-
公开(公告)号：KR1020120019661A
公开(公告)日：2012-03-07
申请号：KR1020100082996
申请日：2010-08-26
Applicant: 아주대학교산학협력단
Abstract: PURPOSE: An object tracing robot and a method thereof are provided to maintain a fixed distance from an object being traced by controlling a drive motor using information on the distance to the object. CONSTITUTION: An object tracing robot comprises a camera(1), a laser sensor(2), an RF receiver(3), and a control unit(4). The camera photographs an object or a marker of the object. The RF receiver receives RFID information from an RFID tag of the object. The laser sensor receives a laser signal. The control unit confirms the object using one among the object image and marker image from the camera and the RFID information received from the RFID tag, calculates the distance to the object using the laser signal received by the laser sensor, and controls a drive motor to maintain a fixed distance from the object.
Abstract translation: 目的：提供一种物体跟踪机器人及其方法，通过使用关于到物体的距离的信息来控制驱动马达来保持与被跟踪物体的固定距离。 构成：物体跟踪机器人包括照相机（1），激光传感器（2），RF接收器（3）和控制单元（4）。 相机拍摄对象或对象的标记。 RF接收机从对象的RFID标签接收RFID信息。 激光传感器接收激光信号。 控制单元使用来自摄像机的对象图像和标记图像之一以及从RFID标签接收到的RFID信息中的一个来确认对象，使用由激光传感器接收的激光信号计算与对象的距离，并且控制驱动电动机 保持与物体的距离。
-
Patent Agency Ranking
公开(公告)号：KR1020120002358A
公开(公告)日：2012-01-05
申请号：KR1020100063192
申请日：2010-06-30
Applicant: 아주대학교산학협력단
IPC: H04N7/18
CPC classification number: G06T3/40 , G06T7/254 , G06T2207/20021 , H04N7/185
Abstract: PURPOSE: An active object tracking device using a monitoring camera and a method thereof are provided to obtain an image with high resolution about a tracking target object without an increase of photographed image data. CONSTITUTION: A control unit(15) detects the moving direction and speed of the same object in first and second comparison images. The control unit determines a predicted moving location of the object after the second comparison image is inputted based on the detected moving direction and speed. The control unit enlarges the object based on the predicted moving location of the object. The control unit photographs the enlarged object.
Abstract translation: 目的：提供一种使用监控摄像机的活动对象跟踪装置及其方法，以便不增加拍摄图像数据来获得关于跟踪目标对象的高分辨率的图像。 构成：控制单元（15）检测第一和第二比较图像中相同对象的移动方向和速度。 控制单元基于检测到的移动方向和速度来确定输入了第二比较图像之后的物体的预测移动位置。 控制单元根据对象的预测移动位置放大对象。 控制单元拍摄放大对象。
-
公开(公告)号：KR1020090092490A
公开(公告)日：2009-09-01
申请号：KR1020080017756
申请日：2008-02-27
Applicant: 아주대학교산학협력단
IPC: G01S7/481
CPC classification number: G06T7/285 , G06T7/246 , G06T7/73 , G06T2207/10021 , G06T2207/30204
Abstract: A method for measuring a position of an object using a visual image of a reference coordinate is provided to compensate for the nonlinear distortion by estimating the reference coordinate through the pre-estimation process. An object positioned in an object plane and a reference point corresponding to the object are projected on the virtual viewable plane and the real camera plane. The coordinate of the reference point corresponding to the object is estimated. The relation of the position of the object and the coordinate of the reference point are prescribed. The virtual viewable plane is parallel to the object plane. Each plane supports the zooming and panning of the image devices.
Abstract translation: 提供了使用参考坐标的视觉图像来测量对象的位置的方法，以通过预估过程估计参考坐标来补偿非线性失真。 位于物体平面中的物体和与物体相对应的参考点被投影在虚拟可见平面和真实相机平面上。 估计与对象相对应的参考点的坐标。 规定对象的位置与参考点坐标的关系。 虚拟可见平面平行于物体平面。 每个平面支持图像设备的缩放和平移。
-
公开(公告)号：KR1020130031133A
公开(公告)日：2013-03-28
申请号：KR1020110094877
申请日：2011-09-20
Applicant: 아주대학교산학협력단
CPC classification number: G06T7/292 , G06K9/00771 , H04N5/23229 , H04N5/23296 , H04N7/181
Abstract: PURPOSE: An active tracking multi-camera control device based on a sector and a method thereof are provided to prevent overlapped tracking of the same object by using active tracking for a multi-camera. CONSTITUTION: A control unit(110) assigns an assignment area to each image input unit so that overlapped areas are existed in neighbor input units(120). The control unit outputs a control signal for monitoring an object to two or more image input units based on an activity which is calculated in a sector unit. . [Reference numerals] (110) Control unit; (AA) Image input unit 1; (BB) Image input unit 2; (CC) Image input unit n
Abstract translation: 目的：提供一种基于扇区及其方法的主动跟踪多摄像机控制设备，以通过使用多摄像机的主动跟踪来防止对同一物体的重叠跟踪。 构成：控制单元（110）为每个图像输入单元分配一个分配区域，使得相邻输入单元（120）中存在重叠区域。 控制单元基于以扇区单位计算的活动，输出用于将对象监视到两个或更多个图像输入单元的控制信号。 。 （附图标记）（110）控制单元; （AA）图像输入单元1; （BB）图像输入单元2; （CC）图像输入单元n
-
公开(公告)号：KR100951321B1
公开(公告)日：2010-04-05
申请号：KR1020080017936
申请日：2008-02-27
Applicant: 아주대학교산학협력단
CPC classification number: G01S3/8006
Abstract: 파티클 필터 기반의 음향 센서를 이용한 3차원 공간에서의 객체 추적 방법이 개시된다. 종래의 베어링스-온니 트랙킹(bearings-only tracking)을 위한 파티클 필터링 알고리즘을 3차원 공간으로 직접적으로 확장하는 대신에, 본 발명은 3차원 파티클 필터를 다양하고 간단한 2차원 파티클 필터들로 재구성한다. 2차원 파티클 필터들에 대한 재구성 및 선택은 노이즈 환경에서의 음향 센서의 특성에 근거한다. 본 발명은 다중 파티클 필터 결합으로 확장되는데, 본 발명의 강건함과 성능은 Cramer-Rao Lower Bound(CRLB)를 사용하여 증명될 수 있다. 본 발명은 계산의 복잡성을 감소시키면서도 정확한 3차원 객체 추적을 수행할 수 있는 장점이 있다.
객체 추적, 3차원, 파티클 필터-
公开(公告)号：KR100884904B1
公开(公告)日：2009-02-19
申请号：KR1020070092775
申请日：2007-09-12
Applicant: 아주대학교산학협력단
IPC: G06T7/20
CPC classification number: G06T7/73 , G06T2207/30244 , G06T2207/30252
Abstract: A method for self-localization using a parallel projection model are provided to simplify the configuration for self-localization by enabling self-localization with single images obtained by a single image acquisition device. At least two virtual visible planes placed between an image plane and a reference object plane and at least two reference object planes are set up. The reference objects are projected onto the virtual visible planes. The distance between a visible shaft and a reference object in an image acquisition device and between the visible shaft and an image of the image plane corresponding to a reference shaft are calculated. Self-localization is enabled by using azimuth and zoom vectors of the image acquisition device and the coordinate of reference objects.
Abstract translation: 提供了一种使用平行投影模型进行自定位的方法，以通过对通过单个图像采集装置获得的单个图像进行自定位来简化用于自定位的配置。 放置在图像平面和参考对象平面之间的至少两个虚拟可视平面和至少两个参考对象平面。 参考对象投影到虚拟可见平面上。 计算图像采集装置中的可见轴与参考对象之间以及可见轴与对应于基准轴的图像的图像之间的距离。 通过使用图像采集设备的方位角和缩放向量以及参考对象的坐标来启用自定位。
-
-
-
-
-
Search Results
16
records
(took 0.02 seconds)
