File size: 4,024 Bytes
320e465
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import numpy as np
from PIL import Image
from os.path import *
import re

import cv2
cv2.setNumThreads(0)
cv2.ocl.setUseOpenCL(False)

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 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.')

    dim_match = re.match(rb'^(\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 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 readDispKITTI(filename):
    disp = cv2.imread(filename, cv2.IMREAD_ANYDEPTH) / 256.0
    valid = disp > 0.0
    flow = np.stack([-disp, np.zeros_like(disp)], -1)
    return flow, valid


def writeFlowKITTI(filename, uv):
    uv = 64.0 * uv + 2**15
    valid = np.ones([uv.shape[0], uv.shape[1], 1])
    uv = np.concatenate([uv, valid], axis=-1).astype(np.uint16)
    cv2.imwrite(filename, uv[..., ::-1])
    

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':
        flow = readPFM(file_name).astype(np.float32)
        if len(flow.shape) == 2:
            return flow
        else:
            return flow[:, :, :-1]
    return []