公开(公告)号：US09129158B1

公开(公告)日：2015-09-08

申请号：US13412527

申请日：2012-03-05

申请人： Swarup Medasani ,  Suhas E. Chelian ,  Shinko Y. Cheng ,  Rashmi N. Sundareswara ,  Howard Neely, III

发明人： Swarup Medasani ,  Suhas E. Chelian ,  Shinko Y. Cheng ,  Rashmi N. Sundareswara ,  Howard Neely, III

IPC分类号： G06K9/62 ,  G06K9/00 ,  G06T7/20

CPC分类号： G06K9/00718 ,  G06K9/00335 ,  G06K9/00342 ,  G06K9/6219 ,  G06K9/6263 ,  G06K9/6296 ,  G06T2207/10016

摘要： Described is a method and system for embedding unsupervised learning into three critical processing stages of the spatio-temporal visual stream. The system first receives input video comprising input video pixels representing at least one action and at least one object having a location. Microactions are generated from the input image using a set of motion sensitive filters. A relationship between the input video pixels and the microactions is then learned, and a set of spatio-temporal concepts is learned from the microactions. The system then learns to acquire new knowledge from the spatio-temporal concepts using mental imagery processes. Finally, a visual output is presented to a user based on the learned set of spatio-temporal concepts and the new knowledge to aid the user in visually comprehending the at least one action in the input video.

摘要翻译： 描述了将无监督学习嵌入时空视觉流的三个关键处理阶段的方法和系统。 系统首先接收包括表示至少一个动作的输入视频像素和至少一个具有位置的对象的输入视频。 使用一组运动敏感滤波器从输入图像生成微反应。 然后学习输入视频像素和微动作之间的关系，并从微动态学习一组时空概念。 该系统然后学习从使用心理图像过程的时空概念中获取新知识。 最后，基于学习的时空概念和新知识，向用户呈现视觉输出，以帮助用户直观地理解输入视频中的至少一个动作。

公开(公告)号：US08948499B1

公开(公告)日：2015-02-03

申请号：US12962548

申请日：2010-12-07

申请人： Swarup Medasani ,  David L. Allen ,  Suhas E. Chelian ,  Yuri Owechko

发明人： Swarup Medasani ,  David L. Allen ,  Suhas E. Chelian ,  Yuri Owechko

IPC分类号： G06K9/62

CPC分类号： G06K9/469 ,  G06K9/00771 ,  G06K9/00785 ,  G06K9/6296

摘要： Described is a system for object and behavior recognition which utilizes a collection of modules which, when integrated, can automatically recognize, learn, and adapt to simple and complex visual behaviors. An object recognition module utilizes a cooperative swarm algorithm to classify an object in a domain. A graph-based object representation module is configured to use a graphical model to represent a spatial organization of the object within the domain. Additionally, a reasoning and recognition engine module consists of two sub-modules: a knowledge sub-module and a behavior recognition sub-module. The knowledge sub-module utilizes a Bayesian network, while the behavior recognition sub-module consists of layers of adaptive resonance theory clustering networks and a layer of a sustained temporal order recurrent temporal order network. The described invention has applications in video forensics, data mining, and intelligent video archiving.

摘要翻译： 描述了一种用于对象和行为识别的系统，其利用模块集合，当集成时，可以自动识别，学习和适应简单和复杂的视觉行为。 对象识别模块利用协作群算法对域中的对象进行分类。 基于图形的对象表示模块被配置为使用图形模型来表示域内对象的空间组织。 另外，推理和识别引擎模块由两个子模块组成：知识子模块和行为识别子模块。 知识子模块利用贝叶斯网络，而行为识别子模块由自适应共振理论聚类网络层和持续时间顺序复现时间顺序网络层组成。 所描述的发明在视频取证，数据挖掘和智能视频归档中具有应用。

公开(公告)号：US09449259B1

公开(公告)日：2016-09-20

申请号：US13558298

申请日：2012-07-25

申请人： Shinko Y. Cheng ,  Yuri Owechko ,  Swarup Medasani

发明人： Shinko Y. Cheng ,  Yuri Owechko ,  Swarup Medasani

IPC分类号： G06K9/62 ,  G06K9/46 ,  G06K9/66 ,  G06K9/68 ,  G06K9/70 ,  G06N99/00

CPC分类号： G06K9/6257 ,  G06K9/3241 ,  G06K9/6217 ,  G06N99/005

摘要： The present invention relates to a classifier cascade object detection system. The system operates by inputting an image patch into parallel feature generation modules, each of the feature generation modules operable for extracting features from the image patch. The features are provided to an opportunistic classifier cascade, the opportunistic classifier cascade having a series of classifier stages. The opportunistic classifier cascade is executed by progressively evaluating, in each classifier in the classifier cascade, the features to produce a response, with each response progressively utilized by a decision function to generate a stage response for each classifier stage. If each stage response exceeds a stage threshold then the image patch is classified as a target object, and if the stage response from any of the decision functions does not exceed the stage threshold, then the image patch is classified as a non-target object.

摘要翻译： 本发明涉及分级器级联物体检测系统。 该系统通过将图像补丁输入到并行特征生成模块中来操作，每个特征生成模块可操作用于从图像补片提取特征。 这些特征被提供给机会分类器级联，机会分类器级联具有一系列分类器级。 机会分类器级联是通过在分类器级联中的每个分类器中逐步评估产生响应的特征来执行的，每个响应由决策函数逐渐被利用以产生每个分类器阶段的阶段响应。 如果每个阶段响应超过阶段阈值，则图像补丁被分类为目标对象，并且如果来自任何决策函数的阶段响应不超过阶段阈值，则将图像补丁分类为非目标对象。

公开(公告)号：US08818036B1

公开(公告)日：2014-08-26

申请号：US13558257

申请日：2012-07-25

申请人： Yuri Owechko ,  Shinko Y. Cheng ,  Swarup Medasani ,  Kyungnam Kim

发明人： Yuri Owechko ,  Shinko Y. Cheng ,  Swarup Medasani ,  Kyungnam Kim

IPC分类号： G06K9/00

CPC分类号： G06K9/00771 ,  G06K9/00369 ,  G06K9/209 ,  G06T7/277 ,  G06T2207/10016 ,  G06T2207/20076 ,  G06T2207/30232 ,  G06T2207/30241

摘要： Described is a system for registering a viewpoint of an imaging sensor with respect to a geospatial model or map. An image of a scene of a geospatial region comprising an object is received as input. The image of the scene is captured by a sensor having a current sensor state. Observation data related to the object's state is received, wherein the observation data comprises an object behavior of the object given the geospatial region. An estimate of the current sensor state is generated using a probability of an observation from the observation data given the current sensor state x. Finally, the image of the scene is registered with a geospatial model or map based on the estimate of the current sensor state.

摘要翻译： 描述了一种用于记录关于地理空间模型或地图的成像传感器的视点的系统。 接收包括对象的地理空间区域的场景的图像作为输入。 场景的图像由具有当前传感器状态的传感器捕获。 接收与对象状态相关的观测数据，其中观测数据包括给定地理空间区域的对象的对象行为。 使用给定当前传感器状态x的观测数据的观察概率来生成当前传感器状态的估计。 最后，基于当前传感器状态的估计，将场景的图像与地理空间模型或地图一起注册。

公开(公告)号：US08270671B1

公开(公告)日：2012-09-18

申请号：US12380415

申请日：2009-02-27

申请人： Swarup Medasani ,  Rahul Shringarpure

发明人： Swarup Medasani ,  Rahul Shringarpure

IPC分类号： G06K9/00

CPC分类号： G06K9/00986 ,  G06K9/4642 ,  G06K9/6202

摘要： Disclosed is a method and system for generic object detection using block-based feature computation and, more specifically, a method and system for massively parallel computation of object features sets according to an optimized clock-cycle matrix. The method uses an array of correlators to calculate block sums for each section of the image to be analyzed. A greedy heuristic scheduling algorithm is executed to produce an optimized clock cycle matrix such that overlapping features which use the same block sum do not attempt to access the block at the same time, thereby avoiding race memory conditions. The processing system can employ any of a variety of hardwired Very Large Scale Integration (VLSI) chips such as Field Programmable Gate Arrays (FPGAs), Digital Signal Processors (DSPs) and Application Specific Integrated Circuits (ASICs).

摘要翻译： 公开了一种使用基于块的特征计算的通用对象检测的方法和系统，更具体地，涉及根据优化的时钟周期矩阵对对象特征集进行大规模并行计算的方法和系统。 该方法使用相关器阵列来计算待分析图像的每个部分的块和。 执行贪婪启发式调度算法以产生优化的时钟周期矩阵，使得使用相同块和的重叠特征不尝试同时访问块，从而避免竞态存储器条件。 处理系统可以采用各种硬连线超大规模集成（VLSI）芯片，例如现场可编程门阵列（FPGA），数字信号处理器（DSP）和专用集成电路（ASIC）。

公开(公告)号：US07761389B2

公开(公告)日：2010-07-20

申请号：US11843876

申请日：2007-08-23

申请人： Swarup Medasani ,  Qin Jiang ,  Narayan Srinivasa ,  Yilu Zhang ,  Leandro G. Barajas ,  Nick S. Kapsokavathis

发明人： Swarup Medasani ,  Qin Jiang ,  Narayan Srinivasa ,  Yilu Zhang ,  Leandro G. Barajas ,  Nick S. Kapsokavathis

IPC分类号： G06F15/18 ,  G06N7/02

CPC分类号： G01R31/3606 ,  G01R31/3693

摘要： Anomaly prediction of battery parasitic load includes processing input data related to a state of charge for a battery and a durational factor utilizing a machine learning algorithm and generating a predicted start-up state of charge. Warnings are issued if the predicted start-up state of charge drops below a threshold level within an operational time.

摘要翻译： 电池寄生负载的异常预测包括利用机器学习算法处理与电池的充电状态有关的输入数据和持续时间因子，并产生预测的充电状态。 如果预计的启动状态在运行时间内下降到阈值以下，则发出警告。

公开(公告)号：US07715591B2

公开(公告)日：2010-05-11

申请号：US10132875

申请日：2002-04-24

申请人： Yuri Owechko ,  Narayan Srinivasa ,  Swarup Medasani ,  Riccardo Boscolo

发明人： Yuri Owechko ,  Narayan Srinivasa ,  Swarup Medasani ,  Riccardo Boscolo

IPC分类号： G06K9/00

CPC分类号： G06K9/6292 ,  G06K9/00201 ,  G06K9/00369 ,  G06K9/00832 ,  G06K9/209 ,  G06K9/522 ,  G06T7/97 ,  G06T2207/10021 ,  G06T2207/20064 ,  G06T2207/30268 ,  H04N2013/0081 ,  H04N2013/0092

摘要： A vision-based system for automatically detecting the type of object within a specified area, such as the type of occupant within a vehicle is presented. The type of occupant can then be used to determine whether an airbag deployment system should be enabled or not. The system extracts different features, including wavelet features and/or a disparity map from images captured by image sensors. These features are then processed by classification algorithms to produce class confidences for various occupant types. The occupant class confidences are fused and processed to determine occupant type. In a preferred embodiment, image features from image edges, wavelet features, and disparity are used. Various classification algorithms may be implemented to classify the object. Use of the disparity map and/or wavelet features provides greater computational efficiency.

摘要翻译： 提出了一种基于视觉的系统，用于自动检测指定区域内物体的类型，例如车辆内乘客的类型。 然后可以使用乘客的类型来确定是否应启用安全气囊展开系统。 该系统从图像传感器捕获的图像中提取不同的特征，包括小波特征和/或视差图。 然后通过分类算法对这些特征进行处理，以便为各种乘客类型生成类别信息。 乘员班信心被融合和处理以确定乘客类型。 在优选实施例中，使用来自图像边缘的图像特征，小波特征和视差。 可以实现各种分类算法来对对象进行分类。 使用视差图和/或小波特征提供更大的计算效率。

公开(公告)号：US20070183670A1

公开(公告)日：2007-08-09

申请号：US11433159

申请日：2006-05-12

申请人： Yuri Owechko ,  Swarup Medasani

发明人： Yuri Owechko ,  Swarup Medasani

IPC分类号： G06K9/62 ,  G06K9/46

CPC分类号： G06K9/6292 ,  G06K9/00369 ,  G06K9/6229

摘要： An object recognition system is described that incorporates swarming classifiers. The swarming classifiers comprise a plurality of software agents configured to operate as a cooperative swarm to classify an object group in a domain. Each node N represents an object in the group having K object attributes. Each agent is assigned an initial velocity vector to explore a KN-dimensional solution space for solutions matching the agent's graph. Further, each agent is configured to search the solution space for an optimum solution. The agents keep track of their coordinates in the KN-dimensional solution space that are associated with an observed best solution (pbest) and a global best solution (gbest). The gbest is used to store the best solution among all agents which corresponds to a best graph among all agents. Each velocity vector thereafter changes towards pbest and gbest, allowing the cooperative swarm to classify of the object group.

摘要翻译： 描述了包含群组分类器的对象识别系统。 群集分类器包括被配置为作为协作群进行操作以将域中的对象组分类的多个软件代理。 每个节点N表示具有K个对象属性的组中的对象。 为每个代理分配一个初始速度向量，以探索与代理图相匹配的解决方案的KN维解决方案空间。 此外，每个代理被配置为搜索解空间以获得最佳解决方案。 代理人跟踪与观察到的最佳解决方案（pbest）和全局最佳解决方案（gbest）相关联的KN维解决方案空间中的坐标。 gbest用于在所有代理之间存储对应于最佳图形的所有代理中的最佳解决方案。 其后每个速度矢量向pbest和gbest变化，允许协作群对目标群进行分类。

公开(公告)号：US08645294B1

公开(公告)日：2014-02-04

申请号：US12583238

申请日：2009-08-17

申请人： Yuri Owechko ,  Yang Chen ,  Swarup Medasani

发明人： Yuri Owechko ,  Yang Chen ,  Swarup Medasani

IPC分类号： G06F15/18

CPC分类号： G06N5/043 ,  G06K9/6229 ,  G06N3/006 ,  G06T7/337 ,  G06T7/35

摘要： Described is a method for image registration utilizing particle swarm optimization (PSO). In order to register two images, a set of image windows is first selected from a test image and transformed. A plurality of software agents is configured to operate as a cooperative swarm to optimize an objective function, and an objective function is then evaluated at the location of each agent. The objective function represents a measure of the difference or registration quality between at least one transformed image window and a reference image. The position vectors representing the current individual best solution found and the current global best solution found by all agents are then updated according to PSO dynamics. Finally, the current global best solution is compared with a maximum pixel value which signifies a match between an image window and the reference image. A system and a computer program product are also described.

摘要翻译： 描述了使用粒子群优化（PSO）的图像配准的方法。 为了注册两个图像，首先从测试图像中选择一组图像窗口并进行变换。 多个软件代理被配置为作为协作群来操作以优化目标函数，然后在每个代理的位置处评估目标函数。 目标函数表示至少一个变换的图像窗口和参考图像之间的差异或注册质量的度量。 然后根据PSO动态更新表示当前找到的最佳解决方案的位置向量和所有代理发现的当前全局最佳解。 最后，将当前全局最佳解决方案与表示图像窗口和参考图像之间的匹配的最大像素值进行比较。 还描述了系统和计算机程序产品。

公开(公告)号：US08553989B1

公开(公告)日：2013-10-08

申请号：US12799618

申请日：2010-04-27

申请人： Yuri Owechko ,  Swarup Medasani ,  Jim Nelson

发明人： Yuri Owechko ,  Swarup Medasani ,  Jim Nelson

IPC分类号： G06K9/00

CPC分类号： G06K9/00201 ,  G06K9/3233 ,  G06K9/468

摘要： The present invention relates to a method for three-dimensional (3D) object recognition using region of interest geometric features. The method includes acts of receiving an implicit geometry representation regarding a three-dimensional (3D) object of interest. A region of interest (ROI) is centered on the implicit geometry representation such that there is at least one intersection area between the ROI and the implicit geometry representation. Object shape features are calculated that reflect a location of the ROI with respect to the implicit geometry representation. The object shape features are assembled into a feature vector. A classification confidence value is generated with respect to a particular object classification. Finally, the 3D object of interest is classified as a particular object upon the output of a statistical classifier reaching a predetermined threshold.

摘要翻译： 本发明涉及使用感兴趣区域几何特征的三维（3D）物体识别方法。 该方法包括接收关于感兴趣的三维（3D）对象的隐式几何表示的动作。 感兴趣区域（ROI）以隐式几何表示为中心，使得ROI和隐式几何表示之间存在至少一个交叉区域。 计算反映相对于隐式几何表示的ROI的位置的对象形状特征。 对象形状特征被组合成特征向量。 相对于特定对象分类产生分类置信度值。 最后，感兴趣的3D对象在统计分类器的输出达到预定阈值时被分类为特定对象。