chamfer_pcd

Chamfer距离计算

最新推荐文章于 2024-10-10 07:31:06 发布

转载最新推荐文章于 2024-10-10 07:31:06 发布 · 366 阅读

1 ·

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/BambooEatPanda/p/10974184.html

文章标签：

#python

本文介绍了一种在点云匹配中常用的Chamfer距离计算方法，包括使用TensorFlow和NumPy实现的距离矩阵计算、平均距离计算及总Chamfer距离计算。通过具体代码示例，展示了如何计算两个点集之间的Chamfer距离。

import tensorflow as tf
import numpy as np

def distance_matrix(array1, array2):
    """
    arguments:
        array1: the array, size: (num_point, num_feature)
        array2: the samples, size: (num_point, num_feature)
    returns:
        distances: each entry is the distance from a sample to array1
            , it's size: (num_point, num_point)
    """
    num_point, num_features = array1.shape
    expanded_array1 = tf.tile(array1, (num_point, 1))
    expanded_array2 = tf.reshape(
            tf.tile(tf.expand_dims(array2, 1),
                    (1, num_point, 1)),
            (-1, num_features))
    distances = tf.norm(expanded_array1-expanded_array2, axis=1)
    distances = tf.reshape(distances, (num_point, num_point))
    return distances

def av_dist(array1, array2):
    """
    arguments:
        array1, array2: both size: (num_points, num_feature)
    returns:
        distances: size: (1,)
    """
    distances = distance_matrix(array1, array2)
    distances = tf.reduce_min(distances, axis=1)
    distances = tf.reduce_mean(distances)
    return distances

def av_dist_sum(arrays):
    """
    arguments:
        arrays: array1, array2
    returns:
        sum of av_dist(array1, array2) and av_dist(array2, array1)
    """
    array1, array2 = arrays
    av_dist1 = av_dist(array1, array2)
    av_dist2 = av_dist(array2, array1)
    return av_dist1+av_dist2

def chamfer_distance_tf(array1, array2):
    batch_size, num_point, num_features = array1.shape
    dist = tf.reduce_mean(
               tf.map_fn(av_dist_sum, elems=(array1, array2), dtype=tf.float64)
           )
    return dist

def array2samples_distance(array1, array2):
    """
    arguments:
        array1: the array, size: (num_point, num_feature)
        array2: the samples, size: (num_point, num_feature)
    returns:
        distances: each entry is the distance from a sample to array1
    """
    num_point, num_features = array1.shape
    expanded_array1 = np.tile(array1, (num_point, 1))
    expanded_array2 = np.reshape(
            np.tile(np.expand_dims(array2, 1),
                    (1, num_point, 1)),
            (-1, num_features))
    distances = np.linalg.norm(expanded_array1-expanded_array2, axis=1)
    distances = np.reshape(distances, (num_point, num_point))
    distances = np.min(distances, axis=1)
    distances = np.mean(distances)
    return distances

def chamfer_distance_numpy(array1, array2):
    batch_size, num_point, num_features = array1.shape
    dist = 0
    for i in range(batch_size):
        av_dist1 = array2samples_distance(array1[i], array2[i])
        av_dist2 = array2samples_distance(array2[i], array1[i])
        dist = dist + (av_dist1+av_dist2)/batch_size
    return dist

if __name__=='__main__':
    batch_size = 3
    num_point = 10
    num_features = 3
    np.random.seed(1)
    array1 = np.random.randint(0, high=4, size=(batch_size, num_point, num_features))
    array2 = np.random.randint(0, high=4, size=(batch_size, num_point, num_features))
    print (array1)
    #print(array2)
    print('numpy: ', chamfer_distance_numpy(array1, array2))

转载于:https://www.cnblogs.com/BambooEatPanda/p/10974184.html