seeds: add C++ and python samples

modules/ximgproc/samples/seeds.cpp

+#include <opencv2/imgproc.hpp>
+#include <opencv2/highgui.hpp>
+#include <opencv2/imgcodecs.hpp>
+#include <opencv2/core/utility.hpp>
+
+#include <opencv2/ximgproc.hpp>
+
+#include <ctype.h>
+#include <stdio.h>
+#include <iostream>
+
+using namespace cv;
+using namespace cv::ximgproc;
+using namespace std;
+
+static void help()
+{
+    cout << "\nThis program demonstrates SEEDS superpixels using OpenCV class SuperpixelSEEDS\n"
+            "Use [space] to toggle output mode\n"
+            "\n"
+            "It captures either from the camera of your choice: 0, 1, ... default 0\n"
+            "Or from an input image\n"
+            "Call:\n"
+            "./seeds [camera #, default 0]\n"
+            "./seeds [input image file]\n" << endl;
+}
+
+static const char* window_name = "SEEDS Superpixels";
+
+static bool init = false;
+
+void trackbarChanged(int pos, void* data)
+{
+    init = false;
+}
+
+
+int main(int argc, char** argv)
+{
+    VideoCapture cap;
+    Mat input_image;
+    bool use_video_capture = false;
+    help();
+
+    if( argc == 1 || (argc == 2 && strlen(argv[1]) == 1 && isdigit(argv[1][0])) )
+    {
+        cap.open(argc == 2 ? argv[1][0] - '0' : 0);
+        use_video_capture = true;
+    }
+    else if( argc >= 2 )
+    {
+        input_image = imread(argv[1]);
+    }
+
+    if( use_video_capture )
+    {
+        if( !cap.isOpened() )
+        {
+            cout << "Could not initialize capturing...\n";
+            return -1;
+        }
+    }
+    else if( input_image.empty() )
+    {
+        cout << "Could not open image...\n";
+        return -1;
+    }
+
+    namedWindow(window_name, 0);
+    int num_iterations = 4;
+    int prior = 2;
+    bool double_step = false;
+    int num_superpixels = 400;
+    int num_levels = 4;
+    int num_histogram_bins = 5;
+    createTrackbar("Number of Superpixels", window_name, &num_superpixels, 1000, trackbarChanged);
+    createTrackbar("Smoothing Prior", window_name, &prior, 5, trackbarChanged);
+    createTrackbar("Number of Levels", window_name, &num_levels, 10, trackbarChanged);
+    createTrackbar("Iterations", window_name, &num_iterations, 12, 0);
+
+    Mat result, mask;
+    Ptr<SuperpixelSEEDS> seeds;
+    int width, height;
+    int display_mode = 0;
+
+    for (;;)
+    {
+        Mat frame;
+        if( use_video_capture )
+            cap >> frame;
+        else
+            input_image.copyTo(frame);
+
+        if( frame.empty() )
+            break;
+
+        if( !init )
+        {
+            width = frame.size().width;
+            height = frame.size().height;
+            seeds = createSuperpixelSEEDS(width, height, frame.channels(), num_superpixels,
+                    num_levels, prior, num_histogram_bins, double_step);
+            init = true;
+        }
+        Mat converted;
+        cvtColor(frame, converted, COLOR_BGR2HSV);
+
+        double t = (double) getTickCount();
+
+        seeds->iterate(converted, num_iterations);
+        result = frame;
+
+        t = ((double) getTickCount() - t) / getTickFrequency();
+        printf("SEEDS segmentation took %i ms with %3i superpixels\n",
+                (int) (t * 1000), seeds->getNumberOfSuperpixels());
+
+        /* retrieve the segmentation result */
+        Mat labels;
+        seeds->getLabels(labels);
+
+        /* get the contours for displaying */
+        seeds->getLabelContourMask(mask, false);
+        result.setTo(Scalar(0, 0, 255), mask);
+
+        /* display output */
+        switch (display_mode)
+        {
+        case 0: //superpixel contours
+            imshow(window_name, result);
+            break;
+        case 1: //mask
+            imshow(window_name, mask);
+            break;
+        case 2: //labels array
+        {
+            // use the last x bit to determine the color. Note that this does not
+            // guarantee that 2 neighboring superpixels have different colors.
+            const int num_label_bits = 2;
+            labels &= (1 << num_label_bits) - 1;
+            labels *= 1 << (16 - num_label_bits);
+            imshow(window_name, labels);
+        }
+            break;
+        }
+
+
+        int c = waitKey(1);
+        if( (c & 255) == 'q' || c == 'Q' || (c & 255) == 27 )
+            break;
+        else if( (c & 255) == ' ' )
+            display_mode = (display_mode + 1) % 3;
+    }
+
+    return 0;
+}

samples/python2/common.py

+#!/usr/bin/env python
+
+'''
+This module contains some common routines used by other samples.
+'''
+
+import numpy as np
+import cv2
+
+# built-in modules
+import os
+import itertools as it
+from contextlib import contextmanager
+
+image_extensions = ['.bmp', '.jpg', '.jpeg', '.png', '.tif', '.tiff', '.pbm', '.pgm', '.ppm']
+
+class Bunch(object):
+    def __init__(self, **kw):
+        self.__dict__.update(kw)
+    def __str__(self):
+        return str(self.__dict__)
+
+def splitfn(fn):
+    path, fn = os.path.split(fn)
+    name, ext = os.path.splitext(fn)
+    return path, name, ext
+
+def anorm2(a):
+    return (a*a).sum(-1)
+def anorm(a):
+    return np.sqrt( anorm2(a) )
+
+def homotrans(H, x, y):
+    xs = H[0, 0]*x + H[0, 1]*y + H[0, 2]
+    ys = H[1, 0]*x + H[1, 1]*y + H[1, 2]
+    s  = H[2, 0]*x + H[2, 1]*y + H[2, 2]
+    return xs/s, ys/s
+
+def to_rect(a):
+    a = np.ravel(a)
+    if len(a) == 2:
+        a = (0, 0, a[0], a[1])
+    return np.array(a, np.float64).reshape(2, 2)
+
+def rect2rect_mtx(src, dst):
+    src, dst = to_rect(src), to_rect(dst)
+    cx, cy = (dst[1] - dst[0]) / (src[1] - src[0])
+    tx, ty = dst[0] - src[0] * (cx, cy)
+    M = np.float64([[ cx,  0, tx],
+                    [  0, cy, ty],
+                    [  0,  0,  1]])
+    return M
+
+
+def lookat(eye, target, up = (0, 0, 1)):
+    fwd = np.asarray(target, np.float64) - eye
+    fwd /= anorm(fwd)
+    right = np.cross(fwd, up)
+    right /= anorm(right)
+    down = np.cross(fwd, right)
+    R = np.float64([right, down, fwd])
+    tvec = -np.dot(R, eye)
+    return R, tvec
+
+def mtx2rvec(R):
+    w, u, vt = cv2.SVDecomp(R - np.eye(3))
+    p = vt[0] + u[:,0]*w[0]    # same as np.dot(R, vt[0])
+    c = np.dot(vt[0], p)
+    s = np.dot(vt[1], p)
+    axis = np.cross(vt[0], vt[1])
+    return axis * np.arctan2(s, c)
+
+def draw_str(dst, (x, y), s):
+    cv2.putText(dst, s, (x+1, y+1), cv2.FONT_HERSHEY_PLAIN, 1.0, (0, 0, 0), thickness = 2, lineType=cv2.LINE_AA)
+    cv2.putText(dst, s, (x, y), cv2.FONT_HERSHEY_PLAIN, 1.0, (255, 255, 255), lineType=cv2.LINE_AA)
+
+class Sketcher:
+    def __init__(self, windowname, dests, colors_func):
+        self.prev_pt = None
+        self.windowname = windowname
+        self.dests = dests
+        self.colors_func = colors_func
+        self.dirty = False
+        self.show()
+        cv2.setMouseCallback(self.windowname, self.on_mouse)
+
+    def show(self):
+        cv2.imshow(self.windowname, self.dests[0])
+
+    def on_mouse(self, event, x, y, flags, param):
+        pt = (x, y)
+        if event == cv2.EVENT_LBUTTONDOWN:
+            self.prev_pt = pt
+        elif event == cv2.EVENT_LBUTTONUP:
+            self.prev_pt = None
+
+        if self.prev_pt and flags & cv2.EVENT_FLAG_LBUTTON:
+            for dst, color in zip(self.dests, self.colors_func()):
+                cv2.line(dst, self.prev_pt, pt, color, 5)
+            self.dirty = True
+            self.prev_pt = pt
+            self.show()
+
+
+# palette data from matplotlib/_cm.py
+_jet_data =   {'red':   ((0., 0, 0), (0.35, 0, 0), (0.66, 1, 1), (0.89,1, 1),
+                         (1, 0.5, 0.5)),
+               'green': ((0., 0, 0), (0.125,0, 0), (0.375,1, 1), (0.64,1, 1),
+                         (0.91,0,0), (1, 0, 0)),
+               'blue':  ((0., 0.5, 0.5), (0.11, 1, 1), (0.34, 1, 1), (0.65,0, 0),
+                         (1, 0, 0))}
+
+cmap_data = { 'jet' : _jet_data }
+
+def make_cmap(name, n=256):
+    data = cmap_data[name]
+    xs = np.linspace(0.0, 1.0, n)
+    channels = []
+    eps = 1e-6
+    for ch_name in ['blue', 'green', 'red']:
+        ch_data = data[ch_name]
+        xp, yp = [], []
+        for x, y1, y2 in ch_data:
+            xp += [x, x+eps]
+            yp += [y1, y2]
+        ch = np.interp(xs, xp, yp)
+        channels.append(ch)
+    return np.uint8(np.array(channels).T*255)
+
+def nothing(*arg, **kw):
+    pass
+
+def clock():
+    return cv2.getTickCount() / cv2.getTickFrequency()
+
+@contextmanager
+def Timer(msg):
+    print msg, '...',
+    start = clock()
+    try:
+        yield
+    finally:
+        print "%.2f ms" % ((clock()-start)*1000)
+
+class StatValue:
+    def __init__(self, smooth_coef = 0.5):
+        self.value = None
+        self.smooth_coef = smooth_coef
+    def update(self, v):
+        if self.value is None:
+            self.value = v
+        else:
+            c = self.smooth_coef
+            self.value = c * self.value + (1.0-c) * v
+
+class RectSelector:
+    def __init__(self, win, callback):
+        self.win = win
+        self.callback = callback
+        cv2.setMouseCallback(win, self.onmouse)
+        self.drag_start = None
+        self.drag_rect = None
+    def onmouse(self, event, x, y, flags, param):
+        x, y = np.int16([x, y]) # BUG
+        if event == cv2.EVENT_LBUTTONDOWN:
+            self.drag_start = (x, y)
+        if self.drag_start:
+            if flags & cv2.EVENT_FLAG_LBUTTON:
+                xo, yo = self.drag_start
+                x0, y0 = np.minimum([xo, yo], [x, y])
+                x1, y1 = np.maximum([xo, yo], [x, y])
+                self.drag_rect = None
+                if x1-x0 > 0 and y1-y0 > 0:
+                    self.drag_rect = (x0, y0, x1, y1)
+            else:
+                rect = self.drag_rect
+                self.drag_start = None
+                self.drag_rect = None
+                if rect:
+                    self.callback(rect)
+    def draw(self, vis):
+        if not self.drag_rect:
+            return False
+        x0, y0, x1, y1 = self.drag_rect
+        cv2.rectangle(vis, (x0, y0), (x1, y1), (0, 255, 0), 2)
+        return True
+    @property
+    def dragging(self):
+        return self.drag_rect is not None
+
+
+def grouper(n, iterable, fillvalue=None):
+    '''grouper(3, 'ABCDEFG', 'x') --> ABC DEF Gxx'''
+    args = [iter(iterable)] * n
+    return it.izip_longest(fillvalue=fillvalue, *args)
+
+def mosaic(w, imgs):
+    '''Make a grid from images.
+
+    w    -- number of grid columns
+    imgs -- images (must have same size and format)
+    '''
+    imgs = iter(imgs)
+    img0 = imgs.next()
+    pad = np.zeros_like(img0)
+    imgs = it.chain([img0], imgs)
+    rows = grouper(w, imgs, pad)
+    return np.vstack(map(np.hstack, rows))
+
+def getsize(img):
+    h, w = img.shape[:2]
+    return w, h
+
+def mdot(*args):
+    return reduce(np.dot, args)
+
+def draw_keypoints(vis, keypoints, color = (0, 255, 255)):
+    for kp in keypoints:
+            x, y = kp.pt
+            cv2.circle(vis, (int(x), int(y)), 2, color)

samples/python2/seeds.py

+#!/usr/bin/env python
+
+'''
+This sample demonstrates SEEDS Superpixels segmentation
+Use [space] to toggle output mode
+
+Usage:
+  seeds.py [<video source>]
+
+'''
+
+import numpy as np
+import cv2
+
+# relative module
+import video
+
+# built-in module
+import sys
+
+
+if __name__ == '__main__':
+    print __doc__
+
+    try:
+        fn = sys.argv[1]
+    except:
+        fn = 0
+
+    def nothing(*arg):
+        pass
+
+    cv2.namedWindow('SEEDS')
+    cv2.createTrackbar('Number of Superpixels', 'SEEDS', 400, 1000, nothing)
+    cv2.createTrackbar('Iterations', 'SEEDS', 4, 12, nothing)
+
+    seeds = None
+    display_mode = 0
+    num_superpixels = 400
+    prior = 2
+    num_levels = 4
+    num_histogram_bins = 5
+
+    cap = video.create_capture(fn)
+    while True:
+        flag, img = cap.read()
+        converted_img = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
+        height,width,channels = converted_img.shape
+        num_superpixels_new = cv2.getTrackbarPos('Number of Superpixels', 'SEEDS')
+        num_iterations = cv2.getTrackbarPos('Iterations', 'SEEDS')
+
+        if not seeds or num_superpixels_new != num_superpixels:
+            num_superpixels = num_superpixels_new
+            seeds = cv2.ximgproc.createSuperpixelSEEDS(width, height, channels,
+                    num_superpixels, num_levels, prior, num_histogram_bins)
+            color_img = np.zeros((height,width,3), np.uint8)
+            color_img[:] = (0, 0, 255)
+
+        seeds.iterate(converted_img, num_iterations)
+
+        # retrieve the segmentation result
+        labels = seeds.getLabels()
+
+
+        # labels output: use the last x bits to determine the color
+        num_label_bits = 2
+        labels &= (1<<num_label_bits)-1
+        labels *= 1<<(16-num_label_bits)
+
+
+        mask = seeds.getLabelContourMask(False)
+
+        # stitch foreground & background together
+        mask_inv = cv2.bitwise_not(mask)
+        result_bg = cv2.bitwise_and(img, img, mask=mask_inv)
+        result_fg = cv2.bitwise_and(color_img, color_img, mask=mask)
+        result = cv2.add(result_bg, result_fg)
+
+        if display_mode == 0:
+            cv2.imshow('SEEDS', result)
+        elif display_mode == 1:
+            cv2.imshow('SEEDS', mask)
+        else:
+            cv2.imshow('SEEDS', labels)
+
+        ch = cv2.waitKey(1)
+        if ch == 27:
+            break
+        elif ch & 0xff == ord(' '):
+            display_mode = (display_mode + 1) % 3
+    cv2.destroyAllWindows()

samples/python2/video.py

+#!/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()