公开(公告)号：US07379100B2

公开(公告)日：2008-05-27

申请号：US11058028

申请日：2005-02-14

申请人： Salih Burak Gokturk ,  Abbas Rafii

发明人： Salih Burak Gokturk ,  Abbas Rafii

IPC分类号： H04N5/235

CPC分类号： G01S17/89 ,  G01S7/4865 ,  G01S7/4868 ,  G01S7/487 ,  G01S17/10 ,  H04N5/2355

摘要： Dynamic range of photodetector sensors useable in a TOF system is enhanced by capturing images of an object using multiple exposure time settings. Longer exposure settings more appropriately capture non-reflective and/or distant objects, while shorter exposure settings more appropriately capture reflective and/or closer objects. During parallel mode operation, detection signal readouts are taken from each photodetector at different time intervals within an overall exposure time. In sequential mode operation, detection signal readouts are taken and stored for each photodetector at the end of a first exposure time interval and the photodetectors are reset. After a second, different exposure time interval readouts are taken and stored, and the photodetectors reset, etc. In these modes one of the time exposure intervals will be relatively optimum for enhanced dynamic range operation. Once images with multiple exposure settings are obtained, best effort brightness and range images can be obtained, and motion artifacts can be reduced.

摘要翻译： 在TOF系统中可用的光电检测器传感器的动态范围通过使用多个曝光时间设置捕获物体的图像来增强。 较长的曝光设置更适当地捕获非反射和/或远距离的物体，而较短的曝光设置更适当地捕获反射和/或更近的物体。 在并行模式操作期间，在整个曝光时间内以不同的时间间隔从每个光电检测器获取检测信号读出。 在顺序模式操作中，在第一曝光时间间隔结束时对每个光电检测器采集和存储检测信号读出，并且光电检测器被复位。 一秒钟后，拍摄和存储不同的曝光时间间隔读数，并且光电探测器复位等。在这些模式中，对于增强的动态范围操作，时间曝光间隔之一将是相对最佳的。 一旦获得具有多个曝光设置的图像，就可以获得尽力而为的亮度和范围图像，并且可以减少运动伪影。

公开(公告)号：US07203356B2

公开(公告)日：2007-04-10

申请号：US10411674

申请日：2003-04-11

申请人： Salih Burak Gokturk ,  Abbas Rafii

发明人： Salih Burak Gokturk ,  Abbas Rafii

IPC分类号： G06K9/00

CPC分类号： G06K9/00228 ,  G06T9/001 ,  H04N19/23

摘要： Three-dimensional position information is used to segment objects in a scene viewed by a three dimensional camera. At one or more instances of an interval, the head location of the user is determined. Object-based compression schemes are applied on the segmented objects and the detected head.

摘要翻译： 三维位置信息用于分割由三维相机观看的场景中的物体。 在间隔的一个或多个情况下，确定用户的头部位置。 基于对象的压缩方案应用于分段对象和检测到的头部。

公开(公告)号：US07526120B2

公开(公告)日：2009-04-28

申请号：US10660907

申请日：2003-09-11

申请人： Salih Burak Gokturk ,  Cyrus Bamji ,  Abbas Rafii ,  Carlo Tomasi ,  Xinqiao Liu

发明人： Salih Burak Gokturk ,  Cyrus Bamji ,  Abbas Rafii ,  Carlo Tomasi ,  Xinqiao Liu

IPC分类号： G06K9/00

CPC分类号： B60R21/01516 ,  B60R21/013 ,  B60R21/0152 ,  B60R21/01538 ,  G06K9/00362

摘要： A sensor system is provided for determining a deployment level of an airbag in a vehicle. A light source of the sensor system emits light onto a region around a vehicle seat. An array of light-sensitive pixels which capture reflected light from the scene, including reflected light that originated from the light source. Processing resources are provided that determine depth information for an object in the scene based on a time-of-flight characteristic of the reflected light from the light source captured on the array. The processing resources may be configured to determine occupancy data for the object based on the captured reflected light from the scene. The processing resources are configured to determine the deployment level of the airbag based at least in part on the occupancy data in when a collision of the vehicle occurs.

摘要翻译： 提供用于确定车辆中的气囊的展开水平的传感器系统。 传感器系统的光源将光发射到车辆座椅周围的区域。 捕获来自场景的反射光的光敏像素阵列，包括源自光源的反射光。 提供处理资源，其基于来自在阵列上捕获的光源的反射光的飞行时间特性来确定场景中的对象的深度信息。 处理资源可以被配置为基于来自场景的所捕获的反射光来确定对象的占用数据。 处理资源被配置为至少部分地基于当车辆碰撞发生时的占用数据来确定安全气囊的部署水平。

公开(公告)号：US10242255B2

公开(公告)日：2019-03-26

申请号：US12074443

申请日：2008-03-04

申请人： Abbas Rafii ,  Salih Burak Gokturk ,  Carlo Tomasi ,  Fahri Sürücü

发明人： Abbas Rafii ,  Salih Burak Gokturk ,  Carlo Tomasi ,  Fahri Sürücü

IPC分类号： G06K9/00 ,  G06F3/01 ,  H04N21/4223 ,  H04N21/442

摘要： Acquired three-dimensional positional information is used to identify user created gesture(s), which gesture(s) are classified to determine appropriate input(s) to an associated electronic device or devices. Preferably at at least one instance of a time interval, the posture of a portion of a user is recognized, based at least one factor such as shape, position, orientation, velocity. Posture over each of the instance(s) is recognized as a combined gesture. Because acquired information is three-dimensional, two gestures may occur simultaneously.

公开(公告)号：US09165368B2

公开(公告)日：2015-10-20

申请号：US13219349

申请日：2011-08-26

申请人： Abbas Rafii ,  Salih Burak Gokturk

发明人： Abbas Rafii ,  Salih Burak Gokturk

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/66 ,  G06K9/62 ,  G06K9/34 ,  G06K9/38 ,  G06T7/00

CPC分类号： G06T7/0081 ,  G06K9/00201 ,  G06T7/11 ,  G06T7/136 ,  G06T2207/10028 ,  G06T2207/30261

摘要： A method and system analyzes data acquired by image systems to more rapidly identify objects of interest in the data. In one embodiment, z-depth data are segmented such that neighboring image pixels having similar z-depths are given a common label. Blobs, or groups of pixels with a same label, may be defined to correspond to different objects. Blobs preferably are modeled as primitives to more rapidly identify objects in the acquired image. In some embodiments, a modified connected component analysis is carried out where image pixels are pre-grouped into regions of different depth values preferably using a depth value histogram. The histogram is divided into regions and image cluster centers are determined. A depth group value image containing blobs is obtained, with each pixel being assigned to one of the depth groups.

摘要翻译： 一种方法和系统分析由图像系统获取的数据，以更快速地识别数据中感兴趣的对象。 在一个实施例中，z深度数据被分割，使得具有相似z深度的相邻图像像素被给予公共标签。 具有相同标签的Blob或像素组可以被定义为对应于不同的对象。 Blob优选地被建模为基元以更快速地识别所获取的图像中的对象。 在一些实施例中，执行修改的连接分量分析，其中图像像素优选地使用深度值直方图被预分组成不同深度值的区域。 直方图被划分为区域，确定图像聚类中心。 获得包含斑点的深度组值图像，其中每个像素被分配给深度组之一。

公开(公告)号：US20110291926A1

公开(公告)日：2011-12-01

申请号：US12074443

申请日：2008-03-04

申请人： Salih Burak Gokturk ,  Carlo Tomasi ,  Fahri Surucu ,  Abbas Rafii

发明人： Salih Burak Gokturk ,  Carlo Tomasi ,  Fahri Surucu ,  Abbas Rafii

IPC分类号： G06F3/033 ,  G06K9/66

CPC分类号： G06K9/00389 ,  A63F2300/1093 ,  G06F3/017 ,  G06K9/00382 ,  H04N21/4223 ,  H04N21/44218

摘要： Acquired three-dimensional positional information is used to identify user created gesture(s), which gesture(s) are classified to determine appropriate input(s) to an associated electronic device or devices. Preferably at at least one instance of a time interval, the posture of a portion of a user is recognized, based at least one factor such as shape, position, orientation, velocity. Posture over each of the instance(s) is recognized as a combined gesture. Because acquired information is three-dimensional, two gestures may occur simultaneously.

摘要翻译： 获取的三维位置信息用于识别用户创建的手势，哪些手势被分类以确定与相关联的电子设备或设备的适当输入。 优选地，在至少一个时间间隔的情况下，基于形状，位置，取向，速度等至少一个因素来识别用户的一部分的姿势。 每个实例的姿势被识别为组合手势。 因为获取的信息是三维的，所以可能同时发生两个手势。

公开(公告)号：US08009871B2

公开(公告)日：2011-08-30

申请号：US11349311

申请日：2006-02-06

申请人： Abbas Rafii ,  Salih Burak Gokturk

发明人： Abbas Rafii ,  Salih Burak Gokturk

IPC分类号： G06K9/00 ,  G06K9/34 ,  G06K9/46 ,  G06K9/62 ,  G01N21/86 ,  G01V8/00 ,  G01C3/08

CPC分类号： G06T7/0081 ,  G06K9/00201 ,  G06T7/11 ,  G06T7/136 ,  G06T2207/10028 ,  G06T2207/30261

摘要： A method and system analyzes data acquired by image systems to more rapidly identify objects of interest in the data. In one embodiment, z-depth data are segmented such that neighboring image pixels having similar z-depths are given a common label. Blobs, or groups of pixels with a same label, may be defined to correspond to different objects. Blobs preferably are modeled as primitives to more rapidly identify objects in the acquired image. In some embodiments, a modified connected component analysis is carried out where image pixels are pre-grouped into regions of different depth values preferably using a depth value histogram. The histogram is divided into regions and image cluster centers are determined. A depth group value image containing blobs is obtained, with each pixel being assigned to one of the depth groups.

摘要翻译： 一种方法和系统分析由图像系统获取的数据，以更快速地识别数据中感兴趣的对象。 在一个实施例中，z深度数据被分割，使得具有相似z深度的相邻图像像素被给予公共标签。 具有相同标签的Blob或像素组可以被定义为对应于不同的对象。 Blob优选地被建模为基元以更快速地识别所获取的图像中的对象。 在一些实施例中，执行修改的连接分量分析，其中图像像素优选地使用深度值直方图被预分组成不同深度值的区域。 直方图被划分为区域，确定图像聚类中心。 获得包含斑点的深度组值图像，其中每个像素被分配给深度组之一。

公开(公告)号：US07511801B1

公开(公告)日：2009-03-31

申请号：US12154774

申请日：2008-05-27

申请人： Abbas Rafii ,  Salih Burak Gokturk

发明人： Abbas Rafii ,  Salih Burak Gokturk

IPC分类号： G01C3/08

CPC分类号： G01C3/08

摘要： Performance of pixel detectors in a TOF imaging system is dynamically adjusted to improve dynamic range to maximize the number of pixel detectors that output valid data. The invention traverses the system-acquired z depth, the brightness, and the active brightness images, and assigns each pixel a quantized value. Quantization values encompass pixels receiving too little light, normal light, to too much light. Pixels are grouped into quantized category groups, whose populations are represented by a histogram. If the number of pixels in the normal category exceeds a threshold, no immediate corrective action is taken. If the number of pixel receiving too little (or too much) light exceeds those receiving too much (or too little) light, the invention commands at least one system parameter change to increase (or decrease) light reaching the pixels. Controllable TOF system parameters can include exposure time, common mode resets, video gain, among others.

摘要翻译： 动态地调整TOF成像系统中的像素检测器的性能，以改善动态范围，以最大化输出有效数据的像素检测器的数量。 本发明遍历系统获取的z深度，亮度和有效亮度图像，并且将每个像素分配为量化值。 量化值包括光线太少，正常光线过多的光线。 像素被分组成量化类别组，其群体由直方图表示。 如果正常类别中的像素数超过阈值，则不会立即采取纠正措施。 如果接收太少（或太多）的光的数量超过接收太多（或太少）光的光的数量，则本发明命令至少一个系统参数变化来增加（或减少）到达像素的光。 可控TOF系统参数可以包括曝光时间，共模复位，视频增益等。

公开(公告)号：US07379163B2

公开(公告)日：2008-05-27

申请号：US11349310

申请日：2006-02-06

申请人： Abbas Rafii ,  Salih Burak Gokturk

发明人： Abbas Rafii ,  Salih Burak Gokturk

IPC分类号： G01C3/08

CPC分类号： G01C3/08

摘要： Performance of pixel detectors in a TOF imaging system is dynamically adjusted to improve dynamic range to maximize the number of pixel detectors that output valid data. The invention traverses the system-acquired z depth, the brightness, and the active brightness images, and assigns each pixel a quantized value. Quantization values encompass pixels receiving too little light, normal light, to too much light. Pixels are grouped into quantized category groups, whose populations are represented by a histogram. If the number of pixels in the normal category exceeds a threshold, no immediate corrective action is taken. If the number of pixel receiving too little (or too much) light exceeds those receiving too much (or too little) light, the invention commands at least one system parameter change to increase (or decrease) light reaching the pixels. Controllable TOF system parameters can include exposure time, common mode resets, video gain, among others.

摘要翻译： 动态地调整TOF成像系统中的像素检测器的性能，以改善动态范围，以最大化输出有效数据的像素检测器的数量。 本发明遍历系统获取的z深度，亮度和有效亮度图像，并且将每个像素分配为量化值。 量化值包括光线太少，正常光线过多的光线。 像素被分组成量化类别组，其群体由直方图表示。 如果正常类别中的像素数超过阈值，则不会立即采取纠正措施。 如果接收太少（或太多）的光的数量超过接收太多（或太少）光的光的数量，则本发明命令至少一个系统参数变化来增加（或减少）到达像素的光。 可控TOF系统参数可以包括曝光时间，共模复位，视频增益等。

公开(公告)号：US07340077B2

公开(公告)日：2008-03-04

申请号：US10369999

申请日：2003-02-18

申请人： Salih Burak Gokturk ,  Carlo Tomasi ,  Fahri Sürücü ,  Abbas Rafii

发明人： Salih Burak Gokturk ,  Carlo Tomasi ,  Fahri Sürücü ,  Abbas Rafii

IPC分类号： G06K9/00

CPC分类号： G06F3/017 ,  A63F2300/1093 ,  G06K9/00335 ,  G06K9/00362 ,  G06K9/00382 ,  H04L2012/2841

摘要： Three-dimensional position information is used to identify the gesture created by a body part of interest. At one or more instances of an interval, the posture of a body part is recognized, based on the shape of the body part and its position and orientation. The posture of the body part over each of the one or more instances in the interval are recognized as a combined gesture. The gesture is classified for determining an input into a related electronic device.

摘要翻译： 三维位置信息用于识别由感兴趣的身体部分创建的手势。 在间隔的一个或多个情况下，基于身体部位的形状及其位置和取向来识别身体部位的姿势。 在该间隔中的一个或多个实例中的每一个上的身体部位的姿势被识别为组合手势。 手势被分类以确定相关电子设备的输入。