公开(公告)号：US08412480B2

公开(公告)日：2013-04-02

申请号：US12407106

申请日：2009-03-19

申请人： Che-Chung Lin ,  Yu-Long Wang ,  Chi-Wei Lin ,  Dau-Chen Huang ,  Yi-Yu Chang

发明人： Che-Chung Lin ,  Yu-Long Wang ,  Chi-Wei Lin ,  Dau-Chen Huang ,  Yi-Yu Chang

IPC分类号： G01C21/00

CPC分类号： G06T7/80 ,  G01S11/12 ,  G06T2207/10016 ,  G06T2207/30244 ,  G06T2207/30252

摘要： The invention provides a method for determining the angular magnitude of an imaging acquiring apparatus, which is capable of obtaining an arranging angular magnitude with respect to the imaging acquiring apparatus in various environments by an iteration algorithm having parameters of position of a calibrating tool with respect to an image coordinate system and characteristic value corresponding to a spatial coordinate system respectively. Meanwhile, the present further provides a vehicle collision warning system which functions to obtain the relative distance between the carrier and objects around according to the image acquired by the imaging acquiring apparatus and the angular magnitude and height of the imaging acquiring apparatus. By means of the method disclosed in the present invention, the procedure to detect the angular magnitude of the image acquiring apparatus is more convenient and accurate such that the convenience for using the vehicle collision warning system is capable of being improved.

摘要翻译： 本发明提供了一种用于确定成像获取装置的角度大小的方法，该方法能够通过具有校准工具的位置参数相对于每个环境的迭代算法在各种环境中获得相对于成像获取装置的排列角度大小 分别对应于空间坐标系的图像坐标系和特征值。 同时，本发明还提供了一种车辆碰撞警告系统，其具有根据由摄像装置获取的图像和摄像装置的角度大小和高度来获得载体与物体之间的相对距离。 通过本发明公开的方法，检测图像获取装置的角度大小的过程更加方便和准确，从而能够改善使用车辆碰撞警告系统的方便性。

公开(公告)号：US08411901B2

公开(公告)日：2013-04-02

申请号：US12831023

申请日：2010-07-06

申请人： Che-Chung Lin ,  Chi-Wei Lin ,  Dau-Chen Huang ,  Yu-Long Wang

发明人： Che-Chung Lin ,  Chi-Wei Lin ,  Dau-Chen Huang ,  Yu-Long Wang

IPC分类号： G06K9/00

CPC分类号： G06K9/00993 ,  G06K9/00798

摘要： The present invention provides a method and system for calculating image recognition rate, which automatically calculates the recognition rate according to recognizing result obtained from an embedded image processing system whose images are provided by an image controlling apparatus. The image controlling apparatus provides an image frame each time according to a control signal issued by the embedded image processing system. The embedded image processing system receives the image frame and recognizes the same. After a plurality of image frames are recognized, it is capable of calculating the recognition rate according to the recognizing result of the embedded image processing system and the recognition rate is capable of being utilized to be a basis for optimizing the parameters used in recognizing logic of the embedded image processing system.

摘要翻译： 本发明提供了一种计算图像识别率的方法和系统，其根据从图像控制装置提供图像的嵌入图像处理系统获得的识别结果自动计算识别率。 图像控制装置每次根据由嵌入图像处理系统发出的控制信号提供图像帧。 嵌入式图像处理系统接收图像帧并识别它们。 在识别出多个图像帧之后，能够根据嵌入图像处理系统的识别结果来计算识别率，并且识别率能够被用作基础，用于优化在识别逻辑中使用的参数 嵌入式图像处理系统。

公开(公告)号：US20110158480A1

公开(公告)日：2011-06-30

申请号：US12831023

申请日：2010-07-06

申请人： Che-Chung Lin ,  Chi-Wei Lin ,  Dau-Chen Huang ,  Yu-Long Wang

发明人： Che-Chung Lin ,  Chi-Wei Lin ,  Dau-Chen Huang ,  Yu-Long Wang

IPC分类号： G06K9/36 ,  G06K9/46

CPC分类号： G06K9/00993 ,  G06K9/00798

摘要： The present invention provides a method and system for calculating image recognition rate, which automatically calculates the recognition rate according to recognizing result obtained from an embedded image processing system whose images are provided by an image controlling apparatus. The image controlling apparatus provides an image frame each time according to a control signal issued by the embedded image processing system. The embedded image processing system receives the image frame and recognizes the same. After a plurality of image frames are recognized, it is capable of calculating the recognition rate according to the recognizing result of the embedded image processing system and the recognition rate is capable of being utilized to be a basis for optimizing the parameters used in recognizing logic of the embedded image processing system.

摘要翻译： 本发明提供了一种计算图像识别率的方法和系统，其根据从图像控制装置提供图像的嵌入图像处理系统获得的识别结果自动计算识别率。 图像控制装置每次根据由嵌入图像处理系统发出的控制信号提供图像帧。 嵌入式图像处理系统接收图像帧并识别它们。 在识别出多个图像帧之后，能够根据嵌入图像处理系统的识别结果来计算识别率，并且识别率能够被用作基础来优化用于识别逻辑的识别逻辑 嵌入式图像处理系统。

公开(公告)号：US08687063B2

公开(公告)日：2014-04-01

申请号：US12019936

申请日：2008-01-25

申请人： Hsi-Wen Hsieh ,  Yung-Sheng Liao ,  Che-Chung Lin ,  Chi-Wei Lin ,  Dau-Chen Huang

发明人： Hsi-Wen Hsieh ,  Yung-Sheng Liao ,  Che-Chung Lin ,  Chi-Wei Lin ,  Dau-Chen Huang

IPC分类号： H04N7/18 ,  H04N7/00

CPC分类号： G08G1/167 ,  B60Q9/008 ,  G06K9/00798

摘要： A method for predicting lane line is provided in the present invention, in which the method is capable of predicting and reconstructing the unidentified lane line according to a predetermined geometry relationship based on the recognized lane line data previously while one side of lane line is unable to be identified. In one embodiment, a lane predicting relationship formula is formed by describing the geometry relationship between the two identified lines defined the lane. When the one side of line of the lane is unable to be identified, a new predicted line can be reconstructed for representing the unidentified line of lane according to the lane predicting relationship curve. In another embodiment, a lane departure warning system utilizing the foregoing method is provided for monitoring vehicle moving status and alerting the driver so as to enhance the vehicle safety.

摘要翻译： 在本发明中提供了一种用于预测车道线的方法，其中该方法能够根据预先确定的车道线数据根据预定的几何关系来预测和重建不明车道线，同时车道线的一侧不能 被确定。 在一个实施例中，通过描述定义车道的两条识别线之间的几何关系来形成车道预测关系公式。 当车道的一侧不能被识别时，可以根据车道预测关系曲线重建新的预测线，以表示车道的不明线。 在另一个实施例中，提供了一种利用上述方法的车道偏离警报系统，用于监视车辆运动状态并提醒驾驶员以增强车辆的安全性。

公开(公告)号：US08903638B2

公开(公告)日：2014-12-02

申请号：US13480070

申请日：2012-05-24

申请人： Che-Chung Lin ,  Yu-Chen Lin ,  Ming-Jen Tu ,  Li-Fen Liu

发明人： Che-Chung Lin ,  Yu-Chen Lin ,  Ming-Jen Tu ,  Li-Fen Liu

IPC分类号： G06F17/10 ,  G08G1/0962 ,  G06K9/00 ,  G06K9/20 ,  B60Q9/00 ,  H04N7/18

CPC分类号： G08G1/0962 ,  B60Q9/008 ,  G06K9/00791 ,  G06K9/00798 ,  G06K9/00825 ,  G06K9/2054 ,  H04N7/18

摘要： A warning method and system for detecting lane-changing condition of rear-approaching vehicles are disclosed, in which the method comprises the steps of: detecting rear-view images of an ego-vehicle so as to be used for defining three regions of interest (ROI) corresponding respectively to a lane to the left of the ego-vehicle, a lane to the right of the ego-vehicle, and a lane where the ego-vehicle is travelling thereon; detecting whether there is any direction light that is flashing to be used as basis for determining whether there is any vehicle approaching from the rear that is expected to be a potential threat to the ego-vehicle; and if so, issuing an alarm signal to the driver of the ego-vehicle for reminding the same to aware the distance between the ego-vehicle and the rear-approaching vehicle. Thereby, the driver's road environment awareness is enhanced and consequently the safety of driving can be improved.

摘要翻译： 公开了一种用于检测后方车辆的车道变化状态的警报方法和系统，其中，所述方法包括以下步骤：检测自动车辆的后视图像，以便用于定义三个感兴趣的区域 ROI）分别对应于自动车辆左侧的车道，自动车辆右侧的车道以及自行车辆在其上行驶的车道; 检测是否有任何闪烁的方向指示灯用作确定是否有任何车辆从后方接近预期是对自我车辆的潜在威胁的基础; 如果是这样，则向自动车辆的驾驶员发出警报信号，以提醒自己，以意识到自动车辆和后方车辆之间的距离。 从而提高驾驶员的道路环境意识，从而可以提高驾驶的安全性。