如有错误,恳请指出。
下面是pointnet++项目实现的点云数据增强方法,主要包括随机旋转、随机缩放、随机丢弃、随机平移、随机扰动等等。
github项目链接:https://github.com/yanx27/Pointnet_Pointnet2_pytorch
# 作用: 随机打乱Batch中点云及其label的顺序
def shuffle_data(data, labels):
""" Shuffle data and labels.
Input:
data: B,N,... numpy array
label: B,... numpy array
Return:
shuffled data, label and shuffle indices
"""
idx = np.arange(len(labels))
np.random.shuffle(idx)
return data[idx, ...], labels[idx], idx
# 作用: 随机打乱一个点云中点的顺序
def shuffle_points(batch_data):
""" Shuffle orders of points in each point cloud -- changes FPS behavior.
Use the same shuffling idx for the entire batch.
Input:
BxNxC array
Output:
BxNxC array
"""
idx = np.arange(batch_data.shape[1]) # 根据索引随机点顺序
np.random.shuffle(idx)
return batch_data[:,idx,:]
这里贴上的是沿3个轴随机旋转
# 作用: 对每个点云与法向量均进行沿xyz三个轴随机(小幅度)旋转
def rotate_perturbation_point_cloud_with_normal(batch_data, angle_sigma=0.06, angle_clip=0.18):
""" Randomly perturb the point clouds by small rotations
Input:
BxNx6 array, original batch of point clouds and point normals
angle_sigma: 权重系数, 控制随机角度的大小
angle_clip: 确定随机角度的上下限(-0.18~0.18)
Return:
BxNx3 array, rotated batch of point clouds
"""
rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
for k in range(batch_data.shape[0]):
# 对xyz三个轴方向随机生成一个旋转角度
angles = np.clip(angle_sigma*np.random.randn(3), -angle_clip, angle_clip)
# 根据公式构建三个轴方向的旋转矩阵
Rx = np.array([[1,0,0],
[0,np.cos(angles[0]),-np.sin(angles[0])],
[0,np.sin(angles[0]),np.cos(angles[0])]])
Ry = np.array([[np.cos(angles[1]),0,np.sin(angles[1])],
[0,1,0],
[-np.sin(angles[1]),0,np.cos(angles[1])]])
Rz = np.array([[np.cos(angles[2]),-np.sin(angles[2]),0],
[np.sin(angles[2]),np.cos(angles[2]),0],
[0,0,1]])
# 按照内旋方式:Z-Y-X旋转顺序获得整体的旋转矩阵
R = np.dot(Rz, np.dot(Ry,Rx))
shape_pc = batch_data[k,:,0:3]
shape_normal = batch_data[k,:,3:6]
# 分别对坐标与法向量进行旋转,整体公式应该为: Pt = (Rz * Ry * Rx) * P
rotated_data[k,:,0:3] = np.dot(shape_pc.reshape((-1, 3)), R)
rotated_data[k,:,3:6] = np.dot(shape_normal.reshape((-1, 3)), R)
return rotated_data
# 作用: 对点云数据添加噪声, 进行小范围扰动
def jitter_point_cloud(batch_data, sigma=0.01, clip=0.05):
""" Randomly jitter points. jittering is per point.
Input:
BxNx3 array, original batch of point clouds
angle_sigma: 权重系数, 控制随机噪声幅度
angle_clip: 确定随机噪声的上下限(-0.05~0.05)
Return:
BxNx3 array, jittered batch of point clouds
"""
B, N, C = batch_data.shape
assert(clip > 0)
jittered_data = np.clip(sigma * np.random.randn(B, N, C), -1*clip, clip)
jittered_data += batch_data # 添加噪声
return jittered_data
# 作用: 对每个点云进行随机平移, 对点云中的每个点添加一个随机的移动距离
def shift_point_cloud(batch_data, shift_range=0.1):
""" Randomly shift point cloud. Shift is per point cloud.
Input:
BxNx3 array, original batch of point clouds
Return:
BxNx3 array, shifted batch of point clouds
"""
B, N, C = batch_data.shape
shifts = np.random.uniform(-shift_range, shift_range, (B,3)) # 对每个batch的点云设置一个随机的移动偏差
for batch_index in range(B):
batch_data[batch_index,:,:] += shifts[batch_index,:] # 每个点都进行移动
return batch_data
# 作用: 对每个点云进行随机缩放, 实现方法是乘积因子直接与点云数据相乘即可
def random_scale_point_cloud(batch_data, scale_low=0.8, scale_high=1.25):
""" Randomly scale the point cloud. Scale is per point cloud.
Input:
BxNx3 array, original batch of point clouds
Return:
BxNx3 array, scaled batch of point clouds
"""
B, N, C = batch_data.shape
scales = np.random.uniform(scale_low, scale_high, B) # 0.8~1.25间的随机缩放
for batch_index in range(B):
batch_data[batch_index,:,:] *= scales[batch_index] # 每个点都进行缩放
return batch_data
# 作用: 随机丢弃点云中的点, 操作是将丢弃点全部赋予first point的值, 也就是是一个伪丢弃(shape是没有改变的)
def random_point_dropout(batch_pc, max_dropout_ratio=0.875):
''' batch_pc: BxNx3 '''
for b in range(batch_pc.shape[0]):
dropout_ratio = np.random.random()*max_dropout_ratio # 设置随机丢弃的概率,区间是0~0.875
drop_idx = np.where(np.random.random((batch_pc.shape[1])) <= dropout_ratio)[0] # 找到那些比概率低的索引值来丢弃
if len(drop_idx) > 0:
batch_pc[b,drop_idx,:] = batch_pc[b,0,:] # 这里所谓的丢弃就是将值设置与第一个点相同
return batch_pc
ps:在PointNet++分组采样k个邻域点时,如果符合距离的点不足k个,也是使用第一个点来对其他不满足距离的点进行替换,达到了一种单点重复多次的效果。和这里的随机丢弃使用的一样的方法。
参考资料:
https://github.com/yanx27/Pointnet_Pointnet2_pytorch