Spaces:
Runtime error
Runtime error
File size: 5,794 Bytes
f670afc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 |
# Copyright (C) 2021 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
#
# This work is made available under the Nvidia Source Code License-NC.
# To view a copy of this license, check out LICENSE.md
import numpy as np
import matplotlib.pyplot as plt
import os.path
TAG_CHAR = np.array([202021.25], np.float32)
def readFlow(fn):
""" Read .flo file in Middlebury format"""
# Code adapted from:
# http://stackoverflow.com/questions/28013200/
# reading-middlebury-flow-files-with-python-bytes-array-numpy
# WARNING: this will work on little-endian architectures
# (eg Intel x86) only!
# print 'fn = %s'%(fn)
with open(fn, 'rb') as f:
magic = np.fromfile(f, np.float32, count=1)
if 202021.25 != magic:
print('Magic number incorrect. Invalid .flo file')
return None
else:
w = np.fromfile(f, np.int32, count=1)
h = np.fromfile(f, np.int32, count=1)
# print 'Reading %d x %d flo file\n' % (w, h)
data = np.fromfile(f, np.float32, count=2 * int(w) * int(h))
# Reshape data into 3D array (columns, rows, bands)
# The reshape here is for visualization, the original code is
# (w,h,2)
return np.resize(data, (int(h), int(w), 2))
def writeFlow(filename, uv, v=None):
""" Write optical flow to file.
If v is None, uv is assumed to contain both u and v channels,
stacked in deep.
Original code by Deqing Sun, adapted from Daniel Scharstein.
"""
nBands = 2
if v is None:
assert(uv.ndim == 3)
assert(uv.shape[2] == 2)
u = uv[:, :, 0]
v = uv[:, :, 1]
else:
u = uv
assert(u.shape == v.shape)
height, width = u.shape
f = open(filename, 'wb')
# write the header
f.write(TAG_CHAR)
np.array(width).astype(np.int32).tofile(f)
np.array(height).astype(np.int32).tofile(f)
# arrange into matrix form
tmp = np.zeros((height, width * nBands))
tmp[:, np.arange(width) * 2] = u
tmp[:, np.arange(width) * 2 + 1] = v
tmp.astype(np.float32).tofile(f)
f.close()
# ref: https://github.com/sampepose/flownet2-tf/
# blob/18f87081db44939414fc4a48834f9e0da3e69f4c/src/flowlib.py#L240
def visulize_flow_file(flow_filename, save_dir=None):
flow_data = readFlow(flow_filename)
img = flow2img(flow_data)
# plt.imshow(img)
# plt.show()
if save_dir:
idx = flow_filename.rfind("/") + 1
plt.imsave(os.path.join(save_dir, "%s-vis.png" %
flow_filename[idx:-4]), img)
def flow2img(flow_data):
"""
convert optical flow into color image
:param flow_data:
:return: color image
"""
# print(flow_data.shape)
# print(type(flow_data))
u = flow_data[:, :, 0]
v = flow_data[:, :, 1]
UNKNOW_FLOW_THRESHOLD = 1e7
pr1 = abs(u) > UNKNOW_FLOW_THRESHOLD
pr2 = abs(v) > UNKNOW_FLOW_THRESHOLD
idx_unknown = (pr1 | pr2)
u[idx_unknown] = v[idx_unknown] = 0
# get max value in each direction
maxu = -999.
maxv = -999.
minu = 999.
minv = 999.
maxu = max(maxu, np.max(u))
maxv = max(maxv, np.max(v))
minu = min(minu, np.min(u))
minv = min(minv, np.min(v))
rad = np.sqrt(u ** 2 + v ** 2)
maxrad = max(-1, np.max(rad))
u = u / maxrad + np.finfo(float).eps
v = v / maxrad + np.finfo(float).eps
img = compute_color(u, v)
idx = np.repeat(idx_unknown[:, :, np.newaxis], 3, axis=2)
img[idx] = 0
return np.uint8(img)
def compute_color(u, v):
"""
compute optical flow color map
:param u: horizontal optical flow
:param v: vertical optical flow
:return:
"""
height, width = u.shape
img = np.zeros((height, width, 3))
NAN_idx = np.isnan(u) | np.isnan(v)
u[NAN_idx] = v[NAN_idx] = 0
colorwheel = make_color_wheel()
ncols = np.size(colorwheel, 0)
rad = np.sqrt(u ** 2 + v ** 2)
a = np.arctan2(-v, -u) / np.pi
fk = (a + 1) / 2 * (ncols - 1) + 1
k0 = np.floor(fk).astype(int)
k1 = k0 + 1
k1[k1 == ncols + 1] = 1
f = fk - k0
for i in range(0, np.size(colorwheel, 1)):
tmp = colorwheel[:, i]
col0 = tmp[k0 - 1] / 255
col1 = tmp[k1 - 1] / 255
col = (1 - f) * col0 + f * col1
idx = rad <= 1
col[idx] = 1 - rad[idx] * (1 - col[idx])
notidx = np.logical_not(idx)
col[notidx] *= 0.75
img[:, :, i] = np.uint8(np.floor(255 * col * (1 - NAN_idx)))
return img
def make_color_wheel():
"""
Generate color wheel according Middlebury color code
:return: Color wheel
"""
RY = 15
YG = 6
GC = 4
CB = 11
BM = 13
MR = 6
ncols = RY + YG + GC + CB + BM + MR
colorwheel = np.zeros([ncols, 3])
col = 0
# RY
colorwheel[0:RY, 0] = 255
colorwheel[0:RY, 1] = np.transpose(np.floor(255 * np.arange(0, RY) / RY))
col += RY
# YG
colorwheel[col:col + YG, 0] = 255 - \
np.transpose(np.floor(255 * np.arange(0, YG) / YG))
colorwheel[col:col + YG, 1] = 255
col += YG
# GC
colorwheel[col:col + GC, 1] = 255
colorwheel[col:col + GC,
2] = np.transpose(np.floor(255 * np.arange(0, GC) / GC))
col += GC
# CB
colorwheel[col:col + CB, 1] = 255 - \
np.transpose(np.floor(255 * np.arange(0, CB) / CB))
colorwheel[col:col + CB, 2] = 255
col += CB
# BM
colorwheel[col:col + BM, 2] = 255
colorwheel[col:col + BM,
0] = np.transpose(np.floor(255 * np.arange(0, BM) / BM))
col += + BM
# MR
colorwheel[col:col + MR, 2] = 255 - \
np.transpose(np.floor(255 * np.arange(0, MR) / MR))
colorwheel[col:col + MR, 0] = 255
return colorwheel
|