公开(公告)号：US07813527B2

公开(公告)日：2010-10-12

申请号：US11669942

申请日：2007-01-31

申请人： Wen-Hao Wang

发明人： Wen-Hao Wang

IPC分类号： G06K9/00

CPC分类号： G06K9/6297

摘要： Disclosed is an object detection method and system in an image plane. A Hidden Markov Model (HMM) is employed and its associated parameters are initialized for an image plane. Updating HMM parameters is accomplished by referring to the previous estimated object mask in a spatial domain. With the updated HMM parameters and a decoding algorithm, a refined state sequence is obtained and a better object mask is restored from the refined state sequence. Consequently, estimation of the HMM parameters can be rapidly achieved and robust object detection can be effected. This allows the resultant object mask to be closer to the real object area, and the false detection in the background area can be decreased.

摘要翻译： 公开了一种图像平面中的物体检测方法和系统。 使用隐马尔可夫模型（HMM），并将其相关参数初始化为图像平面。 通过参考空间域中的先前估计的对象掩码来实现更新HMM参数。 利用更新的HMM参数和解码算法，获得精细的状态序列，并从精细状态序列恢复更好的对象掩码。 因此，可以快速实现HMM参数的估计，并且可以实现鲁棒的物体检测。 这允许所得到的对象掩模更靠近真实对象区域，并且可以减少背景区域中的错误检测。

公开(公告)号：US20090129629A1

公开(公告)日：2009-05-21

申请号：US12016207

申请日：2008-01-18

申请人： Po-Feng Cheng ,  Wen-Hao Wang

发明人： Po-Feng Cheng ,  Wen-Hao Wang

IPC分类号： G06K9/00

CPC分类号： G06K9/00234 ,  G06K9/00369

摘要： Disclosed is a method and apparatus for adaptive object detection, which may be applied in detecting an object having an ellipse feature. The method for adaptive object detection comprises performing an object shape detection based on the extracted foreground from the object; determining whether the object being occluded according to the detected feature statistic information of the object; if the object being not occluded, determining whether to switching object shape detection to ellipse detection; if the object being occluded or necessary to switch to ellipse detection, performing ellipse detection on the foreground; when the foreground being detected to have ellipse features, the object is continuously tracked; and when the current detection being ellipse detection, determining whether the ellipse detection being able to switch back to object shape detection.

摘要翻译： 公开了一种用于自适应对象检测的方法和装置，其可以应用于检测具有椭圆特征的对象。 用于自适应对象检测的方法包括基于从对象提取的前景执行对象形状检测; 根据检测到的对象的特征量统计信息确定对象是否被遮挡; 如果对象不被遮挡，则确定是否将对象形状检测切换到椭圆检测; 如果对象被遮挡或需要切换到椭圆检测，则在前景执行椭圆检测; 当检测到前景具有椭圆特征时，对象被连续跟踪; 并且当当前检测是椭圆检测时，确定椭圆检测是否能切换回对象形状检测。

公开(公告)号：US20080118889A1

公开(公告)日：2008-05-22

申请号：US11602358

申请日：2006-11-21

申请人： Wen-Hao Wang

发明人： Wen-Hao Wang

IPC分类号： A61C1/12 ,  A61C1/02

CPC分类号： A61C1/0061

摘要： The present invention discloses an auxiliary cooling water supplier for a dental implant device, which comprises a main machine having a built-in water-supply module, a conduit, an outlet module, a flowrate control circuit and a pedal. The main machine further comprises a control unit; the control unit is connected to the flowrate control circuit, and the flowrate control circuit is connected to the water-supply module. The user can use the control unit to regulate the flowrate of the outlet module or to switch between an automatic water-supply mode and a pedal control mode. The auxiliary cooling water supplier for a dental implant device of the present invention has the advantages of lightweight, portability, maneuverability, simple structure and easy operation.

摘要翻译： 本发明公开了一种用于牙种植体装置的辅助冷却水供应器，其包括具有内置供水模块，导管，出口模块，流量控制回路和踏板的主机。 主机还包括控制单元; 控制单元连接到流量控制电路，并且流量控制电路连接到供水模块。 用户可以使用控制单元来调节出口模块的流量或者在自动供水模式和踏板控制模式之间切换。 本发明的牙科植入装置的辅助冷却水供给装置具有重量轻，便于携带，机动性好，结构简单，操作简便的优点。

公开(公告)号：US20080108010A1

公开(公告)日：2008-05-08

申请号：US11593555

申请日：2006-11-07

申请人： Wen-Hao Wang

发明人： Wen-Hao Wang

IPC分类号： A61C1/00

CPC分类号： A61C1/088

摘要： The present invention discloses an illuminator for a dental drill, which comprises a body having a front end and a rear end and having an accommodation room thereinside, a drill installed at the front end of the body, and an illuminator having a light-emitting diode (LED). The body further has an opening-located portion, and the opening-located portion has a through-hole. The LED is installed in the through-hole and has a light-emitting portion facing outward from the through-hole. The present invention adopts a LED as the light source and is simpler and cheaper than the conventional illuminator using an electric bulb or optical fibers.

摘要翻译： 本发明公开了一种用于牙科钻头的照明器，其包括具有前端和后端的主体，其内部具有容纳室，安装在身体前端的钻头和具有发光二极管的照明器 （LED）。 主体还具有开口部，开口部具有通孔。 LED安装在通孔中，并且具有从通孔向外的发光部。 本发明采用LED作为光源，并且比使用电灯泡或光纤的常规照明器更简单和便宜。

公开(公告)号：US20080101653A1

公开(公告)日：2008-05-01

申请号：US11669942

申请日：2007-01-31

申请人： Wen-Hao Wang

发明人： Wen-Hao Wang

IPC分类号： G06K9/00 ,  G06K9/62

CPC分类号： G06K9/6297

摘要： Disclosed is an object detection method and system in an image plane. A Hidden Markov Model (HMM) is employed and its associated parameters are initialized for an image plane. Updating HMM parameters is accomplished by referring to the previous estimated object mask in a spatial domain. With the updated HMM parameters and a decoding algorithm, a refined state sequence is obtained and a better object mask is restored from the refined state sequence. Consequently, estimation of the HMM parameters can be rapidly achieved and robust object detection can be effected. This allows the resultant object mask to be closer to the real object area, and the false detection in the background area can be decreased.

摘要翻译： 公开了一种图像平面中的物体检测方法和系统。 使用隐马尔可夫模型（HMM），并将其相关参数初始化为图像平面。 通过参考空间域中的先前估计的对象掩码来实现更新HMM参数。 利用更新的HMM参数和解码算法，获得精细的状态序列，并从精细状态序列恢复更好的对象掩码。 因此，可以快速实现HMM参数的估计，并且可以实现鲁棒的物体检测。 这允许所得到的对象掩模更靠近真实对象区域，并且可以减少背景区域中的错误检测。

公开(公告)号：US20080079721A1

公开(公告)日：2008-04-03

申请号：US11889590

申请日：2007-08-15

申请人： Fu-Jen Hsiao ,  Wen-Hao Wang ,  Tsu-Han Chen ,  Wen-De Zhang

发明人： Fu-Jen Hsiao ,  Wen-Hao Wang ,  Tsu-Han Chen ,  Wen-De Zhang

IPC分类号： G06T15/00

CPC分类号： G06T17/00 ,  G06T7/579 ,  G06T2200/08 ,  G06T2207/10016

摘要： A method for corresponding, evolving and tracking feature points in a three-dimensional space performs corresponding, evolving and tracking on the features points after transferring the two-dimensional feature point information in an image information into a corresponding state in the three-dimensional space. A recursion is employed to continuously update the states of the feature points in the three-dimensional space and evaluate the stability of the feature points by evolving. Hence, the obtained three-dimensional feature point information has a stronger corresponding relationship than the feature point information conventionally generated on the basis of the two-dimensional feature point information. As a result, a more precise three-dimensional scene can then be constructed.

摘要翻译： 用于在三维空间中对应，演进和跟踪特征点的方法在将图像信息中的二维特征点信息转换成三维空间中的对应状态之后，对特征点执行相应的，演进和跟踪。 采用递归来不断更新三维空间中特征点的状态，并通过演化来评估特征点的稳定性。 因此，获得的三维特征点信息具有比基于二维特征点信息常规生成的特征点信息更强的对应关系。 因此，可以构建更精确的三维场景。

公开(公告)号：US06650707B2

公开(公告)日：2003-11-18

申请号：US09796600

申请日：2001-03-02

申请人： Jeongnam Youn ,  Ming-Ting Sun ,  Chia-Wen Lin ,  Wen-Hao Wang

发明人： Jeongnam Youn ,  Ming-Ting Sun ,  Chia-Wen Lin ,  Wen-Hao Wang

IPC分类号： H04N712

CPC分类号： H04N19/59 ,  H04N19/126 ,  H04N19/132 ,  H04N19/176 ,  H04N19/18 ,  H04N19/40 ,  H04N19/61 ,  H04N19/91

摘要： A transcoder for transcoding digital video signals includes a decoder and an encoder. In the decoder, an end-of-block (EOB) position of an incoming block received by the decoder is determined and a discrete cosine transform (DCT) block type is determined based on the determined EOB position. A reduced number of DCT coefficients is computed in a subsequent inverse DCT computation based on the DCT block type. In the encoder, if the incoming block is intercoded, no DCT coefficients are computed after the EOB of the incoming blocks is performing a DCT. Further, in the encoder when the incoming block is intercoded, an algorithm is applied to predict which DCT coefficients may become zero after a subsequent quantization operation, and only DCT coefficients that may not become zero are computed in performing the DCT.

摘要翻译： 用于对数字视频信号进行代码转换的代码转换器包括解码器和编码器。 在解码器中，确定由解码器接收的输入块的块结束位置（EOB），并且基于所确定的EOB位置来确定离散余弦变换（DCT）块类型。 基于DCT块类型在后续的逆DCT计算中计算减少数量的DCT系数。 在编码器中，如果输入块被相互编码，则在输入块的EOB执行DCT之后不计算DCT系数。 此外，在输入块被编码时的编码器中，应用算法来预测在后续量化操作之后哪些DCT系数可能变为零，并且在执行DCT时仅计算可能不变为零的DCT系数。

公开(公告)号：US08472717B2

公开(公告)日：2013-06-25

申请号：US12651376

申请日：2009-12-31

申请人： Wen-Hao Wang ,  Tai-Hui Huang

发明人： Wen-Hao Wang ,  Tai-Hui Huang

IPC分类号： G06K9/34

CPC分类号： H04N9/735 ,  G06T7/194 ,  G06T7/215

摘要： A foreground image separation method is disclosed to separate dynamic foreground and static background in a sequence of input images which have been processed either with automatic white balance or brightness control by the camera. First, an input image is received from the camera, and then a white balance or brightness compensation is performed to the input image according to a reference image to generate a compensated image with background color and background brightness which are approximately similar to that of the reference image. Finally, a background subtraction algorithm is performed to the compensated image to generate a background separation result. The background subtraction algorithm could be a Gaussian Mixture Model based algorithm. The method could process successive images received from the camera to continuously generate background separation results and update the reference image accordingly, such that video surveillance system could adapt to the change of illumination.

摘要翻译： 公开了一种前景图像分离方法，用于在经过相机的自动白平衡或亮度控制处理的输入图像序列中分离动态前景和静态背景。 首先，从相机接收输入图像，然后根据参考图像对输入图像执行白平衡或亮度补偿，以产生具有与参考图像大致相似的背景颜色和背景亮度的补偿图像 图片。 最后，对补偿图像执行背景减法算法以产生背景分离结果。 背景减法算法可以是基于高斯混合模型的算法。 该方法可以处理从相机接收的连续图像，以连续生成背景分离结果，并相应地更新参考图像，使得视频监控系统能够适应照明的变化。

公开(公告)号：US20120154580A1

公开(公告)日：2012-06-21

申请号：US13086178

申请日：2011-04-13

申请人： Tai-Hui Huang ,  Tsung-Chan Li ,  Wen-Hao Wang

发明人： Tai-Hui Huang ,  Tsung-Chan Li ,  Wen-Hao Wang

IPC分类号： G06K9/00 ,  H04N7/18

CPC分类号： G06T7/2006 ,  G06T7/136 ,  G06T7/194 ,  G06T7/215

摘要： A moving object detection method and an image processing system thereof are provided. First, a pixel-wise distance of a received image to a reference image is computed to obtain a distance map. A histogram analysis is performed on the distance map to obtain a distance distribution. An entropy value of the distance distribution is computed and a peak distance value which is with a maximum occurrence probability in the distance distribution is searched out. Then, by using a mapping rule, the entropy value and the peak distance value are transformed into a decision threshold value. The decision threshold value is applied in classifying the pixels of the distance map into a group of foreground attributes and a group of background attributes and thereby moving objects in the current image are obtained.

摘要翻译： 提供了一种移动物体检测方法及其图像处理系统。 首先，计算接收到的图像与参考图像的像素距离，以获得距离图。 对距离图进行直方图分析以获得距离分布。 计算距离分布的熵值，并搜索距离分布中具有最大出现概率的峰值距离值。 然后，通过使用映射规则，将熵值和峰值距离值变换为判定阈值。 应用判定阈值将距离图像的像素分类为一组前景属性和一组背景属性，从而获得当前图像中的移动物体。

公开(公告)号：US08922651B2

公开(公告)日：2014-12-30

申请号：US13086178

申请日：2011-04-13

申请人： Tai-Hui Huang ,  Tsung-Chan Li ,  Wen-Hao Wang

发明人： Tai-Hui Huang ,  Tsung-Chan Li ,  Wen-Hao Wang

IPC分类号： G06T7/20

CPC分类号： G06T7/2006 ,  G06T7/136 ,  G06T7/194 ,  G06T7/215

摘要： A moving object detection method and an image processing system thereof are provided. First, a pixel-wise distance of a received image to a reference image is computed to obtain a distance map. A histogram analysis is performed on the distance map to obtain a distance distribution. An entropy value of the distance distribution is computed and a peak distance value which is with a maximum occurrence probability in the distance distribution is searched out. Then, by using a mapping rule, the entropy value and the peak distance value are transformed into a decision threshold value. The decision threshold value is applied in classifying the pixels of the distance map into a group of foreground attributes and a group of background attributes and thereby moving objects in the current image are obtained.

摘要翻译： 提供了一种移动物体检测方法及其图像处理系统。 首先，计算接收到的图像与参考图像的像素距离，以获得距离图。 对距离图进行直方图分析以获得距离分布。 计算距离分布的熵值，并搜索距离分布中具有最大出现概率的峰值距离值。 然后，通过使用映射规则，将熵值和峰值距离值变换为判定阈值。 应用判定阈值将距离图像的像素分类为一组前景属性和一组背景属性，从而获得当前图像中的移动物体。