CN110473223B - Two-dimensional image auxiliary segmentation method based on three-dimensional point cloud of catenary cantilever system - Google Patents
Two-dimensional image auxiliary segmentation method based on three-dimensional point cloud of catenary cantilever system Download PDFInfo
- Publication number
- CN110473223B CN110473223B CN201910753299.0A CN201910753299A CN110473223B CN 110473223 B CN110473223 B CN 110473223B CN 201910753299 A CN201910753299 A CN 201910753299A CN 110473223 B CN110473223 B CN 110473223B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- wrist
- dimensional
- arm system
- dimensional image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 230000011218 segmentation Effects 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 4
- 238000001914 filtration Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000003384 imaging method Methods 0.000 claims description 6
- 210000000707 wrist Anatomy 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
本发明公开了基于接触网腕臂系统三维点云的二维图像辅助分割方法，包括以下步骤：步骤1：获取接触网腕臂系统三维点云数据；步骤2：采用体素滤波，对三维点云数据进行均匀重采样；步骤3：将均匀重采样后的腕臂系统三维点云数据转换为二维图像；步骤4：对步骤3得到的二维图像进行分割，然后依次进行图像闭运算、中值滤波处理，返回三维点云即得到腕臂系统三维点云各个线性部分的分割结果；本发明采用二维图像进行辅助分割，并最终返回接触网腕臂系统各线性部分的高效分割结果，具有抗噪性好、鲁棒性强、精度较高的特点，提高了接触网腕臂系统的分割效果；减少了人力物力的消耗，不受天气和作业人员的经验判断影响。
The invention discloses a two-dimensional image-assisted segmentation method based on the three-dimensional point cloud of the catenary wrist-arm system, comprising the following steps: step 1: obtaining the three-dimensional point cloud data of the catenary wrist-arm system; The cloud data is uniformly resampled; Step 3: Convert the uniformly resampled 3D point cloud data of the wrist-arm system into a 2D image; Step 4: Segment the 2D image obtained in Step 3, and then perform image closing operation, Median filter processing, return the 3D point cloud to get the segmentation results of each linear part of the 3D point cloud of the wrist-arm system; the present invention uses 2D images for auxiliary segmentation, and finally returns the efficient segmentation results of each linear part of the catenary wrist-arm system, It has the characteristics of good noise resistance, strong robustness, and high precision, which improves the segmentation effect of the catenary wrist-arm system; reduces the consumption of manpower and material resources, and is not affected by the weather and the experience and judgment of operators.
Description
技术领域technical field
本发明涉及高速铁路接触网维护检测领域，具体涉及一种基于接触网腕臂系统三维点云的二维图像辅助分割方法。The invention relates to the field of high-speed railway catenary maintenance and detection, in particular to a two-dimensional image-assisted segmentation method based on a three-dimensional point cloud of a catenary wrist-arm system.
背景技术Background technique
随着电气化铁路的大力发展，列车运行素的也在不断提升。为了保证列车运行的高效性，对受电弓受流的稳定性与可靠性就提出了很高的要求。因此，必须保证腕臂系统的刚性不变性。腕臂系统各连接部分发生松脱而移位，一方面会使得承力索与接触线偏离固有位置，而出现打弓等现象，另一方面会改变腕臂系统内部应力结构，而导致接触网系统局部或区域型的松垮现象，影响列车的正常运行。因此，利用3D视觉技术获取接触网腕臂系统三维点云数据，并结合转换的二维图像进行辅助分割，提高分割结果，为腕臂系统相关参数计算提供更好的基础就变得尤为重要。With the vigorous development of electrified railways, the quality of train operation is also constantly improving. In order to ensure the high efficiency of train operation, high requirements are put forward for the stability and reliability of pantograph current receiving. Therefore, the rigid invariance of the wrist-arm system must be guaranteed. The loosening and displacement of the connecting parts of the wrist-arm system will, on the one hand, cause the catenary cable and the contact line to deviate from the original position, resulting in bowing and other phenomena; on the other hand, it will change the internal stress structure of the wrist-arm system, resulting in catenary Local or regional loosening of the system affects the normal operation of the train. Therefore, it is particularly important to use 3D vision technology to obtain 3D point cloud data of the catenary wrist-arm system, and combine the converted 2D images for auxiliary segmentation, improve the segmentation results, and provide a better basis for the calculation of relevant parameters of the wrist-arm system.
目前，主要依靠人工对接触网腕臂系统进行维护检测，将消耗大量的人力物力，对行车造成干扰，并会受天气和作业人员的经验判断影响。At present, mainly relying on manual maintenance and inspection of the catenary wrist-arm system will consume a lot of manpower and material resources, cause interference to driving, and will be affected by the weather and the experience and judgment of operators.
发明内容Contents of the invention
本发明提供一种抗噪性好、鲁棒性强、精度较高的对接触网腕臂系统实施分割的基于接触网腕臂系统三维点云的二维图像辅助分割方法。The invention provides a two-dimensional image-assisted segmentation method based on the three-dimensional point cloud of the catenary wrist-arm system, which has good noise resistance, strong robustness and high precision, and performs segmentation on the catenary wrist-arm system.
本发明采用的技术方案是：基于接触网腕臂系统三维点云的二维图像辅助分割方法，包括以下步骤：The technical scheme adopted in the present invention is: a two-dimensional image-assisted segmentation method based on the three-dimensional point cloud of the catenary wrist-arm system, comprising the following steps:
步骤1：获取接触网腕臂系统三维点云数据；Step 1: Obtain the 3D point cloud data of the catenary wrist-arm system;
步骤2：采用体素滤波，对三维点云数据进行均匀重采样；Step 2: Use voxel filtering to uniformly resample the 3D point cloud data;
步骤3：将均匀重采样后的腕臂系统三维点云数据转换为二维图像；Step 3: Convert the uniformly resampled 3D point cloud data of the wrist-arm system into a 2D image;
步骤4：对步骤3得到的二维图像进行分割，然后依次进行图像闭运算、中值滤波处理，返回三维点云即得到腕臂系统三维点云各个线性部分的分割结果。Step 4: Segment the two-dimensional image obtained in
进一步的，所述步骤3具体过程如下：Further, the specific process of
S11：确定平面坐标系x-o-z、x-o-y、y-o-z；S11: Determine the plane coordinate system x-o-z, x-o-y, y-o-z;
S12：确定二维图像平面投影的范围，计算三维点云中的X、Y、Z方向上的最大值和最小值，设定平面坐标系的单位刻度为体素的边长；S12: Determine the scope of the plane projection of the two-dimensional image, calculate the maximum and minimum values in the X, Y, and Z directions in the three-dimensional point cloud, and set the unit scale of the plane coordinate system to be the side length of the voxel;
S13：确定三维点云在平面坐标中的位置；S13: Determine the position of the three-dimensional point cloud in the plane coordinates;
S14：确定二维图像的灰度值：S14: Determine the gray value of the two-dimensional image:
式中：color(i,j)为当前点计算之后所对应的二维图像的灰度值，Y(i,j)为当前点需要获得的坐标，Ymin为三维点云在Y轴上的最小值，Ymax为三维点云在Y轴上的最大值；In the formula: color(i, j) is the gray value of the corresponding two-dimensional image after the calculation of the current point, Y(i, j) is the coordinate to be obtained at the current point, and Y min is the value of the three-dimensional point cloud on the Y axis Minimum value, Y max is the maximum value of the three-dimensional point cloud on the Y axis;
S15：还原三维坐标。S15: Restoring the three-dimensional coordinates.
进一步的，所述步骤4具体过程如下：Further, the specific process of step 4 is as follows:
S21：采用SC-LCCP算法对步骤3得到的二维图像进行分割，分别单独提取各线性部分，并将剩余部分转换为二维图像；S21: Using the SC-LCCP algorithm to segment the two-dimensional image obtained in
S22：将S11中各个线性部分对应的剩余部分的二维图像与步骤3中的三维点云二维图像相减，然后依次进行图像闭运算、中值滤波处理；S22: Subtract the two-dimensional image of the remaining part corresponding to each linear part in S11 from the two-dimensional image of the three-dimensional point cloud in
S23：将步骤S22得到的二维图像的分割结果，根据以下返回接触网腕臂系统三维点云数据中各线性部分的分割结果；S23: Return the segmentation result of the two-dimensional image obtained in step S22 to the segmentation result of each linear part in the three-dimensional point cloud data of the catenary wrist-arm system according to the following;
式中：color(i,j)为当前点计算之后所对应的二维图像的灰度值，Y(i,j)为当前点需要获得的坐标，Ymin为三维点云在Y轴上的最小值，Ymax为三维点云在Y轴上的最大值。In the formula: color(i, j) is the gray value of the corresponding two-dimensional image after the calculation of the current point, Y(i, j) is the coordinate to be obtained at the current point, and Y min is the value of the three-dimensional point cloud on the Y axis The minimum value, Y max is the maximum value of the 3D point cloud on the Y axis.
进一步的，所述步骤2中的采用体素滤波，对三维点云数据进行均匀重采样过程如下：Further, the process of uniformly resampling the 3D point cloud data using voxel filtering in the
采用直通滤波器，根据腕臂系统在成像过程中采用的相机的坐标系成像位置，分别设置x、y、z轴的阈值范围，对腕臂系统的背景环境进行滤除；利用体素滤波，设置体素体大小，对腕臂系统三维点云进行均匀重采样。Using a straight-through filter, according to the imaging position of the camera coordinate system used by the wrist-arm system in the imaging process, set the threshold ranges of the x, y, and z axes respectively to filter out the background environment of the wrist-arm system; using voxel filtering, Set the voxel volume size to uniformly resample the 3D point cloud of the wrist-arm system.
进一步的，所述步骤S21中线性部分包括平腕臂、腕臂支撑、斜腕臂、定位管支撑、定位管和定位器。Further, the linear part in step S21 includes a flat arm, an arm support, an oblique arm, a positioning tube support, a positioning tube and a positioner.
本发明的有益效果是：The beneficial effects of the present invention are:
(1)本发明通过3D视觉图像技术获取接触网腕臂系统的三维点云数据，不会增加接触网系统的负载；(1) The present invention acquires the three-dimensional point cloud data of the catenary wrist-arm system through 3D visual image technology, which will not increase the load of the catenary system;
(2)本发明采用二维图像进行辅助分割，并最终返回接触网腕臂系统各线性部分的高效分割结果，具有抗噪性好、鲁棒性强、精度较高的特点，提高了接触网腕臂系统的分割效果；(2) The present invention uses two-dimensional images for auxiliary segmentation, and finally returns the efficient segmentation results of each linear part of the catenary wrist-arm system, which has the characteristics of good noise resistance, strong robustness, and high precision, and improves the catenary The segmentation effect of the wrist-arm system;
(3)本发明采用非接触式3D视觉图像技术，减少了人力物力的消耗，不受天气和作业人员的经验判断影响。(3) The present invention adopts non-contact 3D visual image technology, which reduces the consumption of manpower and material resources, and is not affected by the weather and the experience judgment of operators.
附图说明Description of drawings
图1为本发明分割流程示意图。Fig. 1 is a schematic diagram of the segmentation process of the present invention.
图2为本发明中采用的检测装置示意图。Fig. 2 is a schematic diagram of the detection device used in the present invention.
图3为本发明中获取一帧腕臂系统点云数据示意图。Fig. 3 is a schematic diagram of acquiring a frame of wrist-arm system point cloud data in the present invention.
图4为本发明中获取的现场一帧腕臂系统点云数据。Fig. 4 is a frame of point cloud data of the wrist-arm system obtained in the present invention.
图5为本发明中直通滤波之后的腕臂系统点云数据。Fig. 5 is the point cloud data of the arm-arm system after through filtering in the present invention.
图6为本发明中体素滤波之后的腕臂系统点云数据。Fig. 6 is the point cloud data of the wrist-arm system after voxel filtering in the present invention.
图7为本发明中构建的二维平面坐标系。Fig. 7 is a two-dimensional plane coordinate system constructed in the present invention.
图8为本发明中点云在x-o-z平面中的位置。Fig. 8 is the position of the point cloud in the x-o-z plane in the present invention.
图9为本发明中转换的二维图像。Fig. 9 is a two-dimensional image converted in the present invention.
图10为本发明中SC-LCCP分割结果的二维图像。Fig. 10 is a two-dimensional image of the SC-LCCP segmentation result in the present invention.
图11为本发明中二维图像分割结果示意图。Fig. 11 is a schematic diagram of the results of two-dimensional image segmentation in the present invention.
图12为本发明中映射腕臂系统三维点云分割结果。Fig. 12 is the result of three-dimensional point cloud segmentation of the mapping arm-arm system in the present invention.
图13为本发明中原始接触网腕臂系统三维点云数据集。Fig. 13 is the three-dimensional point cloud data set of the original catenary wrist-arm system in the present invention.
图14为本发明中腕臂系统三维点云分割结果。Fig. 14 is the result of three-dimensional point cloud segmentation of the wrist-arm system in the present invention.
图中：1-检测车，2-深度相机，3-承力索，4-吊弦，5-轨道，6-接触线，7-腕臂系统。In the figure: 1- Inspection vehicle, 2- Depth camera, 3- Catenary cable, 4- Hanging string, 5- Track, 6- Contact line, 7- Wrist arm system.
具体实施方式Detailed ways
下面结合附图和具体实施例对本发明做进一步说明。The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.
如图1所示，一种基于接触网腕臂系统三维点云的二维图像辅助分割方法，包括以下步骤：As shown in Figure 1, a 2D image-assisted segmentation method based on the 3D point cloud of the catenary wrist-arm system includes the following steps:
步骤1：获取接触网腕臂系统三维点云数据；Step 1: Obtain the 3D point cloud data of the catenary wrist-arm system;
深度相机置于检测车正上方，相机水平，并倾斜一定角度，如图2所示。移动检测车，使得整个腕臂系统在深度相机可视范围内，实时获取多帧腕臂系统点云数据，如图3所示，图4为获取的一帧腕臂点云数据。The depth camera is placed directly above the detection vehicle, and the camera is horizontal and tilted at a certain angle, as shown in Figure 2. The mobile detection vehicle makes the entire wrist-arm system obtain multi-frame wrist-arm system point cloud data in real time within the visible range of the depth camera, as shown in Figure 3, and Figure 4 shows the acquired frame of wrist-arm point cloud data.
步骤2：采用体素滤波，对三维点云数据进行均匀重采样；Step 2: Use voxel filtering to uniformly resample the 3D point cloud data;
过程如下：The process is as follows:
采用直通滤波器，根据腕臂系统在成像过程中采用的相机的坐标系成像位置，分别设置x、y、z轴的阈值范围，对腕臂系统的背景环境进行滤除；直通滤波器参数参考设置如表1所示，滤波结果如图5所示。利用体素滤波，设置体素体大小为0.02m，对腕臂系统三维点云进行均匀重采样，滤波结果如图6所示。Using a straight-through filter, according to the imaging position of the camera coordinate system used by the wrist-arm system in the imaging process, set the threshold ranges of the x, y, and z axes respectively to filter out the background environment of the wrist-arm system; refer to the parameters of the straight-through filter The settings are shown in Table 1, and the filtering results are shown in Figure 5. Using voxel filtering, set the voxel size to 0.02m, and uniformly resample the 3D point cloud of the wrist-arm system. The filtering results are shown in Figure 6.
表1.直通滤波器参数设置Table 1. Pass-through Filter Parameter Settings
步骤3：将均匀重采样后的腕臂系统三维点云数据转换为二维图像；Step 3: Convert the uniformly resampled 3D point cloud data of the wrist-arm system into a 2D image;
具体过程如下：The specific process is as follows:
S11：确定平面坐标系x-o-z、x-o-y、y-o-z(其中任意一个坐标轴所在平面都可以)，坐标系见图7；S11: Determine the plane coordinate system x-o-z, x-o-y, y-o-z (the plane where any coordinate axis is located can be used), the coordinate system is shown in Figure 7;
S12：确定二维图像平面投影的范围，计算三维点云中的X、Y、Z方向上的最大值和最小值，分别记为Xmax、Ymax、Zmax和Xmin、Ymin、Zmin；设定平面坐标系的单位刻度为体素的边长；以此保证平面坐标系单位刻度所对应面积为体素的面大小。S12: Determine the range of two-dimensional image plane projection, and calculate the maximum and minimum values in the X, Y, and Z directions in the three-dimensional point cloud, which are respectively recorded as X max , Y max , Z max and X min , Y min , Z min ; set the unit scale of the plane coordinate system as the side length of the voxel; in this way, the area corresponding to the unit scale of the plane coordinate system is the surface size of the voxel.
S13：确定三维点云在平面坐标(如x-o-z，其中任意一个坐标轴所在平面都可以)中的位置，如图8所示；S13: Determine the position of the three-dimensional point cloud in the plane coordinates (such as x-o-z, where any one of the coordinate axes is located in the plane), as shown in Figure 8;
S14：确定二维图像的灰度值：S14: Determine the gray value of the two-dimensional image:
式中：color(i,j)为当前点计算之后所对应的二维图像的灰度值，Y(i,j)为当前点需要获得的坐标，Ymin为三维点云在Y轴上的最小值，Ymax为三维点云在Y轴上的最大值；In the formula: color(i, j) is the gray value of the corresponding two-dimensional image after the calculation of the current point, Y(i, j) is the coordinate to be obtained at the current point, and Y min is the value of the three-dimensional point cloud on the Y axis Minimum value, Y max is the maximum value of the three-dimensional point cloud on the Y axis;
S15：还原三维坐标，二维图像如图9所示。S15: Restore the three-dimensional coordinates, and the two-dimensional image is as shown in FIG. 9 .
步骤4：对步骤3得到的二维图像进行分割，然后依次进行图像闭运算、中值滤波处理，返回三维点云即得到腕臂系统三维点云各个线性部分的分割结果。Step 4: Segment the two-dimensional image obtained in
具体过程如下：The specific process is as follows:
S21：采用基于斜率约束的凸连接打包(Slope Constrained Locally ConvexConnected Patches:SC-LCCP)SC-LCCP算法对步骤3得到的二维图像进行分割，分别单独提取各线性部分，包括平腕臂、腕臂支撑、斜腕臂、定位管支撑、定位管和定位器。并将剩余部分转换为二维图像，如图10所示。S21: Use Slope Constrained Locally ConvexConnected Patches (SC-LCCP) SC-LCCP algorithm to segment the two-dimensional image obtained in
S22：将S11中各个线性部分对应的剩余部分的二维图像与步骤3中的三维点云二维图像相减，然后依次进行图像闭运算、中值滤波处理，如图11所示；S22: Subtract the two-dimensional image of the remaining part corresponding to each linear part in S11 from the two-dimensional image of the three-dimensional point cloud in
S23：将步骤S22得到的二维图像的分割结果，根据以下返回接触网腕臂系统三维点云数据中各线性部分的分割结果，如图12所示；S23: Return the segmentation result of the two-dimensional image obtained in step S22 to the segmentation result of each linear part in the three-dimensional point cloud data of the catenary wrist-arm system according to the following, as shown in Figure 12;
式中：color(i,j)为当前点计算之后所对应的二维图像的灰度值，Y(i,j)为当前点需要获得的坐标，Ymin为三维点云在Y轴上的最小值，Ymax为三维点云在Y轴上的最大值。In the formula: color(i, j) is the gray value of the corresponding two-dimensional image after the calculation of the current point, Y(i, j) is the coordinate to be obtained at the current point, and Y min is the value of the three-dimensional point cloud on the Y axis The minimum value, Y max is the maximum value of the 3D point cloud on the Y axis.
采用本发明方法，对通过深度相机获取的500组腕臂系统点云数据进行各线性部分的高效分割，并展示了部分原始数据集和6组分割结果。原始数据如图13所示，分割结果数据如图14所示。By adopting the method of the present invention, 500 groups of wrist-arm system point cloud data acquired by depth cameras are efficiently segmented for each linear part, and some original data sets and 6 groups of segmentation results are displayed. The original data is shown in Figure 13, and the segmentation result data is shown in Figure 14.
本发明通过3D视觉图像技术，对接触网腕臂系统进行各线性部分的高效分割。这种非接触式的腕臂系统分割方法，不会对接触网系统增加额外的负载，且不会干扰行车；减少了人力物力的消耗。不受天气的约束以及作业人员的经验判断影响。采用基于斜率约束的凸连接打包(Slope Constrained Locally Convex Connected Patches:SC-LCCP)算法，提高了各线性部分的分割结果，为后续的参数检测提供了更好的基础，具有较好的使用前景。The invention uses 3D visual image technology to efficiently segment each linear part of the catenary wrist-arm system. This non-contact wrist-arm system division method will not add additional load to the catenary system, and will not interfere with driving; it reduces the consumption of manpower and material resources. It is not affected by the constraints of the weather and the experience and judgment of the operators. Using the Slope Constrained Locally Convex Connected Patches (SC-LCCP) algorithm based on slope constraints improves the segmentation results of each linear part, provides a better foundation for subsequent parameter detection, and has a better application prospect.
Claims (2)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910753299.0A CN110473223B (en) | 2019-08-15 | 2019-08-15 | Two-dimensional image auxiliary segmentation method based on three-dimensional point cloud of catenary cantilever system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910753299.0A CN110473223B (en) | 2019-08-15 | 2019-08-15 | Two-dimensional image auxiliary segmentation method based on three-dimensional point cloud of catenary cantilever system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110473223A CN110473223A (en) | 2019-11-19 |
| CN110473223B true CN110473223B (en) | 2023-05-05 |
Family
ID=68510090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910753299.0A Expired - Fee Related CN110473223B (en) | 2019-08-15 | 2019-08-15 | Two-dimensional image auxiliary segmentation method based on three-dimensional point cloud of catenary cantilever system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110473223B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335263A (en) * | 2019-06-28 | 2019-10-15 | 珠海博明软件有限公司 | It is a kind of to identify the measurement scheme for improving 3D difference in height computational accuracy by brightness |
| CN111814679B (en) * | 2020-07-08 | 2023-10-13 | 上海雪湖科技有限公司 | FPGA-based implementation algorithm for voxel-encoder and VFE of voxel-encoder 3D network |
| CN112948954B (en) * | 2021-04-16 | 2023-06-02 | 中铁第四勘察设计院集团有限公司 | Three-dimensional modeling method and system for catenary cantilever positioning device with driving constraint |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011070927A1 (en) * | 2009-12-11 | 2011-06-16 | 株式会社トプコン | Point group data processing device, point group data processing method, and point group data processing program |
| CN104299260A (en) * | 2014-09-10 | 2015-01-21 | 西南交通大学 | Contact network three-dimensional reconstruction method based on SIFT and LBP point cloud registration |
| CN107123161A (en) * | 2017-06-14 | 2017-09-01 | 西南交通大学 | A kind of the whole network three-dimensional rebuilding method of contact net zero based on NARF and FPFH |
| CN108564575A (en) * | 2018-04-11 | 2018-09-21 | 西南交通大学 | A kind of contactless catenary's parameters detection method based on three dimensional point cloud |
| CN109118500A (en) * | 2018-07-16 | 2019-01-01 | 重庆大学产业技术研究院 | A kind of dividing method of the Point Cloud Data from Three Dimension Laser Scanning based on image |
| CN109816682A (en) * | 2019-01-22 | 2019-05-28 | 西南交通大学 | A method for segmentation and parameter detection of wrist-arm system based on concavo-convexity |
-
2019
- 2019-08-15 CN CN201910753299.0A patent/CN110473223B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011070927A1 (en) * | 2009-12-11 | 2011-06-16 | 株式会社トプコン | Point group data processing device, point group data processing method, and point group data processing program |
| CN104299260A (en) * | 2014-09-10 | 2015-01-21 | 西南交通大学 | Contact network three-dimensional reconstruction method based on SIFT and LBP point cloud registration |
| CN107123161A (en) * | 2017-06-14 | 2017-09-01 | 西南交通大学 | A kind of the whole network three-dimensional rebuilding method of contact net zero based on NARF and FPFH |
| CN108564575A (en) * | 2018-04-11 | 2018-09-21 | 西南交通大学 | A kind of contactless catenary's parameters detection method based on three dimensional point cloud |
| CN109118500A (en) * | 2018-07-16 | 2019-01-01 | 重庆大学产业技术研究院 | A kind of dividing method of the Point Cloud Data from Three Dimension Laser Scanning based on image |
| CN109816682A (en) * | 2019-01-22 | 2019-05-28 | 西南交通大学 | A method for segmentation and parameter detection of wrist-arm system based on concavo-convexity |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110473223A (en) | 2019-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110473223B (en) | Two-dimensional image auxiliary segmentation method based on three-dimensional point cloud of catenary cantilever system | |
| CN107833270B (en) | Real-time object three-dimensional reconstruction method based on depth camera | |
| CN102902355B (en) | The space interaction method of mobile device | |
| CN104915978B (en) | Realistic animation generation method based on body-sensing camera Kinect | |
| WO2023212997A1 (en) | Knowledge distillation based neural network training method, device, and storage medium | |
| CN112284291A (en) | A three-dimensional scanning method and device capable of obtaining physical texture | |
| CN103957397B (en) | A kind of low resolution depth image top sampling method based on characteristics of image | |
| CN114898061B (en) | A fast reconstruction method for power transmission corridor based on fly-away dual-mode visual information | |
| CN107730519A (en) | A kind of method and system of face two dimensional image to face three-dimensional reconstruction | |
| CN106919257B (en) | Texture force reproduction method based on image brightness information force-tactile interaction | |
| CN108663026A (en) | A kind of vibration measurement method | |
| CN107330980A (en) | A kind of virtual furnishings arrangement system based on no marks thing | |
| CN116912158A (en) | Workpiece quality inspection method, device, equipment and readable storage medium | |
| CN110197156A (en) | Manpower movement and the shape similarity metric method and device of single image based on deep learning | |
| CN104655041B (en) | A kind of industrial part contour line multi-feature extraction method of additional constraint condition | |
| CN107105214A (en) | A kind of 3 d video images method for relocating | |
| CN116612235A (en) | Multi-view geometric unmanned aerial vehicle image three-dimensional reconstruction method and storage medium | |
| CN109816682B (en) | A Wrist-Arm System Segmentation and Parameter Detection Method Based on Concavity and Convexity | |
| CN110400268A (en) | A system and method for fabric image restoration under non-single view | |
| CN201477636U (en) | Image Acquisition Device Based on Vertical Potential Difference | |
| CN118330616A (en) | Underwater pier disease detection data processing method and system with acousto-optic fusion | |
| CN118212200A (en) | Track bolt floating detection method and system for 2D-3D structured light | |
| CN114998444B (en) | A high-precision robot posture measurement system based on two-channel network | |
| CN117704253A (en) | Digital orthophoto image manufacturing mechanism and manufacturing method thereof | |
| CN115760790A (en) | Airport pavement foreign object detection method, server and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20230505 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |