以匹配从结帐通道上拍摄的图像提取的特征。使用比例不变特征变换（SIFT）方法，例如，系统可以将图像的视觉特征与存储在数据库中的特征进行比较，以找到一个或多个匹配，其中发现的一个或多个匹配用于识别的项目。

14. 发明授权

US07228123B2 Method and system for automatically determining lines of sight between nodes 失效
标题翻译：自动确定节点之间视线的方法和系统
公开(公告)号：US07228123B2
公开(公告)日：2007-06-05
申请号：US10802405
申请日：2004-03-17
申请人： Carter Moursund , Lorenzo Caminiti , Enrico Di Bernardo , Luis Goncalves
发明人： Carter Moursund , Lorenzo Caminiti , Enrico Di Bernardo , Luis Goncalves
IPC分类号： H04B5/00
CPC分类号： H04W16/18
摘要： The present invention uses data from several sources to determine lines-of-sight between nodes in a FSO network. The present invention provides a three-dimensional neighborhood modeling system that uses aerial image data, Digital Elevation Models, U.S. street map data and address data to automatically map the placement of nodes within a neighborhood or other geographical area.Method for creating the 3-Dimensional, House and Tree Maps used in the line-of-sight processing are also disclosed. A House Map in the present invention identifies houses in an area of consideration, and a Tree Map in the present invention identifies trees in an area of consideration. A 3-Dimensional Map in the present invention provides an elevation for every pixel for the area under consideration, whereby the elevation is adjusted for the height of trees, houses and other objects.
摘要翻译：本发明使用来自多个源的数据来确定FSO网络中的节点之间的视距。本发明提供一种使用空中图像数据，数字高程模型，美国街道地图数据和地址数据的三维邻域建模系统，以自动映射邻域或其他地理区域内的节点的位置。还公开了在视距处理中使用的用于创建三维，房屋和树图的方法。本发明中的房屋地图识别考虑区域中的房屋，并且本发明中的树形图识别考虑区域中的树木。本发明的三维图提供了所考虑的区域的每个像素的高度，由此根据树木，房屋和其他物体的高度来调节高度。

15. 发明申请

US20060012493A1 SYSTEMS AND METHODS FOR INCREMENTALLY UPDATING A POSE OF A MOBILE DEVICE CALCULATED BY VISUAL SIMULTANEOUS LOCALIZATION AND MAPPING TECHNIQUES 有权
标题翻译：通过视觉同步本地化和映射技术计算的移动设备的位置更新的系统和方法
公开(公告)号：US20060012493A1
公开(公告)日：2006-01-19
申请号：US10739937
申请日：2003-12-17
申请人： L. Karlsson , Paolo Pirjanian , Luis Goncalves , Enrico Bernardo
发明人： L. Karlsson , Paolo Pirjanian , Luis Goncalves , Enrico Bernardo
IPC分类号： G08G1/123 , G01C21/26
CPC分类号： G05D1/0246 , G01C21/12 , G05D1/0231 , G05D1/0234 , G05D1/024 , G05D1/0242 , G05D1/0248 , G05D1/0272 , G05D1/0274 , G05D1/0278 , G05D2201/0207 , G05D2201/0215 , G06T7/55 , G06T7/70 , G06T7/74 , G06T2207/30204 , Y10S901/01 , Y10S901/46 , Y10S901/47 , Y10S901/50
摘要： The invention is related to methods and apparatus that use a visual sensor and dead reckoning sensors to process Simultaneous Localization and Mapping (SLAM). These techniques can be used in robot navigation. Advantageously, such visual techniques can be used to autonomously generate and update a map. Unlike with laser rangefinders, the visual techniques are economically practical in a wide range of applications and can be used in relatively dynamic environments such as environments in which people move. One embodiment further advantageously uses multiple particles to maintain multiple hypotheses with respect to localization and mapping. Further advantageously, one embodiment maintains the particles in a relatively computationally-efficient manner, thereby permitting the SLAM processes to be performed in software using relatively inexpensive microprocessor-based computer systems.
摘要翻译：本发明涉及使用视觉传感器和航位推算传感器来处理同时定位和映射（SLAM）的方法和装置。这些技术可用于机器人导航。有利地，可以使用这种可视化技术来自主地生成和更新地图。与激光测距仪不同，视觉技术在广泛的应用中在经济上是实用的，并且可以在诸如人们移动的环境的相对动态的环境中使用。一个实施例进一步有利地使用多个粒子来维持关于定位和映射的多个假设。进一步有利的是，一个实施例以相对计算效率的方式维护颗粒，从而允许使用相对便宜的基于微处理器的计算机系统在软件中执行SLAM处理。

16. 发明申请

US20050189411A1 Systems and methods for merchandise checkout 有权
标题翻译：商品结帐的系统和方法
公开(公告)号：US20050189411A1
公开(公告)日：2005-09-01
申请号：US11023004
申请日：2004-12-27
申请人： Jim Ostrowski , Luis Goncalves , Michael Cremean , Alex Simonini , Alec Hudnut
发明人： Jim Ostrowski , Luis Goncalves , Michael Cremean , Alex Simonini , Alec Hudnut
IPC分类号： A47F9/04 , G07F7/02 , G07G1/00 , G07G3/00 , G08B13/194 , G08B13/196 , G06K15/00
CPC分类号： G07F7/02 , A47F9/045 , G06Q20/343 , G07G1/0036 , G07G1/0063 , G07G3/00 , G07G3/003 , G08B13/1961 , G08B13/19671
摘要： Systems and methods for recognizing and identifying items located on the lower shelf of a shopping cart in a checkout lane of a retail store environment for the purpose of reducing or preventing loss or fraud and increasing the efficiency of a checkout process. The system includes one or more visual sensors that can take images of items and a computer system that receives the images from the one or more visual sensors and automatically identifies the items. The system can be trained to recognize the items using images taken of the items. The system relies on matching visual features from training images to match against features extracted from images taken at the checkout lane. Using the scale-invariant feature transformation (SIFT) method, for example, the system can compare the visual features of the images to the features stored in a database to find one or more matches, where the found one or more matches are used to identify the items.
摘要翻译：为了减少或防止丢失或欺诈以及增加结帐过程的效率，识别和识别位于零售商店环境的结帐通道中的购物车的下架上的物品的系统和方法。该系统包括可以拍摄物品图像的一个或多个视觉传感器和从一个或多个视觉传感器接收图像并自动识别物品的计算机系统。可以使用拍摄的项目的图像来训练系统来识别物品。系统依赖于训练图像的匹配视觉特征，以匹配从结帐通道上拍摄的图像提取的特征。使用比例不变特征变换（SIFT）方法，例如，系统可以将图像的视觉特征与存储在数据库中的特征进行比较，以找到一个或多个匹配，其中发现的一个或多个匹配用于识别的项目。

17. 发明授权

US09092458B1 System and method for managing search results including graphics 有权
标题翻译：用于管理包括图形在内的搜索结果的系统和方法
公开(公告)号：US09092458B1
公开(公告)日：2015-07-28
申请号：US13615381
申请日：2012-09-13
申请人： Pietro Perona , Luis Goncalves , Enrico Di Bernardo
发明人： Pietro Perona , Luis Goncalves , Enrico Di Bernardo
IPC分类号： G06F17/30 , G06F7/00
CPC分类号： G06F17/30253 , G06F17/30247 , G06F17/30256 , G06F17/30274 , G06F17/30277 , G06F17/30864
摘要： A system and method of sorting graphics files with a graphic server and image search engine is disclosed. The method preferably comprises the steps of: receiving a plurality of search results where each of the search results comprising one or more associated graphics; using a general purpose computer to identifying one or more groups of said graphics that depict or otherwise possess similar visual features; and returning the plurality of search results to a user in accordance with said identified groups. The preferred embodiment effectively clusters graphics files, particularly image files, based on upon shared scale-invariant features in order to enable the user to readily identify collections of images relevant to the user while skip past collections of less relevant images.
摘要翻译：公开了一种使用图形服务器和图像搜索引擎排列图形文件的系统和方法。该方法优选地包括以下步骤：接收多个搜索结果，其中每个搜索结果包括一个或多个相关联的图形; 使用通用计算机来识别描绘或以其他方式具有相似视觉特征的一组或多组所述图形; 以及根据所述识别的组将所述多个搜索结果返回给用户。优选实施例基于共享的比例不变特征有效地集中图形文件，特别是图像文件，以便使用户能够容易地识别与用户相关的图像集合，同时跳过不太相关图像的集合。

18. 发明授权

US09002511B1 Methods and systems for obstacle detection using structured light 有权
标题翻译：使用结构光进行障碍物检测的方法和系统
公开(公告)号：US09002511B1
公开(公告)日：2015-04-07
申请号：US11584355
申请日：2006-10-20
申请人： Kevin Hickerson , Luis Goncalves , Paolo Pirjanian , Nikolai Romanov
发明人： Kevin Hickerson , Luis Goncalves , Paolo Pirjanian , Nikolai Romanov
IPC分类号： G06F15/00 , G06F13/376 , G05D1/02
CPC分类号： G05D1/0248 , G01S7/483 , G01S17/023 , G01S17/026 , G01S17/89 , G01S17/936 , G05D1/0038 , G05D1/0246 , G05D1/0253 , G05D1/0274 , G05D2201/0209 , G05D2201/0211 , Y10S901/01
摘要： An obstacle detector for a mobile robot while the robot is in motion is disclosed. The detector preferably includes at least one light source configured to project pulsed light in the path of the robot; a visual sensor for capturing a plurality of images of light reflected from the path of the robot; a processing unit configured to extract the reflections from the images; and an obstacle detection unit configured to detect an obstacle in the path of the robot based on the extracted reflections. In the preferred embodiment, the reflections of the projected light are extracted by subtracting pairs of images in which each pair includes a first image captured with the at least one light source on and a second image captured with the at least one light source off, and then combining images of two or more extracted reflections to suppress the background.
摘要翻译：公开了一种在机器人运动时用于移动机器人的障碍物检测器。检测器优选地包括配置成在机器人的路径中投射脉冲光的至少一个光源; 用于捕获从机器人的路径反射的光的多个图像的视觉传感器; 处理单元，被配置为从图像中提取反射; 以及障碍物检测单元，被配置为基于所提取的反射来检测所述机器人的路径中的障碍物。在优选实施例中，通过减去其中每对包括用至少一个光源捕获的第一图像和至少一个光源捕获的第二图像的图像对，提取投影光的反射，以及然后组合两个或多个提取的反射的图像以抑制背景。

19. 发明授权

US08196822B2 Self checkout with visual recognition 有权
标题翻译：自动结帐，视觉识别
公开(公告)号：US08196822B2
公开(公告)日：2012-06-12
申请号：US13052965
申请日：2011-03-21
申请人： Luis Goncalves
发明人： Luis Goncalves
IPC分类号： G06K15/00
CPC分类号： G07G1/0063 , G07G1/0072 , G07G3/006
摘要： A system and method is disclosed for using object recognition/verification and weight information to confirm the accuracy of a UPC scan, or to provide an affirmative recognition where no UPC scan was made. In the preferred embodiment, the checkout system comprises: a universal product code (UPC) scanner configured to generate a product identifier; at least one camera for capturing one or more image of an item; a database of features and images of known objects; an image processor configured to: extract a plurality of geometric point features from the one or more images; identify matches between the extracted geometric point features and the features of known objects; generate a geometric transform between the extracted geometric point features and the features of known objects for a subset of known objects corresponding to matches; and identify one of the known objects based on a best match of the geometric transform; and a transaction processor configured to execute one of a predetermined set of actions if the identified object is different than the product identifier.
摘要翻译：公开了一种用于使用对象识别/验证和权重信息来确认UPC扫描的准确性的系统和方法，或者在不进行UPC扫描的情况下提供肯定的识别。在优选实施例中，结帐系统包括：通用产品代码（UPC）扫描器，被配置为生成产品标识符; 用于捕获物品的一个或多个图像的至少一个照相机; 已知对象的特征和图像的数据库; 图像处理器，其被配置为：从所述一个或多个图像中提取多个几何点特征; 识别所提取的几何点特征与已知对象的特征之间的匹配; 在提取的几何点特征和已知对象的特征之间生成对应于匹配的已知对象的子集的几何变换; 并基于几何变换的最佳匹配来识别已知对象之一; 以及交易处理器，被配置为如果所识别的对象不同于所述产品标识符，则执行预定动作集中的一个。

20. 发明授权

US07909248B1 Self checkout with visual recognition 有权
标题翻译：自动结帐，视觉识别
公开(公告)号：US07909248B1
公开(公告)日：2011-03-22
申请号：US12229069
申请日：2008-08-18
申请人： Luis Goncalves
发明人： Luis Goncalves
IPC分类号： G06K15/00
CPC分类号： G07G1/0063 , G07G1/0072 , G07G3/006
摘要： A system and method is disclosed for using object recognition/verification and weight information to confirm the accuracy of a UPC scan, or to provide an affirmative recognition where no UPC scan was made. In the preferred embodiment, the checkout system comprises: a universal product code (UPC) scanner configured to generate a product identifier; at least one camera for capturing one or more image of an item; a database of features and images of known objects; an image processor configured to: extract a plurality of geometric point features from the one or more images; identifying matches between the extracted geometric point features and the features of known objects; generate a geometric transform between the extracted geometric point features and the features of known objects for a subset of known objects corresponding to matches; and identify one of the known objects based on a best match of the geometric transform; and a transaction processor configured to execute one of a predetermined set of actions if the identified object is different than the product identifier.
摘要翻译：公开了一种用于使用对象识别/验证和权重信息来确认UPC扫描的准确性的系统和方法，或者在不进行UPC扫描的情况下提供肯定的识别。在优选实施例中，结帐系统包括：通用产品代码（UPC）扫描器，被配置为生成产品标识符; 用于捕获物品的一个或多个图像的至少一个照相机; 已知对象的特征和图像的数据库; 图像处理器，其被配置为：从所述一个或多个图像中提取多个几何点特征; 识别所提取的几何点特征与已知对象的特征之间的匹配; 在提取的几何点特征和已知对象的特征之间生成对应于匹配的已知对象的子集的几何变换; 并基于几何变换的最佳匹配来识别已知对象之一; 以及交易处理器，被配置为如果所识别的对象不同于所述产品标识符，则执行预定动作集中的一个。

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