mirror of
https://github.com/opencv/opencv.git
synced 2025-01-18 14:13:15 +08:00
new feature_homography.py sample
This commit is contained in:
Alexander Mordvintsev
parent
c6705fbe20
commit
a2c3c1800a
@ -151,12 +151,9 @@ class RectSelector:
|
||||
self.drag_start = (x, y)
|
||||
if self.drag_start:
|
||||
if flags & cv2.EVENT_FLAG_LBUTTON:
|
||||
#h, w = self.frame.shape[:2]
|
||||
xo, yo = self.drag_start
|
||||
x0, y0 = np.minimum([xo, yo], [x, y])
|
||||
x1, y1 = np.maximum([xo, yo], [x, y])
|
||||
#x0, y0 = np.maximum(0, np.minimum([xo, yo], [x, y]))
|
||||
#x1, y1 = np.minimum([w, h], 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)
|
||||
@ -168,9 +165,13 @@ class RectSelector:
|
||||
self.callback(rect)
|
||||
def draw(self, vis):
|
||||
if not self.drag_rect:
|
||||
return
|
||||
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):
|
||||
|
||||
@ -3,94 +3,135 @@ Feature homography
|
||||
==================
|
||||
|
||||
Example of using features2d framework for interactive video homography matching.
|
||||
ORB features and FLANN matcher are used.
|
||||
|
||||
Inspired by http://www.youtube.com/watch?v=-ZNYoL8rzPY
|
||||
|
||||
Usage
|
||||
-----
|
||||
feature_homography.py [<video source>]
|
||||
|
||||
Keys
|
||||
----
|
||||
SPACE - set reference frame
|
||||
ESC - exit
|
||||
'''
|
||||
Select a textured planar object to track by drawing a box with a mouse.
|
||||
|
||||
'''
|
||||
|
||||
import numpy as np
|
||||
import cv2
|
||||
import video
|
||||
from common import draw_str, clock
|
||||
import sys
|
||||
import common
|
||||
from operator import attrgetter
|
||||
|
||||
def get_size(a):
|
||||
h, w = a.shape[:2]
|
||||
return w, h
|
||||
|
||||
detector = cv2.FastFeatureDetector(16, True)
|
||||
detector = cv2.GridAdaptedFeatureDetector(detector)
|
||||
extractor = cv2.DescriptorExtractor_create('ORB')
|
||||
|
||||
|
||||
FLANN_INDEX_KDTREE = 1
|
||||
FLANN_INDEX_LSH = 6
|
||||
flann_params= dict(algorithm = FLANN_INDEX_LSH,
|
||||
table_number = 6, # 12
|
||||
key_size = 12, # 20
|
||||
multi_probe_level = 1) #2
|
||||
matcher = cv2.FlannBasedMatcher(flann_params, {}) # bug : need to pass empty dict (#1329)
|
||||
|
||||
green, red = (0, 255, 0), (0, 0, 255)
|
||||
|
||||
MIN_MATCH_COUNT = 10
|
||||
|
||||
class App:
|
||||
def __init__(self, src):
|
||||
self.cap = video.create_capture(src)
|
||||
self.ref_frame = None
|
||||
|
||||
self.detector = cv2.ORB( nfeatures = 1000 )
|
||||
self.matcher = cv2.FlannBasedMatcher(flann_params, {}) # bug : need to pass empty dict (#1329)
|
||||
|
||||
cv2.namedWindow('plane')
|
||||
self.rect_sel = common.RectSelector('plane', self.on_rect)
|
||||
|
||||
self.frame = None
|
||||
|
||||
def match_frames(self):
|
||||
if len(self.frame_desc) < MIN_MATCH_COUNT or len(self.frame_desc) < MIN_MATCH_COUNT:
|
||||
return
|
||||
|
||||
raw_matches = self.matcher.knnMatch(self.ref_descs, trainDescriptors = self.frame_desc, k = 2)
|
||||
p0, p1 = [], []
|
||||
for m in raw_matches:
|
||||
if len(m) == 2 and m[0].distance < m[1].distance * 0.75:
|
||||
m = m[0]
|
||||
p0.append( self.ref_points[m.queryIdx].pt )
|
||||
p1.append( self.frame_points[m.trainIdx].pt )
|
||||
p0, p1 = np.float32((p0, p1))
|
||||
if len(p0) < MIN_MATCH_COUNT:
|
||||
return
|
||||
|
||||
H, status = cv2.findHomography(p0, p1, cv2.RANSAC, 4.0)
|
||||
status = status.ravel() != 0
|
||||
if status.sum() < MIN_MATCH_COUNT:
|
||||
return
|
||||
p0, p1 = p0[status], p1[status]
|
||||
return p0, p1, H
|
||||
|
||||
|
||||
def on_frame(self, frame):
|
||||
if self.frame is None or not self.rect_sel.dragging:
|
||||
self.frame = frame = np.fliplr(frame).copy()
|
||||
self.frame_points, self.frame_desc = self.detector.detectAndCompute(self.frame, None)
|
||||
if self.frame_desc is None: # detectAndCompute returns descs=None if not keypoints found
|
||||
self.frame_desc = []
|
||||
else:
|
||||
self.ref_frame = None
|
||||
|
||||
w, h = get_size(self.frame)
|
||||
vis = np.zeros((h, w*2, 3), np.uint8)
|
||||
vis[:h,:w] = self.frame
|
||||
self.rect_sel.draw(vis)
|
||||
|
||||
if self.ref_frame is not None:
|
||||
vis[:h,w:] = self.ref_frame
|
||||
x0, y0, x1, y1 = self.ref_rect
|
||||
cv2.rectangle(vis, (x0+w, y0), (x1+w, y1), (0, 255, 0), 2)
|
||||
|
||||
for kp in self.ref_points:
|
||||
x, y = kp.pt
|
||||
cv2.circle(vis, (int(x+w), int(y)), 2, (0, 255, 255))
|
||||
|
||||
|
||||
match = self.match_frames()
|
||||
if match is not None:
|
||||
p0, p1, H = match
|
||||
for (x0, y0), (x1, y1) in zip(np.int32(p0), np.int32(p1)):
|
||||
cv2.line(vis, (x0+w, y0), (x1, y1), (0, 255, 0))
|
||||
x0, y0, x1, y1 = self.ref_rect
|
||||
corners = np.float32([[x0, y0], [x1, y0], [x1, y1], [x0, y1]])
|
||||
corners = np.int32( cv2.perspectiveTransform(corners.reshape(1, -1, 2), H) )
|
||||
cv2.polylines(vis, [corners], True, (255, 255, 255), 2)
|
||||
|
||||
cv2.imshow('plane', vis)
|
||||
|
||||
def on_rect(self, rect):
|
||||
x0, y0, x1, y1 = rect
|
||||
self.ref_frame = self.frame.copy()
|
||||
self.ref_rect = rect
|
||||
points, descs = [], []
|
||||
for kp, desc in zip(self.frame_points, self.frame_desc):
|
||||
x, y = kp.pt
|
||||
if x0 <= x <= x1 and y0 <= y <= y1:
|
||||
points.append(kp)
|
||||
descs.append(desc)
|
||||
self.ref_points, self.ref_descs = points, np.uint8(descs)
|
||||
|
||||
def run(self):
|
||||
while True:
|
||||
ret, frame = self.cap.read()
|
||||
self.on_frame(frame)
|
||||
ch = cv2.waitKey(1)
|
||||
if ch == 27:
|
||||
break
|
||||
|
||||
if __name__ == '__main__':
|
||||
print __doc__
|
||||
|
||||
try: src = sys.argv[1]
|
||||
except: src = 0
|
||||
cap = video.create_capture(src)
|
||||
|
||||
ref_kp = None
|
||||
|
||||
while True:
|
||||
ret, img = cap.read()
|
||||
vis = img.copy()
|
||||
kp = detector.detect(img)
|
||||
kp, desc = extractor.compute(img, kp)
|
||||
|
||||
for p in kp:
|
||||
x, y = np.int32(p.pt)
|
||||
r = int(0.5*p.size)
|
||||
cv2.circle(vis, (x, y), r, (0, 255, 0))
|
||||
draw_str(vis, (20, 20), 'feature_n: %d' % len(kp))
|
||||
|
||||
if ref_kp is not None:
|
||||
raw_matches = matcher.knnMatch(desc, 2)
|
||||
matches = []
|
||||
for m in raw_matches:
|
||||
if len(m) == 2:
|
||||
m1, m2 = m
|
||||
if m1.distance < m2.distance * 0.7:
|
||||
matches.append((m1.trainIdx, m1.queryIdx))
|
||||
match_n = len(matches)
|
||||
|
||||
inlier_n = 0
|
||||
if match_n > 10:
|
||||
p0 = np.float32( [ref_kp[i].pt for i, j in matches] )
|
||||
p1 = np.float32( [kp[j].pt for i, j in matches] )
|
||||
|
||||
H, status = cv2.findHomography(p0, p1, cv2.RANSAC, 10.0)
|
||||
inlier_n = sum(status)
|
||||
if inlier_n > 10:
|
||||
for (x1, y1), (x2, y2), inlier in zip(np.int32(p0), np.int32(p1), status):
|
||||
cv2.line(vis, (x1, y1), (x2, y2), (red, green)[inlier])
|
||||
|
||||
h, w = img.shape[:2]
|
||||
overlay = cv2.warpPerspective(ref_img, H, (w, h))
|
||||
vis = cv2.addWeighted(vis, 0.5, overlay, 0.5, 0.0)
|
||||
draw_str(vis, (20, 40), 'matched: %d ( %d outliers )' % (match_n, match_n-inlier_n))
|
||||
|
||||
cv2.imshow('img', vis)
|
||||
ch = 0xFF & cv2.waitKey(1)
|
||||
if ch == ord(' '):
|
||||
matcher.clear()
|
||||
matcher.add([desc])
|
||||
ref_kp = kp
|
||||
ref_img = img.copy()
|
||||
if ch == 27:
|
||||
break
|
||||
cv2.destroyAllWindows()
|
||||
import sys
|
||||
try: video_src = sys.argv[1]
|
||||
except: video_src = '0'
|
||||
App(video_src).run()
|
||||
|
||||
Loading…
Reference in New Issue
Block a user