File size: 5,170 Bytes
899c526
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import numpy as np
from PIL import Image
from os.path import *
import re
import cv2
cv2.setNumThreads(0)


TAG_CHAR = np.array([202021.25], np.float32)

def readFlowKITTI(filename):
    flow = cv2.imread(filename, cv2.IMREAD_ANYDEPTH|cv2.IMREAD_COLOR)
    flow = flow[:,:,::-1].astype(np.float32)
    flow, valid = flow[:, :, :2], flow[:, :, 2]
    flow = (flow - 2**15) / 64.0
    return flow, valid

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 readPFM(file):
    file = open(file, 'rb')

    color = None
    width = None
    height = None
    scale = None
    endian = None

    header = file.readline().rstrip()
    if header == b'PF':
        color = True
    elif header == b'Pf':
        color = False
    else:
        raise Exception('Not a PFM file.')

    try:
        dim_match = re.match(rb'^(\d+)\s(\d+)\s$', file.readline())
    except:
        dim_match = re.match(r'^(\d+)\s(\d+)\s$', file.readline())

    if dim_match:
        width, height = map(int, dim_match.groups())
    else:
        raise Exception('Malformed PFM header.')

    scale = float(file.readline().rstrip())
    if scale < 0: # little-endian
        endian = '<'
        scale = -scale
    else:
        endian = '>' # big-endian

    data = np.fromfile(file, endian + 'f')
    shape = (height, width, 3) if color else (height, width)

    data = np.reshape(data, shape)
    data = np.flipud(data)
    return data


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 depth.
    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()


def readDPT(filename):
    """ Read depth data from file, return as numpy array. """
    f = open(filename,'rb')
    check = np.fromfile(f,dtype=np.float32,count=1)[0]
    TAG_FLOAT = 202021.25
    TAG_CHAR = 'PIEH'
    assert check == TAG_FLOAT, ' depth_read:: Wrong tag in flow file (should be: {0}, is: {1}). Big-endian machine? '.format(TAG_FLOAT,check)
    width = np.fromfile(f,dtype=np.int32,count=1)[0]
    height = np.fromfile(f,dtype=np.int32,count=1)[0]
    size = width*height
    assert width > 0 and height > 0 and size > 1 and size < 100000000, ' depth_read:: Wrong input size (width = {0}, height = {1}).'.format(width,height)
    depth = np.fromfile(f,dtype=np.float32,count=-1).reshape((height,width))
    return depth

def cam_read(filename):
    """ Read camera data, return (M,N) tuple.
    M is the intrinsic matrix, N is the extrinsic matrix, so that
    x = M*N*X,
    with x being a point in homogeneous image pixel coordinates, X being a
    point in homogeneous world coordinates."""
    f = open(filename,'rb')
    check = np.fromfile(f,dtype=np.float32,count=1)[0]
    M = np.fromfile(f,dtype='float64',count=9).reshape((3,3))
    N = np.fromfile(f,dtype='float64',count=12).reshape((3,4))

    E = np.eye(4)
    E[0:3,:] = N

    fx, fy, cx, cy = M[0,0], M[1,1], M[0,2], M[1,2]
    kvec = np.array([fx, fy, cx, cy])

    q = Rotation.from_matrix(E[:3,:3]).as_quat()
    pvec = np.concatenate([E[:3,3], q], 0)

    return pvec, kvec


def read_gen(file_name, pil=False):
    ext = splitext(file_name)[-1]
    if ext == '.png' or ext == '.jpeg' or ext == '.ppm' or ext == '.jpg':
        return Image.open(file_name)
    elif ext == '.bin' or ext == '.raw':
        return np.load(file_name)
    elif ext == '.flo':
        return readFlow(file_name).astype(np.float32)
    elif ext == '.pfm':
        return readPFM(file_name).astype(np.float32)
    elif ext == '.dpt':
        return readDPT(file_name).astype(np.float32)
    elif ext == '.cam':
        return cam_read(file_name)
    return []