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

US08538171B2 Method and system for object detection in images utilizing adaptive scanning 有权
标题翻译：利用自适应扫描的图像中物体检测的方法和系统
公开(公告)号：US08538171B2
公开(公告)日：2013-09-17
申请号：US12058224
申请日：2008-03-28
申请人： Michal Juza , Tomas Gold
发明人： Michal Juza , Tomas Gold
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/3233
摘要： An object detection method and system for detecting an object in an image utilizing an adaptive image scanning strategy is disclosed herein. An initial rough shift can be determined based on the size of a scanning window and the image can be scanned continuously for several detections of similar sizes using the rough shift. The scanning window can be classified with respect to a cascade of homogenous classification functions covering one or more features of the object. The size and scanning direction of the scanning window can be adaptively changed depending on the probability of the object occurrence in accordance with scan acceleration. The object can be detected by an object detector and can be localized with higher precision and accuracy.
摘要翻译：本文公开了一种使用自适应图像扫描策略来检测图像中的物体的物体检测方法和系统。可以基于扫描窗口的大小来确定初始粗略位移，并且可以使用粗移位来连续扫描图像以进行几次相似尺寸的检测。扫描窗口可以相对于涵盖对象的一个或多个特征的均匀分类函数的级联来分类。扫描窗口的尺寸和扫描方向可以根据扫描加速度的对象发生的概率自适应地改变。物体可以被物体检测器检测到，并且可以以更高的精度和精度进行定位。

2. 发明申请

US20090245570A1 METHOD AND SYSTEM FOR OBJECT DETECTION IN IMAGES UTILIZING ADAPTIVE SCANNING 有权
标题翻译：使用自适应扫描的图像中对象检测的方法和系统
公开(公告)号：US20090245570A1
公开(公告)日：2009-10-01
申请号：US12058224
申请日：2008-03-28
申请人： Michal Juza , Tomas Gold
发明人： Michal Juza , Tomas Gold
IPC分类号： G06K9/62
CPC分类号： G06K9/3233
摘要： An object detection method and system for detecting an object in an image utilizing an adaptive image scanning strategy is disclosed herein. An initial rough shift can be determined based on the size of a scanning window and the image can be scanned continuously for several detections of similar sizes using the rough shift. The scanning window can be classified with respect to a cascade of homogenous classification functions covering one or more features of the object. The size and scanning direction of the scanning window can be adaptively changed depending on the probability of the object occurrence in accordance with scan acceleration. The object can be detected by an object detector and can be localized with higher precision and accuracy.
摘要翻译：本文公开了一种使用自适应图像扫描策略来检测图像中的物体的物体检测方法和系统。可以基于扫描窗口的大小来确定初始粗略位移，并且可以使用粗移位来连续扫描图像以进行几次相似尺寸的检测。扫描窗口可以相对于涵盖对象的一个或多个特征的均匀分类函数的级联来分类。扫描窗口的尺寸和扫描方向可以根据扫描加速度的对象发生的概率自适应地改变。物体可以被物体检测器检测到，并且可以以更高的精度和精度进行定位。

3. 发明申请

US20090022364A1 MULTI-POSE FAC TRACKING USING MULTIPLE APPEARANCE MODELS 有权
标题翻译：使用多个外观模型的多位置FAC跟踪
公开(公告)号：US20090022364A1
公开(公告)日：2009-01-22
申请号：US11780238
申请日：2007-07-19
申请人： Gurumurthy Swaminathan , Vijendran G. Venkoparao , Rudra N. Hota , Saad J. Bedros , Michal Juza
发明人： Gurumurthy Swaminathan , Vijendran G. Venkoparao , Rudra N. Hota , Saad J. Bedros , Michal Juza
IPC分类号： G06K9/00
CPC分类号： G06K9/00261 , G06T7/251 , G06T7/277 , G06T7/75 , G06T2207/10016 , G06T2207/30201
摘要： A system and method are provided for tracking a face moving through multiple frames of a video sequence. A predicted position of a face in a video frame is obtained. Similarity matching for both a color model and an edge model are performed to derive correlation values for each about the predicted position. The correlation values are then combined to determine a best position and scale match to track a face in the video.
摘要翻译：提供了一种用于跟踪通过视频序列的多个帧移动的面部的系统和方法。获得视频帧中的脸部的预测位置。执行颜色模型和边缘模型的相似性匹配以导出关于预测位置的相关值。然后将相关值组合以确定用于跟踪视频中的脸部的最佳位置和比例匹配。

4. 发明申请

US20070171281A1 Object initialization in video tracking 审中-公开
标题翻译：视频跟踪中的对象初始化
公开(公告)号：US20070171281A1
公开(公告)日：2007-07-26
申请号：US11337771
申请日：2006-01-23
申请人： Michal Juza , Karel Marik
发明人： Michal Juza , Karel Marik
IPC分类号： H04N7/18
CPC分类号： G06K9/4647 , G06K9/00771 , G06K2209/23 , G06T7/277 , G06T2207/10016 , G06T2207/30196 , G06T2207/30236 , G06T2207/30241
摘要： A system and method initializes objects in video data. In an embodiment, the video data is an output of a video tracker, and in a particular embodiment, the video tracker is a particle filter. A histogram is calculated that indicates a number of particles that do not cover an object in an input image from the particle filter at a position in the input image. The system and method then initializes an object to be tracked in the input image as a function of the histogram.
摘要翻译：系统和方法初始化视频数据中的对象。在一个实施例中，视频数据是视频跟踪器的输出，并且在特定实施例中，视频跟踪器是粒子滤波器。计算直方图，其指示在输入图像中的位置处不包括来自粒子滤波器的输入图像中的物体的数量的粒子。然后，系统和方法根据直方图初始化输入图像中要跟踪的对象。

5. 发明授权

US08064639B2 Multi-pose face tracking using multiple appearance models 有权
标题翻译：多姿态脸部跟踪使用多种外观模型
公开(公告)号：US08064639B2
公开(公告)日：2011-11-22
申请号：US11780238
申请日：2007-07-19
申请人： Gurumurthy Swaminathan , Vijendran G. Venkoparao , Rudra N. Hota , Saad J. Bedros , Michal Juza
发明人： Gurumurthy Swaminathan , Vijendran G. Venkoparao , Rudra N. Hota , Saad J. Bedros , Michal Juza
IPC分类号： G06K9/00
CPC分类号： G06K9/00261 , G06T7/251 , G06T7/277 , G06T7/75 , G06T2207/10016 , G06T2207/30201
摘要： A system and method are provided for tracking a face moving through multiple frames of a video sequence. A predicted position of a face in a video frame is obtained. Similarity matching for both a color model and an edge model are performed to derive correlation values for each about the predicted position. The correlation values are then combined to determine a best position and scale match to track a face in the video.
摘要翻译：提供了一种用于跟踪通过视频序列的多个帧移动的面部的系统和方法。获得视频帧中的脸部的预测位置。执行颜色模型和边缘模型的相似性匹配以导出关于预测位置的相关值。然后将相关值组合以确定用于跟踪视频中的脸部的最佳位置和比例匹配。

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