video.py 5.69 KB
Newer Older
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
#!/usr/bin/env python

'''
Video capture sample.

Sample shows how VideoCapture class can be used to acquire video
frames from a camera of a movie file. Also the sample provides
an example of procedural video generation by an object, mimicking
the VideoCapture interface (see Chess class).

'create_capture' is a convinience function for capture creation,
falling back to procedural video in case of error.

Usage:
    video.py [--shotdir <shot path>] [source0] [source1] ...'

    sourceN is an
     - integer number for camera capture
     - name of video file
     - synth:<params> for procedural video

Synth examples:
    synth:bg=../cpp/lena.jpg:noise=0.1
    synth:class=chess:bg=../cpp/lena.jpg:noise=0.1:size=640x480

Keys:
    ESC    - exit
    SPACE  - save current frame to <shot path> directory

'''

import numpy as np
from numpy import pi, sin, cos

import cv2

# built-in modules
from time import clock

# local modules
import common

class VideoSynthBase(object):
    def __init__(self, size=None, noise=0.0, bg = None, **params):
        self.bg = None
        self.frame_size = (640, 480)
        if bg is not None:
            self.bg = cv2.imread(bg, 1)
            h, w = self.bg.shape[:2]
            self.frame_size = (w, h)

        if size is not None:
            w, h = map(int, size.split('x'))
            self.frame_size = (w, h)
            self.bg = cv2.resize(self.bg, self.frame_size)

        self.noise = float(noise)

    def render(self, dst):
        pass

    def read(self, dst=None):
        w, h = self.frame_size

        if self.bg is None:
            buf = np.zeros((h, w, 3), np.uint8)
        else:
            buf = self.bg.copy()

        self.render(buf)

        if self.noise > 0.0:
            noise = np.zeros((h, w, 3), np.int8)
            cv2.randn(noise, np.zeros(3), np.ones(3)*255*self.noise)
            buf = cv2.add(buf, noise, dtype=cv2.CV_8UC3)
        return True, buf

    def isOpened(self):
        return True

class Chess(VideoSynthBase):
    def __init__(self, **kw):
        super(Chess, self).__init__(**kw)

        w, h = self.frame_size

        self.grid_size = sx, sy = 10, 7
        white_quads = []
        black_quads = []
        for i, j in np.ndindex(sy, sx):
            q = [[j, i, 0], [j+1, i, 0], [j+1, i+1, 0], [j, i+1, 0]]
            [white_quads, black_quads][(i + j) % 2].append(q)
        self.white_quads = np.float32(white_quads)
        self.black_quads = np.float32(black_quads)

        fx = 0.9
        self.K = np.float64([[fx*w, 0, 0.5*(w-1)],
                        [0, fx*w, 0.5*(h-1)],
                        [0.0,0.0,      1.0]])

        self.dist_coef = np.float64([-0.2, 0.1, 0, 0])
        self.t = 0

    def draw_quads(self, img, quads, color = (0, 255, 0)):
        img_quads = cv2.projectPoints(quads.reshape(-1, 3), self.rvec, self.tvec, self.K, self.dist_coef) [0]
        img_quads.shape = quads.shape[:2] + (2,)
        for q in img_quads:
            cv2.fillConvexPoly(img, np.int32(q*4), color, cv2.LINE_AA, shift=2)

    def render(self, dst):
        t = self.t
        self.t += 1.0/30.0

        sx, sy = self.grid_size
        center = np.array([0.5*sx, 0.5*sy, 0.0])
        phi = pi/3 + sin(t*3)*pi/8
        c, s = cos(phi), sin(phi)
        ofs = np.array([sin(1.2*t), cos(1.8*t), 0]) * sx * 0.2
        eye_pos = center + np.array([cos(t)*c, sin(t)*c, s]) * 15.0 + ofs
        target_pos = center + ofs

        R, self.tvec = common.lookat(eye_pos, target_pos)
        self.rvec = common.mtx2rvec(R)

        self.draw_quads(dst, self.white_quads, (245, 245, 245))
        self.draw_quads(dst, self.black_quads, (10, 10, 10))


classes = dict(chess=Chess)

presets = dict(
    empty = 'synth:',
    lena = 'synth:bg=../cpp/lena.jpg:noise=0.1',
    chess = 'synth:class=chess:bg=../cpp/lena.jpg:noise=0.1:size=640x480'
)


def create_capture(source = 0, fallback = presets['chess']):
    '''source: <int> or '<int>|<filename>|synth [:<param_name>=<value> [:...]]'
    '''
    source = str(source).strip()
    chunks = source.split(':')
    # handle drive letter ('c:', ...)
    if len(chunks) > 1 and len(chunks[0]) == 1 and chunks[0].isalpha():
        chunks[1] = chunks[0] + ':' + chunks[1]
        del chunks[0]

    source = chunks[0]
    try: source = int(source)
    except ValueError: pass
    params = dict( s.split('=') for s in chunks[1:] )

    cap = None
    if source == 'synth':
        Class = classes.get(params.get('class', None), VideoSynthBase)
        try: cap = Class(**params)
        except: pass
    else:
        cap = cv2.VideoCapture(source)
        if 'size' in params:
            w, h = map(int, params['size'].split('x'))
            cap.set(cv2.CAP_PROP_FRAME_WIDTH, w)
            cap.set(cv2.CAP_PROP_FRAME_HEIGHT, h)
    if cap is None or not cap.isOpened():
        print 'Warning: unable to open video source: ', source
        if fallback is not None:
            return create_capture(fallback, None)
    return cap

if __name__ == '__main__':
    import sys
    import getopt

    print __doc__

    args, sources = getopt.getopt(sys.argv[1:], '', 'shotdir=')
    args = dict(args)
    shotdir = args.get('--shotdir', '.')
    if len(sources) == 0:
        sources = [ 0 ]

    caps = map(create_capture, sources)
    shot_idx = 0
    while True:
        imgs = []
        for i, cap in enumerate(caps):
            ret, img = cap.read()
            imgs.append(img)
            cv2.imshow('capture %d' % i, img)
        ch = 0xFF & cv2.waitKey(1)
        if ch == 27:
            break
        if ch == ord(' '):
            for i, img in enumerate(imgs):
                fn = '%s/shot_%d_%03d.bmp' % (shotdir, i, shot_idx)
                cv2.imwrite(fn, img)
                print fn, 'saved'
            shot_idx += 1
    cv2.destroyAllWindows()