安装
- 下载并安装opencv for windows
- 安装selenium：
pip install selenium
测试用图片
代码
''' Feature-based image matching sample. USAGE find_obj.py [--feature=<sift|surf|orb>[-flann]] [ <image1> <image2> ] --feature - Feature to use. Can be sift, surf of orb. Append '-flann' to feature name to use Flann-based matcher instead bruteforce. Press left mouse button on a feature point to see its mathcing point. '''
import numpy as np
import cv2
from common import anorm, getsize
from selenium import webdriver
browser = webdriver.Firefox()
url = "http://www.baike.com/wiki/%E4%B8%B9%E9%BA%A6%E8%93%9D%E7%BD%90%E6%9B%B2%E5%A5%87"
FLANN_INDEX_KDTREE = 1
FLANN_INDEX_LSH = 6
def init_feature(name):
chunks = name.split('-')
if chunks[0] == 'sift':
detector = cv2.SIFT()
norm = cv2.NORM_L2
elif chunks[0] == 'surf':
detector = cv2.SURF(800)
norm = cv2.NORM_L2
elif chunks[0] == 'orb':
detector = cv2.ORB(400)
norm = cv2.NORM_HAMMING
else:
return None, None
if 'flann' in chunks:
if norm == cv2.NORM_L2:
flann_params = dict(algorithm = FLANN_INDEX_KDTREE, trees = 5)
else:
flann_params= dict(algorithm = FLANN_INDEX_LSH,
table_number = 6,
key_size = 12,
multi_probe_level = 1)
matcher = cv2.FlannBasedMatcher(flann_params, {})
else:
matcher = cv2.BFMatcher(norm)
return detector, matcher
def filter_matches(kp1, kp2, matches, ratio = 0.75):
mkp1, mkp2 = [], []
for m in matches:
if len(m) == 2 and m[0].distance < m[1].distance * ratio:
m = m[0]
mkp1.append( kp1[m.queryIdx] )
mkp2.append( kp2[m.trainIdx] )
p1 = np.float32([kp.pt for kp in mkp1])
p2 = np.float32([kp.pt for kp in mkp2])
kp_pairs = zip(mkp1, mkp2)
return p1, p2, kp_pairs
def explore_match(win, img1, img2, kp_pairs, status = None, H = None):
h1, w1 = img1.shape[:2]
h2, w2 = img2.shape[:2]
vis = np.zeros((max(h1, h2), w1+w2), np.uint8)
vis[:h1, :w1] = img1
vis[:h2, w1:w1+w2] = img2
vis = cv2.cvtColor(vis, cv2.COLOR_GRAY2BGR)
if H is not None:
corners = np.float32([[0, 0], [w1, 0], [w1, h1], [0, h1]])
corners = np.int32( cv2.perspectiveTransform(corners.reshape(1, -1, 2), H).reshape(-1, 2) + (w1, 0) )
cv2.polylines(vis, [corners], True, (255, 255, 255))
if status is None:
status = np.ones(len(kp_pairs), np.bool_)
p1 = np.int32([kpp[0].pt for kpp in kp_pairs])
p2 = np.int32([kpp[1].pt for kpp in kp_pairs]) + (w1, 0)
green = (0, 255, 0)
red = (0, 0, 255)
white = (255, 255, 255)
kp_color = (51, 103, 236)
for (x1, y1), (x2, y2), inlier in zip(p1, p2, status):
if inlier:
col = green
cv2.circle(vis, (x1, y1), 2, col, -1)
cv2.circle(vis, (x2, y2), 2, col, -1)
else:
col = red
r = 2
thickness = 3
cv2.line(vis, (x1-r, y1-r), (x1+r, y1+r), col, thickness)
cv2.line(vis, (x1-r, y1+r), (x1+r, y1-r), col, thickness)
cv2.line(vis, (x2-r, y2-r), (x2+r, y2+r), col, thickness)
cv2.line(vis, (x2-r, y2+r), (x2+r, y2-r), col, thickness)
vis0 = vis.copy()
for (x1, y1), (x2, y2), inlier in zip(p1, p2, status):
if inlier:
cv2.line(vis, (x1, y1), (x2, y2), green)
cv2.imshow(win, vis)
def onmouse(event, x, y, flags, param):
cur_vis = vis
if flags & cv2.EVENT_FLAG_LBUTTON:
cur_vis = vis0.copy()
r = 8
m = (anorm(p1 - (x, y)) < r) | (anorm(p2 - (x, y)) < r)
idxs = np.where(m)[0]
kp1s, kp2s = [], []
for i in idxs:
(x1, y1), (x2, y2) = p1[i], p2[i]
col = (red, green)[status[i]]
cv2.line(cur_vis, (x1, y1), (x2, y2), col)
kp1, kp2 = kp_pairs[i]
kp1s.append(kp1)
kp2s.append(kp2)
cur_vis = cv2.drawKeypoints(cur_vis, kp1s, flags=4, color=kp_color)
cur_vis[:,w1:] = cv2.drawKeypoints(cur_vis[:,w1:], kp2s, flags=4, color=kp_color)
cv2.imshow(win, cur_vis)
cv2.setMouseCallback(win, onmouse)
return vis
if __name__ == '__main__':
print __doc__
import sys, getopt
opts, args = getopt.getopt(sys.argv[1:], '', ['feature='])
opts = dict(opts)
feature_name = opts.get('--feature', 'sift')
try: fn1, fn2 = args
except:
fn1 = '../c/box.png'
fn2 = '../c/box_in_scene.png'
img1 = cv2.imread(fn1, 0)
img2 = cv2.imread(fn2, 0)
detector, matcher = init_feature(feature_name)
if detector != None:
print 'using', feature_name
else:
print 'unknown feature:', feature_name
sys.exit(1)
kp1, desc1 = detector.detectAndCompute(img1, None)
kp2, desc2 = detector.detectAndCompute(img2, None)
print 'img1 - %d features, img2 - %d features' % (len(kp1), len(kp2))
def match_and_draw(win):
print 'matching...'
raw_matches = matcher.knnMatch(desc1, trainDescriptors = desc2, k = 2)
p1, p2, kp_pairs = filter_matches(kp1, kp2, raw_matches)
if len(p1) >= 4:
H, status = cv2.findHomography(p1, p2, cv2.RANSAC, 5.0)
print '%d / %d inliers/matched' % (np.sum(status), len(status))
if len(status) - np.sum(status) <= 20:
browser.get(url)
else:
H, status = None, None
print '%d matches found, not enough for homography estimation' % len(p1)
vis = explore_match(win, img1, img2, kp_pairs, status, H)
match_and_draw('find_obj')
cv2.waitKey()
cv2.destroyAllWindows()
''' This module contais some common routines used by other samples. '''
import numpy as np
import cv2
import os
from contextlib import contextmanager
import itertools as it
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]
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.CV_AA)
cv2.putText(dst, s, (x, y), cv2.FONT_HERSHEY_PLAIN, 1.0, (255, 255, 255), lineType=cv2.CV_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
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()
else:
self.prev_pt = None
_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])
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)
测试
- cmd命令：
python find_obj.py logo.jpg obj.jpg
