-
1.发明授权
公开(公告)号：US5870494A
公开(公告)日：1999-02-09
申请号：US893256
申请日：1997-07-16
申请人： Shinji Kanda , Jun Wakitani , Tsugito Maruyama , Toshihiko Morita
发明人： Shinji Kanda , Jun Wakitani , Tsugito Maruyama , Toshihiko Morita
CPC分类号： G06K9/4633 , G06K9/4609 , G06T5/20 , G06T7/0042 , G06T7/0083 , G06T7/0085
摘要： A method for determining an orientation of a line segment in a contour in a local area of a binary contour image. The number of pixels having a predetermined value and located in each orientation in the local area, is obtained, and it is determined that a line segment exists in an orientation in which the number of pixels is large. Further, when it is determined that the number of pixels located in each of a plurality of orientations and having a predetermined value, is greater than a sum of the numbers of pixels in orientations adjacent to said each orientation on both sides thereof, it is determined that a line segment exists in said each orientation. Two orientations in which large numbers of pixels are located are detected, and it is determined whether the point is a constituent of a line segment, a line segment of the sub-straight-line form, or a near-corner point, depending on angles made by the two orientations is equal to 180.degree., or a difference of the angles made by the two orientations from 180.degree.. Contiguously arrayed pixels in the same orientation are detected as a line segment. A position and an orientation are obtained from points near a corner, and representative values of the positions and orientations of contiguously arrayed near-corner points are determined. (FIG. 3)
摘要翻译： 一种用于确定二进制轮廓图像的局部区域中的轮廓中的线段的取向的方法。 获得具有预定值并位于局部区域中的每个取向的像素数，并且确定在像素数量大的取向中存在线段。 此外，当确定位于多个取向中的并且具有预定值的每个中的像素的数量大于与其两侧上的所述每个取向相邻的取向中的像素数的总和时，确定 在所述每个取向上存在线段。 检测到其中存在大量像素的两个取向，并且根据角度确定该点是线段，亚直线形式的线段还是近角点的组成 由两个取向制成的角度等于180°，或者两个方向的角度与180°的差。 以相同方向连续排列的像素被检测为线段。 从拐角附近的点获得位置和取向，并且确定连续排列的近角点的位置和取向的代表值。 （图3）
-
2.发明授权
公开(公告)号：US5509090A
公开(公告)日：1996-04-16
申请号：US285441
申请日：1994-08-04
申请人： Tsugito Maruyama , Shinji Kanda , Jun Wakitani
发明人： Tsugito Maruyama , Shinji Kanda , Jun Wakitani
CPC分类号： G06T7/0057 , G01B11/2527 , G01S17/89 , G01S17/42 , G01S7/481
摘要： A three-dimensional measuring apparatus including a multi-slit projector has an actuator for displacing at least one of first and second diffraction gratings by only a minute distance in a direction perpendicular to the slit lights. An image recognizing apparatus includes an image arithmetic unit for changing, each time a coded multi-slit light pattern is changed, weights assigned to the binarized image signals, and for summing up the last weighted binarized image signals or the image signals of the last added results read out from an image memory, with newly weighted binarized image signals. This improves the image resolution reduces the memory capacity and increases the processing speed.
摘要翻译： 包括多狭缝投影仪的三维测量装置具有用于使第一和第二衍射光栅中的至少一个在垂直于狭缝光的方向上仅移动微小距离的致动器。 图像识别装置包括图像运算单元，用于每次改变编码的多狭缝光图案时，分配给二值化图像信号的权重，以及用于对最后加权的二值化图像信号或最后添加的图像信号 结果从图像存储器读出，具有新加权的二值化图像信号。 这提高了图像分辨率，降低了存储容量并提高了处理速度。
-
3.发明授权
公开(公告)号：US5668893A
公开(公告)日：1997-09-16
申请号：US676512
申请日：1996-07-08
申请人： Shinji Kanda , Jun Wakitani , Tsugito Maruyama , Toshihiko Morita
发明人： Shinji Kanda , Jun Wakitani , Tsugito Maruyama , Toshihiko Morita
CPC分类号： G06K9/4633 , G06K9/4609 , G06T5/20 , G06T7/0042 , G06T7/0083 , G06T7/0085
摘要： The present invention relates to a method for determining an orientation of a line segment in a contour in a local area of a binary contour image. The number of pixels having a predetermined value and located in each orientation in the local area, is obtained, and it is determined that a line segment exists in an orientation in which the number of pixels is large. Further, when it is determined that the number of pixels located in each of a plurality of orientations and having a predetermined value is greater than a sum of the numbers of pixels in orientations adjacent to said each orientation on both sides thereof, it is determined that a line segment exists in said each orientation. Two orientations in which large numbers of pixels are located are detected, and it is determined whether the point is a constituent of a line segment, a line segment of the sub-straight-line form, or a near-corner point, depending on angles made by the two orientations is equal to 180.degree., or a difference of the angles made by the two orientations from 180.degree.. Contiguously arrayed pixels in the same orientation are detected as a line segment. A position and an orientation are obtained from points near a corner, and representative values of the positions and orientations of contiguously arrayed near-corner points are determined.
摘要翻译： 本发明涉及一种用于确定二进制轮廓图像的局部区域中的轮廓中的线段的取向的方法。 获得具有预定值并位于局部区域中的每个取向的像素数，并且确定在像素数量大的取向中存在线段。 此外，当确定位于多个取向中的并且具有预定值的每个中的像素的数量大于其两侧上与所述每个取向相邻的取向中的像素数的总和时，确定 在所述每个取向上存在线段。 检测到其中存在大量像素的两个取向，并且根据角度确定该点是线段，亚直线形式的线段还是近角点的组成 由两个取向制成的角度等于180°，或者两个方向的角度与180°的差。 以相同方向连续排列的像素被检测为线段。 从拐角附近的点获得位置和取向，并且确定连续排列的近角点的位置和取向的代表值。
-
4.发明授权
公开(公告)号：US5586199A
公开(公告)日：1996-12-17
申请号：US70450
申请日：1993-06-02
申请人： Shinji Kanda , Jun Wakitani , Tsugito Maruyama , Toshihiko Morita
发明人： Shinji Kanda , Jun Wakitani , Tsugito Maruyama , Toshihiko Morita
CPC分类号： G06K9/4633 , G06K9/4609 , G06T5/20 , G06T7/0042 , G06T7/0083 , G06T7/0085
摘要： The present invention relates to a method for determining an orientation of a line segment in a contour in a local area of a binary contour image. The number of pixels having a predetermined value and located in each orientation in the local area, is obtained, and it is determined that a line segment exists in an orientation in which the number of pixels is large. Further, when it is determined that the number of pixels located in each of a plurality of orientations and having a predetermined value is greater than a sum of the numbers of pixels in orientations adjacent to said each orientation on both sides thereof, it is determined that a line segment exists in said each orientation. Two orientations in which large numbers of pixels are located are detected, and it is determined whether the point is a constituent of a line segment, a line segment of the sub-straight-line form, or a near-corner point, depending on angles made by the two orientations is equal to 180.degree., or a difference of the angles made by the two orientations from 180.degree.. Contiguously arrayed pixels in the same orientation are detected as a line segment. A position and an orientation are obtained from points near a corner, and representative values of the positions and orientations of contiguously arrayed near-corner points are determined.
摘要翻译： PCT No.PCT / JP92 / 01277 Sec。 371日期：1993年6月6日 102（e）日期1993年6月6日PCT提交1992年10月2日PCT公布。 出版物WO93 / 07580 日期：1993年04月15日本发明涉及一种用于确定二值轮廓图像的局部区域中的轮廓中的线段的取向的方法。 获得具有预定值并位于局部区域中的每个取向的像素数，并且确定在像素数量大的取向中存在线段。 此外，当确定位于多个取向中的并且具有预定值的每个中的像素的数量大于其两侧上与所述每个取向相邻的取向中的像素数的总和时，确定 在所述每个取向上存在线段。 检测到其中存在大量像素的两个取向，并且根据角度确定该点是线段，亚直线形式的线段还是近角点的组成 由两个取向制成的角度等于180°，或者两个方向的角度与180°的差。 以相同方向连续排列的像素被检测为线段。 从拐角附近的点获得位置和取向，并且确定连续排列的近角点的位置和取向的代表值。
-
公开(公告)号：US5307153A
公开(公告)日：1994-04-26
申请号：US113745
申请日：1993-08-31
申请人： Tsugito Maruyama , Shinji Kanda , Jun Wakitani
发明人： Tsugito Maruyama , Shinji Kanda , Jun Wakitani
CPC分类号： G06T7/0057 , G01B11/2527 , G01S17/89 , G01S17/42 , G01S7/481
摘要： A three-dimensional measuring apparatus including a multi-slit projector has an actuator for displacing at least one of first and second diffraction gratings by only a minute distance in a direction perpendicular to the slit lights. An image recognizing apparatus includes an image arithmetic unit for changing, each time a coded multi-slit light pattern is changed, weights assigned to the binarized image signals, and for summing up the last weighted binarized image signals or the image signals of the last added results read out from an image memory with newly weighted binarized image signals. This improves the image resolution reduces the memory capacity and increases the processing speed.
摘要翻译： 包括多狭缝投影仪的三维测量装置具有用于使第一和第二衍射光栅中的至少一个在垂直于狭缝光的方向上仅移动微小距离的致动器。 图像识别装置包括图像运算单元，用于每次改变编码的多狭缝光图案时，分配给二值化图像信号的权重，以及用于对最后加权的二值化图像信号或最后添加的图像信号 结果从具有新加权的二值化图像信号的图像存储器中读出。 这提高了图像分辨率，降低了存储容量并提高了处理速度。
-
公开(公告)号：US6031568A
公开(公告)日：2000-02-29
申请号：US17313
申请日：1998-02-02
申请人： Jun Wakitani
发明人： Jun Wakitani
CPC分类号： G06T7/20
摘要： In a moving-target tracking apparatus for tracking a target moving in a dynamic picture image, color information, differential information and target position information based on a prediction for a motion according to the past motion are detected in the form of two-dimensional map. These maps are merged into a single map. A target position is detected in accordance with the merged map. Thus, an operational ability on a real-time basis and a tracking performance are improved.
摘要翻译： 在用于跟踪在动态画面图像中移动的目标的移动目标跟踪装置中，以二维地图的形式检测基于根据过去动作的运动的预测的颜色信息，差分信息和目标位置信息。 这些地图合并成一张地图。 根据合并图来检测目标位置。 因此，提高了实时性和跟踪性能的操作能力。
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.027 秒)
