公开(公告)号：US08442117B2

公开(公告)日：2013-05-14

申请号：US13170736

申请日：2011-06-28

申请人： Jiann-Der Lee ,  Hao-Hang Hsu

发明人： Jiann-Der Lee ,  Hao-Hang Hsu

IPC分类号： H04N7/12

CPC分类号： H04N19/533

摘要： Motion estimation is efficient to reduce redundant information among successive frames in video compression applications. The blocks in the current frame can be replaced with the neighboring blocks in the spatial directions in the previous frame with small errors. Many types of motion estimation methods such as Block Matching Algorithm are widely used to take a balance between a good image quality and the computation complexity. A Block Matching Algorithm named as New Cellular Search (NCS) Algorithm utilizes two particular search patterns: HCSP and VCSP, in the horizontal and vertical directions to search the best motion vector. Three performance measurements including peak signal to noise ration (PSNR), Average Search Point (ASP), and Mean Square Error (MSE) are used to compare this new search algorithm with some major motion estimations like FS, TSS, CS, and NCDS. The NCS is very efficient in computation reduction while keeping the almost same picture quality.

摘要翻译： 运动估计在视频压缩应用中在连续帧之间减少冗余信息是有效的。 当前帧中的块可以用前一帧的空间方向上的相邻块替换为小错误。 许多类型的运动估计方法如块匹配算法被广泛用于在良好的图像质量和计算复杂度之间取得平衡。 名为新蜂窝搜索（NCS）算法的块匹配算法利用两种特定的搜索模式：HCSP和VCSP，在水平和垂直方向上搜索最佳运动矢量。 使用三个性能测量，包括峰值信噪比（PSNR），平均搜索点（ASP）和均方误差（MSE），以将这种新的搜索算法与诸如FS，TSS，CS和NCDS之类的一些主要运动估计进行比较。 NCS在减少计算中非常有效，同时保持几乎相同的图像质量。

公开(公告)号：US08200355B2

公开(公告)日：2012-06-12

申请号：US12645890

申请日：2009-12-23

申请人： Shih Tseng Lee ,  Yu-Te Wu ,  Yuan-Lin Liao ,  Chia-Feng Lu ,  Jiann-Der Lee

发明人： Shih Tseng Lee ,  Yu-Te Wu ,  Yuan-Lin Liao ,  Chia-Feng Lu ,  Jiann-Der Lee

IPC分类号： G06F19/00

CPC分类号： G06T17/00 ,  G05B2219/45172 ,  G05B2219/49008 ,  G06T3/0068 ,  G06T7/32 ,  G06T2207/10072 ,  G06T2207/30016

摘要： The present invention relates to a method for manufacturing artificial implants, comprising 1) acquiring the pre-operation three dimensional volume image and the post-operation three dimensional volume image of the operation portion, thereby respectively producing the pre-operation target image and the post-operation target image including the target; 2) aligning the pre-operation target image with the post-operation target image so as to generate the aligned image; 3) acquiring the difference image of the incised part in the target based on the aligned image; 4) building the three dimensional model of mold points of the incised part based on the difference image; and 5) manufacturing the artificial implant having the same shape with the incised part based on such three dimensional model of mold points.

摘要翻译： 本发明涉及一种人造植入物的制造方法，其特征在于，包括：1）获取所述手术部的所述手术前三维体积图像和所述手术后三维体积图像，分别生成所述手术前图像和所述贴片 包括目标的操作目标图像; 2）使所述操作前目标图像与所述术后目标图像对准，以便生成所述对准图像; 3）基于对准的图像获取目标中的切割部分的差分图像; 4）基于差异图像构建切口部分的模具点的三维模型; 以及5）基于模具点的这种三维模型来制造具有与切口部分相同形状的人造植入物。

公开(公告)号：US07426237B2

公开(公告)日：2008-09-16

申请号：US10863025

申请日：2004-06-08

申请人： Jiann-Der Lee ,  Su-Yen Wang

发明人： Jiann-Der Lee ,  Su-Yen Wang

IPC分类号： H04N7/12 ,  G06K9/36

CPC分类号： H04N19/533 ,  G06T7/238 ,  H04N5/145

摘要： An algorithm for decreasing the number of unnecessary checkpoints in the cellular search includes first and second search ways of each of the processes. All the first search ways are the same, and the second search ways are classified to different search modes by an algorithm. The first search ways and the second search ways are continually consecutively actuated and stopped when obtaining a broken condition or finding a best block-matching, and a best motion vector is obtained.

摘要翻译： 用于减少蜂窝搜索中的不必要的检查点的数量的算法包括每个处理的第一和第二搜索方式。 所有的第一搜索方式都是相同的，第二种搜索方式通过算法分类到不同的搜索模式。 当获得破坏的条件或找到最佳块匹配时，第一搜索方式和第二搜索方式被不断连续地启动和停止，并且获得最佳运动矢量。

公开(公告)号：US20070223587A1

公开(公告)日：2007-09-27

申请号：US11389718

申请日：2006-03-27

申请人： Jiann-Der Lee ,  Hao-Hang Hsu

发明人： Jiann-Der Lee ,  Hao-Hang Hsu

IPC分类号： H04N11/02 ,  H04B1/66

CPC分类号： H04N19/533

摘要： Motion estimation is efficient to reduce redundant information among successive frames in video compression applications. The blocks in the current frame can be replaced with the neighboring blocks in the spatial directions in the previous frame with small errors. Many types of motion estimation methods such as Block matching algorithm are widely used to take a balance between a good image quality and the computation complexity. A block matching algorithm named as New Cellular Search Algorithm utilizes two particular search patterns: HCSP and VCSP, in the horizontal and vertical directions to search the best motion vector. Three performance measurements including PSNR), ASP, and MAE are used to compare this new search algorithm with some major motion estimations like FS, TSS, CS, and NCDS. The FCS is very efficient in computation reduction while keeping the almost same picture quality.

摘要翻译： 运动估计在视频压缩应用中在连续帧之间减少冗余信息是有效的。 当前帧中的块可以用前一帧的空间方向上的相邻块替换为小错误。 许多类型的运动估计方法，如块匹配算法被广泛用于在良好的图像质量和计算复杂度之间取得平衡。 称为新蜂窝搜索算法的块匹配算法使用两种特定的搜索模式：HCSP和VCSP，在水平和垂直方向上搜索最佳运动矢量。 使用三个性能测量，包括PSNR），ASP和MAE来比较这种新的搜索算法与一些主要的运动估计，如FS，TSS，CS和NCDS。 FCS在减少计算中非常有效，同时保持几乎相同的图像质量。

公开(公告)号：US06574356B1

公开(公告)日：2003-06-03

申请号：US09552083

申请日：2000-04-19

申请人： Jiann-Der Lee ,  Shih-Tsang Lee ,  Chi-Shun Chang

发明人： Jiann-Der Lee ,  Shih-Tsang Lee ,  Chi-Shun Chang

IPC分类号： G06K900

CPC分类号： G06T11/008 ,  G06T7/12 ,  G06T2207/10081 ,  G06T2207/20064 ,  G06T2207/20128 ,  G06T2207/30016

摘要： The present invention relates to a method for three-dimensional image reconstruction of basal ganglion. A novel geometrical algorithm has been developed to calculate the correction coordinates of the target based on the reference axial shift in the CT scan coordinate system. Furthermore, wavelet transform along with interpolation techniques are used to obtain continuous sectional images and three-dimensional image reconstruction is then performed to form the stereotactic atlas of basal ganglion. Therefore, the stereotactic atlas of basal ganglion established in this invention can be used as references for assisting operation and training for neurosurgeons.

摘要翻译： 本发明涉及一种基础神经节三维图像重建方法。 已经开发了一种新颖的几何算法，用于基于CT扫描坐标系中的参考轴向移位来计算目标的校正坐标。 此外，使用小波变换以及插值技术来获得连续的截面图像，然后进行三维图像重建以形成基底神经节的立体定向图谱。 因此，本发明中建立的基底神经节的立体定位图可用作辅助神经外科医师的操作和训练的参考。

公开(公告)号：US20110255604A1

公开(公告)日：2011-10-20

申请号：US13170736

申请日：2011-06-28

申请人： Jiann-Der Lee ,  Hao-Hang Hsu

发明人： Jiann-Der Lee ,  Hao-Hang Hsu

IPC分类号： H04N7/26

CPC分类号： H04N19/533

摘要： Motion estimation is efficient to reduce redundant information among successive frames in video compression applications. The blocks in the current frame can be replaced with the neighboring blocks in the spatial directions in the previous frame with small errors. Many types of motion estimation methods such as Block Matching Algorithm are widely used to take a balance between a good image quality and the computation complexity. A Block Matching Algorithm named as New Cellular Search (NCS) Algorithm utilizes two particular search patterns: HCSP and VCSP, in the horizontal and vertical directions to search the best motion vector. Three performance measurements including peak signal to noise ration (PSNR), Average Search Point (ASP), and Mean Square Error (MSE) are used to compare this new search algorithm with some major motion estimations like FS, TSS, CS, and NCDS. The NCS is very efficient in computation reduction while keeping the almost same picture quality.

摘要翻译： 运动估计在视频压缩应用中在连续帧之间减少冗余信息是有效的。 当前帧中的块可以用前一帧的空间方向上的相邻块替换为小错误。 许多类型的运动估计方法如块匹配算法被广泛用于在良好的图像质量和计算复杂度之间取得平衡。 名为新蜂窝搜索（NCS）算法的块匹配算法利用两种特定的搜索模式：HCSP和VCSP，在水平和垂直方向上搜索最佳运动矢量。 使用三个性能测量，包括峰值信噪比（PSNR），平均搜索点（ASP）和均方误差（MSE），以将这种新的搜索算法与诸如FS，TSS，CS和NCDS之类的一些主要运动估计进行比较。 NCS在减少计算中非常有效，同时保持几乎相同的图像质量。

公开(公告)号：US20080230297A1

公开(公告)日：2008-09-25

申请号：US11902140

申请日：2007-09-19

申请人： Jiann-Der Lee ,  Li-Chang Liu ,  Jiann-Der Li

发明人： Jiann-Der Lee ,  Li-Chang Liu ,  Jiann-Der Li

IPC分类号： G06F19/00

CPC分类号： B60W40/08 ,  B60W50/14 ,  B60W2420/42

摘要： An intelligent driving safety monitoring system capable of integrating multiple direction information is adapted to be installed in a vehicle. The system includes a first image capturing device, a second image capturing device, a data processing device, and an indicating device. The first image capturing device is used to capture a face image of a driver of the vehicle. The second image capturing device is used to capture a front lane image. The data processing device, after doing computations based on the face image of the driver and the front lane image, maps a sight direction of the driver and a mid-line of lane into a global coordinate space and integrates the same into multiple direction information. The indicating device outputs the multiple direction information to the driver for suggesting whether driving status of the driver is safe.

摘要翻译： 能够集成多方向信息的智能驾驶安全监控系统适于安装在车辆中。 该系统包括第一图像捕获装置，第二图像捕获装置，数据处理装置和指示装置。 第一图像捕获装置用于捕获车辆驾驶员的脸部图像。 第二图像捕获装置用于捕获前车道图像。 数据处理装置在基于驾驶员的脸部图像和前车道图像进行计算之后，将驾驶员的视线方向和车道中线映射到全局坐标空间中并将其整合到多个方向信息中。 指示装置向驾驶员输出多方向信息，以提示驾驶员的驾驶状态是否安全。

公开(公告)号：US20050271143A1

公开(公告)日：2005-12-08

申请号：US10863025

申请日：2004-06-08

申请人： Jiann-Der Lee ,  Su-Yen Wang

发明人： Jiann-Der Lee ,  Su-Yen Wang

IPC分类号： G06T7/20 ,  H04N5/14 ,  H04N7/12

CPC分类号： H04N19/533 ,  G06T7/238 ,  H04N5/145

摘要： An algorithm for decreasing the number of the unnecessary checkpoints in the cellular search includes a first and second search ways of each of the processes of the present invention. All the first search ways are same and the second search ways are classified to different search modes by algorithm. The first search ways and the second ways are continually consecutively actuated, and stop when obtaining a broken condition or find a best block-matching, and obtain a best motion vector.

摘要翻译： 用于减少蜂窝搜索中的不必要的检查点的数量的算法包括本发明的每个处理的第一和第二搜索方式。 所有的第一搜索方式是相同的，第二种搜索方式通过算法分类到不同的搜索模式。 第一种搜索方式和第二种方式不断连续地启动，当获得破坏条件或找到最佳块匹配时停止，并获得最佳运动矢量。

公开(公告)号：US20110054656A1

公开(公告)日：2011-03-03

申请号：US12645890

申请日：2009-12-23

申请人： Shih Tseng Lee ,  Yu-Te Wu ,  Yuan-Lin Liao ,  Chia-Feng Lu ,  Jiann-Der Lee

发明人： Shih Tseng Lee ,  Yu-Te Wu ,  Yuan-Lin Liao ,  Chia-Feng Lu ,  Jiann-Der Lee

IPC分类号： G06F19/00

CPC分类号： G06T17/00 ,  G05B2219/45172 ,  G05B2219/49008 ,  G06T3/0068 ,  G06T7/32 ,  G06T2207/10072 ,  G06T2207/30016

摘要： The present invention relates to a method for manufacturing artificial implants, comprising 1) acquiring the pre-operation three dimensional volume image and the post-operation three dimensional volume image of the operation portion, thereby respectively producing the pre-operation target image and the post-operation target image including the target; 2) aligning the pre-operation target image with the post-operation target image so as to generate the aligned image; 3) acquiring the difference image of the incised part in the target based on the aligned image; 4) building the three dimensional model of mold points of the incised part based on the difference image; and 5) manufacturing the artificial implant having the same shape with the incised part based on such three dimensional model of mold points.

摘要翻译： 本发明涉及一种人造植入物的制造方法，其特征在于，包括：1）获取所述手术部的所述手术前三维体积图像和所述手术后三维体积图像，分别产生所述手术前图像和所述贴片 包括目标的操作目标图像; 2）使所述操作前目标图像与所述术后目标图像对准，以便生成所述对准图像; 3）基于对准的图像获取目标中的切割部分的差分图像; 4）基于差异图像构建切口部分的模具点的三维模型; 以及5）基于模具点的这种三维模型来制造具有与切口部分相同形状的人造植入物。

公开(公告)号：US07826964B2

公开(公告)日：2010-11-02

申请号：US11902140

申请日：2007-09-19

申请人： Jiann-Der Lee ,  Li-Chang Liu ,  Jiann-Der Li

发明人： Jiann-Der Lee ,  Li-Chang Liu ,  Jiann-Der Li

IPC分类号： G06F19/00

CPC分类号： B60W40/08 ,  B60W50/14 ,  B60W2420/42

摘要： An intelligent driving safety monitoring system capable of integrating multiple direction information is adapted to be installed in a vehicle. The system includes a first image capturing device, a second image capturing device, a data processing device, and an indicating device. The first image capturing device is used to capture a face image of a driver of the vehicle. The second image capturing device is used to capture a front lane image. The data processing device, after doing computations based on the face image of the driver and the front lane image, maps a sight direction of the driver and a mid-line of lane into a global coordinate space and integrates the same into multiple direction information. The indicating device outputs the multiple direction information to the driver for suggesting whether driving status of the driver is safe.

摘要翻译： 能够集成多方向信息的智能驾驶安全监控系统适于安装在车辆中。 该系统包括第一图像捕获装置，第二图像捕获装置，数据处理装置和指示装置。 第一图像捕获装置用于捕获车辆驾驶员的脸部图像。 第二图像捕获装置用于捕获前车道图像。 数据处理装置在基于驾驶员的脸部图像和前车道图像进行计算之后，将驾驶员的视线方向和车道中线映射到全局坐标空间中并将其整合到多个方向信息中。 指示装置向驾驶员输出多方向信息，以提示驾驶员的驾驶状态是否安全。