公开(公告)号：US08553971B2

公开(公告)日：2013-10-08

申请号：US12821682

申请日：2010-06-23

申请人： Kuo-Tang Huang ,  Bor-Tung Jiang ,  Shang-Chieh Lu ,  Po-Huang Shieh

发明人： Kuo-Tang Huang ,  Bor-Tung Jiang ,  Shang-Chieh Lu ,  Po-Huang Shieh

IPC分类号： G06K9/00

CPC分类号： G06T7/85 ,  H04N13/246

摘要： A method and system for measuring three-dimensional coordinates of an object are provided. The method includes: capturing images from a calibration point of known three-dimensional coordinates by two image-capturing devices disposed in a non-parallel manner, so as for a processing module connected to the image-capturing devices to calculate a beam confluence collinear function of the image-capturing devices; calibrating the image-capturing devices to calculate intrinsic parameters and extrinsic parameters of the image-capturing devices and calculate the beam confluence collinear function corresponding to the image-capturing devices; and capturing images from a target object by the image-capturing devices so as for the processing module to calculate three-dimensional coordinates of the object according to the beam confluence collinear function. In so doing, the method and system enable the three-dimensional coordinates and bearings of a target object to be calculated quickly, precisely, and conveniently. Hence, the method and system are applicable to various operating environments.

摘要翻译： 提供了一种用于测量物体的三维坐标的方法和系统。 该方法包括：通过以非平行方式设置的两个图像捕获装置从已知三维坐标的校准点捕获图像，以便连接到图像捕获装置的处理模块来计算束汇合共线函数 的图像捕获装置; 校准图像捕获装置以计算图像捕获装置的固有参数和外在参数，并计算与图像捕获装置相对应的束融合共线功能; 并且通过图像捕获装置从目标对象捕获图像，以便处理模块根据光束汇合共线函数计算对象的三维坐标。 通过这样做，方法和系统能够快速，准确，方便地计算目标对象的三维坐标和轴承。 因此，该方法和系统适用于各种操作环境。

公开(公告)号：US20100278389A1

公开(公告)日：2010-11-04

申请号：US12512628

申请日：2009-07-30

申请人： Ya-Hui Tsai ,  Kuo-Tang Huang ,  Chun-Lung Chang ,  Lai-Sheng Chen

发明人： Ya-Hui Tsai ,  Kuo-Tang Huang ,  Chun-Lung Chang ,  Lai-Sheng Chen

IPC分类号： G06K9/00

CPC分类号： G06K9/325 ,  G06K9/3258 ,  G06K9/4604 ,  G06K9/72 ,  G06K2209/01 ,  G06K2209/15 ,  G06T11/60

摘要： The present invention provides a method for image recombination of a plurality of images and image identification and a system for image acquiring and identification. Features with respect to the plurality of images are recombined and enhanced so as to form a recombined image. After that, the recombined image is processed to emphasize the features of the recombined image so that the recombined image is capable of being identified easily. Furthermore, the present provides a system to perform the foregoing method, whereby reducing unidentified problems caused due to low quality image of the monitoring system.

摘要翻译： 本发明提供了一种用于多个图像和图像识别的图像复合的方法以及用于图像获取和识别的系统。 关于多个图像的特征被重新组合和增强，以便形成重组图像。 之后，重新组合的图像被处理以强调重组图像的特征，使得复合图像能够被容易地识别。 此外，本发明提供了一种执行上述方法的系统，由此减少由于监视系统的低质量图像而导致的不明身份的问题。

公开(公告)号：US08688274B2

公开(公告)日：2014-04-01

申请号：US13013690

申请日：2011-01-25

申请人： Po-Huang Shieh ,  Shang-Chieh Lu ,  Bor-Tung Jiang ,  Kuo-Tang Huang ,  Chin-Kuei Chang

发明人： Po-Huang Shieh ,  Shang-Chieh Lu ,  Bor-Tung Jiang ,  Kuo-Tang Huang ,  Chin-Kuei Chang

IPC分类号： G05B19/18 ,  G05B19/04

CPC分类号： B25J9/1692 ,  G05B2219/39045

摘要： A robot positioning method includes the following steps. A optical sensing device is configured at a front end of a robot. Then, the optical sensing device captures a calibration plate image, and a relative position of the optical sensing device with respective to a calibration plate is calculated according to a Bundle Adjustment. A robot calibration method includes the following steps. An optical sensing device is driven to rotate around a reference axis of a calibration plate, so as to calculate a translation matrix between the calibration plate and the robot, and the optical sensing device is driven to translate along three orthogonal reference axes of the calibration plate, so as to calculate a rotation matrix between the calibration plate and the robot.

摘要翻译： 机器人定位方法包括以下步骤。 光学感测装置构造在机器人的前端。 然后，光学传感装置捕获校准板图像，并且根据捆绑调整计算光学传感装置相对于校准板的相对位置。 机器人校准方法包括以下步骤。 光学感测装置被驱动以围绕校准板的参考轴线旋转，以便计算校准板和机器人之间的平移矩阵，并且光学传感装置被驱动以沿校准板的三个正交参考轴平移 ，以计算校准板和机器人之间的旋转矩阵。

公开(公告)号：US20100189364A1

公开(公告)日：2010-07-29

申请号：US12512575

申请日：2009-07-30

申请人： Ya-Hui Tsai ,  Kuo-Tang Huang ,  Yu-Ting Lin ,  Chun-Lung Chang ,  Tung-Chuan Wu

发明人： Ya-Hui Tsai ,  Kuo-Tang Huang ,  Yu-Ting Lin ,  Chun-Lung Chang ,  Tung-Chuan Wu

IPC分类号： G06K9/62

CPC分类号： G06K9/3258 ,  G06K2209/15

摘要： The present invention provides a method and system for image identification and identification result output, wherein a feature image under identification acquired from an image is compared with a plurality of sample images respectively stored in a database so as to obtain a plurality of similarity indexes associated with the plurality of sample images respectively. Each similarity index represents similarity between the feature image and the corresponding sample image. Thereafter, the plurality of similarity indexes are sorted and then a least one of comparison results is output. The present invention is further capable of being used for identifying identification marks with respect to a carrier. By sorting the similarity index with respect to each feature forming the identification marks, it is capable of outputting many sets of combinations corresponding to the identification marks so as to improve speed for targetting suspected carrier and enhance the identification efficiency.

摘要翻译： 本发明提供了一种用于图像识别和识别结果输出的方法和系统，其中将从图像获取的识别下的特征图像与分别存储在数据库中的多个样本图像进行比较，以获得与 多个样本图像。 每个相似性指数表示特征图像和相应样本图像之间的相似度。 此后，对多个相似度索引进行排序，然后输出至少一个比较结果。 本发明还能够用于识别相对于载体的识别标记。 通过对构成识别标记的每个特征进行相似性索引的排序，能够输出与识别标记对应的许多组合，从而提高针对疑似携带者的速度，提高识别效率。

公开(公告)号：US08391559B2

公开(公告)日：2013-03-05

申请号：US12512575

申请日：2009-07-30

申请人： Ya-Hui Tsai ,  Kuo-Tang Huang ,  Yu-Ting Lin ,  Chun-Lung Chang ,  Tung-Chuan Wu

发明人： Ya-Hui Tsai ,  Kuo-Tang Huang ,  Yu-Ting Lin ,  Chun-Lung Chang ,  Tung-Chuan Wu

IPC分类号： G06K9/00 ,  G06K9/03 ,  G06K9/68

CPC分类号： G06K9/3258 ,  G06K2209/15

摘要： The present invention provides a method and system for image identification and identification result output, wherein a feature image under identification acquired from an image is compared with a plurality of sample images respectively stored in a database so as to obtain a plurality of similarity indexes associated with the plurality of sample images respectively. Each similarity index represents similarity between the feature image and the corresponding sample image. Thereafter, the plurality of similarity indexes are sorted and then a least one of comparison results is output. The present invention is further capable of being used for identifying identification marks with respect to a carrier. By sorting the similarity index with respect to each feature forming the identification marks, it is capable of outputting many sets of combinations corresponding to the identification marks so as to improve speed for targeting suspected carrier and enhance the identification efficiency.

摘要翻译： 本发明提供了一种用于图像识别和识别结果输出的方法和系统，其中将从图像获取的识别下的特征图像与分别存储在数据库中的多个样本图像进行比较，以获得与 多个样本图像。 每个相似性指数表示特征图像和相应样本图像之间的相似度。 此后，对多个相似度索引进行排序，然后输出至少一个比较结果。 本发明还能够用于识别相对于载体的识别标记。 通过对构成识别标记的每个特征进行相似性索引的排序，能够输出与识别标记对应的许多组合，从而提高用于定位可疑载体的速度并提高识别效率。

公开(公告)号：US20120143370A1

公开(公告)日：2012-06-07

申请号：US13013690

申请日：2011-01-25

申请人： Po-Huang Shieh ,  Shang-Chieh Lu ,  Bor-Tung Jiang ,  Kuo-Tang Huang ,  Chin-Kuei Chang

发明人： Po-Huang Shieh ,  Shang-Chieh Lu ,  Bor-Tung Jiang ,  Kuo-Tang Huang ,  Chin-Kuei Chang

IPC分类号： B25J13/08

CPC分类号： B25J9/1692 ,  G05B2219/39045

摘要： A robot positioning method includes the following steps. A optical sensing device is configured at a front end of a robot. Then, the optical sensing device captures a calibration plate image, and a relative position of the optical sensing device with respective to a calibration plate is calculated according to a Bundle Adjustment. A robot calibration method includes the following steps. An optical sensing device is driven to rotate around a reference axis of a calibration plate, so as to calculate a translation matrix between the calibration plate and the robot, and the optical sensing device is driven to translate along three orthogonal reference axes of the calibration plate, so as to calculate a rotation matrix between the calibration plate and the robot.

摘要翻译： 机器人定位方法包括以下步骤。 光学感测装置构造在机器人的前端。 然后，光学传感装置捕获校准板图像，并且根据捆绑调整计算光学传感装置相对于校准板的相对位置。 机器人校准方法包括以下步骤。 光学感测装置被驱动以围绕校准板的参考轴线旋转，以便计算校准板和机器人之间的平移矩阵，并且光学传感装置被驱动以沿校准板的三个正交参考轴平移 ，以计算校准板和机器人之间的旋转矩阵。

公开(公告)号：US08391560B2

公开(公告)日：2013-03-05

申请号：US12512670

申请日：2009-07-30

申请人： Ya-Hui Tsai ,  Yu-Ting Lin ,  Kuo-Tang Huang ,  Chun-Lung Chang ,  Tung-Chuan Wu

发明人： Ya-Hui Tsai ,  Yu-Ting Lin ,  Kuo-Tang Huang ,  Chun-Lung Chang ,  Tung-Chuan Wu

IPC分类号： G06K9/00 ,  G06K9/62 ,  G06K9/66

CPC分类号： G06K9/3258 ,  G06K2209/15

摘要： The present invention provides a method and a system for image identification and identification result output, which determines a location coordinate with respect to an image and a rotating angle based on at least one direction of the image according to features of the image. The image is compared to a plurality of sample images stored in a database according to the rotating angle so as to obtain at least one identification result. By means of the method and the system of the present invention, identification can be achieved with respect to various rotating angles and distances so as to improve the identification rate.

摘要翻译： 本发明提供一种用于图像识别和识别结果输出的方法和系统，其根据图像的特征基于图像的至少一个方向确定相对于图像的位置坐标和旋转角度。 将图像与根据旋转角度存储在数据库中的多个样本图像进行比较，以获得至少一个识别结果。 通过本发明的方法和系统，可以针对各种旋转角度和距离来实现识别，从而提高识别率。

公开(公告)号：US20100278436A1

公开(公告)日：2010-11-04

申请号：US12512670

申请日：2009-07-30

申请人： Ya-Hui Tsai ,  Yu-Ting Lin ,  Kuo-Tang Huang ,  Chun-Lung Chang ,  Tung-Chuan Wu

发明人： Ya-Hui Tsai ,  Yu-Ting Lin ,  Kuo-Tang Huang ,  Chun-Lung Chang ,  Tung-Chuan Wu

IPC分类号： G06K9/62

CPC分类号： G06K9/3258 ,  G06K2209/15

摘要： The present invention provides a method and a system for image identification and identification result output, which determines a location coordinate with respect to an image and a rotating angle based on at least one direction of the image according to features of the image. The image is compared to a plurality of sample images stored in a database according to the rotating angle so as to obtain at least one identification result. By means of the method and the system of the present invention, identification can be achieved with respect to various rotating angles and distances so as to improve the identification rate.

摘要翻译： 本发明提供一种用于图像识别和识别结果输出的方法和系统，其根据图像的特征基于图像的至少一个方向确定相对于图像的位置坐标和旋转角度。 将图像与根据旋转角度存储在数据库中的多个样本图像进行比较，以获得至少一个识别结果。 通过本发明的方法和系统，可以针对各种旋转角度和距离来实现识别，从而提高识别率。

公开(公告)号：US09046496B2

公开(公告)日：2015-06-02

申请号：US13371060

申请日：2012-02-10

申请人： Ya-Hui Tsai ,  Kuo-Tang Huang ,  Chin-Kuei Chang ,  Chun-Lung Chang

发明人： Ya-Hui Tsai ,  Kuo-Tang Huang ,  Chin-Kuei Chang ,  Chun-Lung Chang

IPC分类号： H04N13/02 ,  H04N13/00 ,  G01N21/88 ,  G01N21/956

CPC分类号： G01N21/8806 ,  G01N21/956 ,  G01N2021/8835 ,  G01N2021/95638

摘要： A capturing method for a plurality of images with different view-angles and a capturing system using the same are provided. The capturing method for the images with different view-angles includes the following steps. An appearance image of an object is captured by an image capturing unit at a capturing angle. A light reflection area of the appearance image is detected by a detecting unit, and a dimension characteristic of the light reflection area is analyzed by the same. Whether the dimension characteristic of the light reflection area is larger than a first predetermined value is determined. If the dimension characteristic of the light reflection area is larger than the first predetermined value, then the capturing angle is adjusted within a first adjusting range. After the step of adjusting the capturing angle within a first adjusting range is performed, the step of capturing the appearance image is performed again.

摘要翻译： 提供了具有不同视角的多个图像的捕获方法和使用该捕获方法的捕获系统。 具有不同视角的图像的捕获方法包括以下步骤。 拍摄角度由图像拍摄单元拍摄物体的外观图像。 通过检测单元检测外观图像的光反射区域，并且通过该光反射区域的光反射区域的尺寸特性进行分析。 确定光反射区域的尺寸特性是否大于第一预定值。 如果光反射区域的尺寸特性大于第一预定值，则在第一调整范围内调整拍摄角度。 在执行在第一调整范围内调整拍摄角度的步骤之后，再次执行拍摄外观图像的步骤。

公开(公告)号：US20120249753A1

公开(公告)日：2012-10-04

申请号：US13371060

申请日：2012-02-10

申请人： Ya-Hui Tsai ,  Kuo-Tang Huang ,  Chin-Kuei Chang ,  Chun-Lung Chang

发明人： Ya-Hui Tsai ,  Kuo-Tang Huang ,  Chin-Kuei Chang ,  Chun-Lung Chang

IPC分类号： H04N13/02

CPC分类号： G01N21/8806 ,  G01N21/956 ,  G01N2021/8835 ,  G01N2021/95638

摘要： A capturing method for a plurality of images with different view-angles and a capturing system using the same are provided. The capturing method for the images with different view-angles includes the following steps. An appearance image of an object is captured by an image capturing unit at a capturing angle. A light reflection area of the appearance image is detected by a detecting unit, and a dimension characteristic of the light reflection area is analyzed by the same. Whether the dimension characteristic of the light reflection area is larger than a first predetermined value is determined. If the dimension characteristic of the light reflection area is larger than the first predetermined value, then the capturing angle is adjusted within a first adjusting range. After the step of adjusting the capturing angle within a first adjusting range is performed, the step of capturing the appearance image is performed again.

摘要翻译： 提供了具有不同视角的多个图像的捕获方法和使用该捕获方法的捕获系统。 具有不同视角的图像的拍摄方法包括以下步骤。 拍摄角度由图像拍摄单元拍摄物体的外观图像。 通过检测单元检测外观图像的光反射区域，并且通过该光反射区域的光反射区域的尺寸特性进行分析。 确定光反射区域的尺寸特性是否大于第一预定值。 如果光反射区域的尺寸特性大于第一预定值，则在第一调整范围内调整拍摄角度。 在执行在第一调整范围内调整拍摄角度的步骤之后，再次执行拍摄外观图像的步骤。