本文整理汇总了Python中pcl.SAC_RANSAC属性的典型用法代码示例。如果您正苦于以下问题：Python pcl.SAC_RANSAC属性的具体用法？Python pcl.SAC_RANSAC怎么用？Python pcl.SAC_RANSAC使用的例子？那么恭喜您, 这里精选的属性代码示例或许可以为您提供帮助。您也可以进一步了解该属性所在类pcl的用法示例。
在下文中一共展示了pcl.SAC_RANSAC属性的4个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: exact_planar_normals
# 需要导入模块: import pcl [as 别名]
# 或者: from pcl import SAC_RANSAC [as 别名]
def exact_planar_normals(self):
import pcl
if self.__csv_path == "":
print "csv file path is not spcified!"
raw_data = np.genfromtxt(self.__csv_path, delimiter=",", skip_header=1)
points_xyz_arr = np.array(raw_data[:, :3], dtype=np.float32)
points_cloud = pcl.PointCloud()
points_cloud.from_array(points_xyz_arr)
for i in xrange(self.__palnar_normal_num):
seg = points_cloud.make_segmenter()
seg.set_optimize_coefficients(True)
seg.set_model_type(pcl.SACMODEL_PLANE)
seg.set_method_type(pcl.SAC_RANSAC)
seg.set_distance_threshold(self.ransac_distance_threshold)
indices, model = seg.segment()
if len(indices) < self.__plane_detection_points_thre:
break
# model turns Hessian Normal Form of a plane in 3D
# http://mathworld.wolfram.com/HessianNormalForm.html
self.__normals_list.append(model)
tmp = points_cloud.to_array()
tmp = np.delete(tmp, indices, 0)
points_cloud.from_array(tmp)
# show_xyzrgb_points_vtk(tmp) 示例2: get_plane_model
# 需要导入模块: import pcl [as 别名]
# 或者: from pcl import SAC_RANSAC [as 别名]
def get_plane_model(arr):
import pcl
ransac_distance_threshold = 0.05
point_cloud = pcl.PointCloud(arr.astype(np.float32))
seg = point_cloud.make_segmenter_normals(ksearch=50)
seg.set_model_type(pcl.SACMODEL_PLANE)
seg.set_method_type(pcl.SAC_RANSAC)
seg.set_max_iterations(10000)
seg.set_distance_threshold(ransac_distance_threshold)
indices, model = seg.segment()
print "percentage of points in plane model: ", np.float32(len(indices)) / arr.shape[0]
return model
# project a point to an estimated plane 示例3: do_ransac_plane_segmentation
# 需要导入模块: import pcl [as 别名]
# 或者: from pcl import SAC_RANSAC [as 别名]
def do_ransac_plane_segmentation(point_cloud, max_distance = 0.01):
segmenter = point_cloud.make_segmenter()
segmenter.set_model_type(pcl.SACMODEL_PLANE)
segmenter.set_method_type(pcl.SAC_RANSAC)
segmenter.set_distance_threshold(max_distance)
#obtain inlier indices and model coefficients
inlier_indices, coefficients = segmenter.segment()
inliers = point_cloud.extract(inlier_indices, negative = False)
outliers = point_cloud.extract(inlier_indices, negative = True)
return inliers, outliers
##################################################################################
# This pipeline separates the objects in the table from the given scene
# Load the point cloud in memory 示例4: pc_segmentation
# 需要导入模块: import pcl [as 别名]
# 或者: from pcl import SAC_RANSAC [as 别名]
def pc_segmentation(pc):
# vg = pc.make_voxel_grid_filter()
# vg.set_leaf_size(0.01, 0.01, 0.01)
# cloud_filtered = vg.filter()
# tree = cloud_filtered.make_kdtree()
# seg = pc.make_segmenter()
# seg.set_optimize_coefficients(True)
# seg.set_model_type(pcl.SACMODEL_PLANE)
# seg.set_method_type(pcl.SAC_RANSAC)
# seg.set_distance_threshold(0.001)
# cluster_indices, coefficients = seg.segment()
# inds = np.ones((pc.width,1))
# inds[cluster_indices] = 0
# return inds
# segment = pcl.ConditionalEuclideanClustering()
# cluster_indices = segment.Extract()
# segment = cloud_filtered.make_RegionGrowing(ksearch=50)
# segment.set_MinClusterSize(100)
# segment.set_MaxClusterSize(25000)
# segment.set_NumberOfNeighbours(5)
# segment.set_SmoothnessThreshold(0.2)
# segment.set_CurvatureThreshold(0.05)
# segment.set_SearchMethod(tree)
# cluster_indices = segment.Extract()
cloud_filtered = pc
segment = cloud_filtered.make_EuclideanClusterExtraction()
segment.set_ClusterTolerance(0.5)
segment.set_MinClusterSize(30)
segment.set_MaxClusterSize(10000)
# segment.set_SearchMethod(tree)
cluster_indices = segment.Extract()
cloud_cluster = pcl.PointCloud()
# import pdb; pdb.set_trace()
# print('cluster_indices : ' + str(len(cluster_indices)) + " count.")
cloud_clusters = []
for j, indices in enumerate(cluster_indices):
# print('indices = ' + str(len(indices)))
points = np.zeros((len(indices), 3), dtype=np.float32)
for i, indice in enumerate(indices):
points[i][0] = cloud_filtered[indice][0]
points[i][1] = cloud_filtered[indice][1]
points[i][2] = cloud_filtered[indice][2]
# print(points.shape)
cloud_clusters.append(points)
# cloud_clusters[j].from_array(points)
return cloud_clusters