mirror of
https://github.com/opencv/opencv.git
synced 2024-12-05 09:49:12 +08:00
160 lines
5.4 KiB
Python
160 lines
5.4 KiB
Python
#!/usr/bin/env python
|
|
|
|
'''
|
|
Feature homography
|
|
==================
|
|
|
|
Example of using features2d framework for interactive video homography matching.
|
|
ORB features and FLANN matcher are used. The actual tracking is implemented by
|
|
PlaneTracker class in plane_tracker.py
|
|
'''
|
|
|
|
# Python 2/3 compatibility
|
|
from __future__ import print_function
|
|
|
|
import numpy as np
|
|
import cv2
|
|
import sys
|
|
PY3 = sys.version_info[0] == 3
|
|
|
|
if PY3:
|
|
xrange = range
|
|
|
|
# local modules
|
|
from tst_scene_render import TestSceneRender
|
|
|
|
def intersectionRate(s1, s2):
|
|
|
|
x1, y1, x2, y2 = s1
|
|
s1 = np.array([[x1, y1], [x2,y1], [x2, y2], [x1, y2]])
|
|
|
|
area, intersection = cv2.intersectConvexConvex(s1, np.array(s2))
|
|
return 2 * area / (cv2.contourArea(s1) + cv2.contourArea(np.array(s2)))
|
|
|
|
from tests_common import NewOpenCVTests
|
|
|
|
class feature_homography_test(NewOpenCVTests):
|
|
|
|
render = None
|
|
tracker = None
|
|
framesCounter = 0
|
|
frame = None
|
|
|
|
def test_feature_homography(self):
|
|
|
|
self.render = TestSceneRender(self.get_sample('samples/data/graf1.png'),
|
|
self.get_sample('samples/data/box.png'), noise = 0.5, speed = 0.5)
|
|
self.frame = self.render.getNextFrame()
|
|
self.tracker = PlaneTracker()
|
|
self.tracker.clear()
|
|
self.tracker.add_target(self.frame, self.render.getCurrentRect())
|
|
|
|
while self.framesCounter < 100:
|
|
self.framesCounter += 1
|
|
tracked = self.tracker.track(self.frame)
|
|
if len(tracked) > 0:
|
|
tracked = tracked[0]
|
|
self.assertGreater(intersectionRate(self.render.getCurrentRect(), np.int32(tracked.quad)), 0.6)
|
|
else:
|
|
self.assertEqual(0, 1, 'Tracking error')
|
|
self.frame = self.render.getNextFrame()
|
|
|
|
|
|
# built-in modules
|
|
from collections import namedtuple
|
|
|
|
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
|
|
|
|
MIN_MATCH_COUNT = 10
|
|
|
|
'''
|
|
image - image to track
|
|
rect - tracked rectangle (x1, y1, x2, y2)
|
|
keypoints - keypoints detected inside rect
|
|
descrs - their descriptors
|
|
data - some user-provided data
|
|
'''
|
|
PlanarTarget = namedtuple('PlaneTarget', 'image, rect, keypoints, descrs, data')
|
|
|
|
'''
|
|
target - reference to PlanarTarget
|
|
p0 - matched points coords in target image
|
|
p1 - matched points coords in input frame
|
|
H - homography matrix from p0 to p1
|
|
quad - target bounary quad in input frame
|
|
'''
|
|
TrackedTarget = namedtuple('TrackedTarget', 'target, p0, p1, H, quad')
|
|
|
|
class PlaneTracker:
|
|
def __init__(self):
|
|
self.detector = cv2.AKAZE_create(threshold = 0.003)
|
|
self.matcher = cv2.FlannBasedMatcher(flann_params, {}) # bug : need to pass empty dict (#1329)
|
|
self.targets = []
|
|
self.frame_points = []
|
|
|
|
def add_target(self, image, rect, data=None):
|
|
'''Add a new tracking target.'''
|
|
x0, y0, x1, y1 = rect
|
|
raw_points, raw_descrs = self.detect_features(image)
|
|
points, descs = [], []
|
|
for kp, desc in zip(raw_points, raw_descrs):
|
|
x, y = kp.pt
|
|
if x0 <= x <= x1 and y0 <= y <= y1:
|
|
points.append(kp)
|
|
descs.append(desc)
|
|
descs = np.uint8(descs)
|
|
self.matcher.add([descs])
|
|
target = PlanarTarget(image = image, rect=rect, keypoints = points, descrs=descs, data=data)
|
|
self.targets.append(target)
|
|
|
|
def clear(self):
|
|
'''Remove all targets'''
|
|
self.targets = []
|
|
self.matcher.clear()
|
|
|
|
def track(self, frame):
|
|
'''Returns a list of detected TrackedTarget objects'''
|
|
self.frame_points, frame_descrs = self.detect_features(frame)
|
|
if len(self.frame_points) < MIN_MATCH_COUNT:
|
|
return []
|
|
matches = self.matcher.knnMatch(frame_descrs, k = 2)
|
|
matches = [m[0] for m in matches if len(m) == 2 and m[0].distance < m[1].distance * 0.75]
|
|
if len(matches) < MIN_MATCH_COUNT:
|
|
return []
|
|
matches_by_id = [[] for _ in xrange(len(self.targets))]
|
|
for m in matches:
|
|
matches_by_id[m.imgIdx].append(m)
|
|
tracked = []
|
|
for imgIdx, matches in enumerate(matches_by_id):
|
|
if len(matches) < MIN_MATCH_COUNT:
|
|
continue
|
|
target = self.targets[imgIdx]
|
|
p0 = [target.keypoints[m.trainIdx].pt for m in matches]
|
|
p1 = [self.frame_points[m.queryIdx].pt for m in matches]
|
|
p0, p1 = np.float32((p0, p1))
|
|
H, status = cv2.findHomography(p0, p1, cv2.RANSAC, 3.0)
|
|
status = status.ravel() != 0
|
|
if status.sum() < MIN_MATCH_COUNT:
|
|
continue
|
|
p0, p1 = p0[status], p1[status]
|
|
|
|
x0, y0, x1, y1 = target.rect
|
|
quad = np.float32([[x0, y0], [x1, y0], [x1, y1], [x0, y1]])
|
|
quad = cv2.perspectiveTransform(quad.reshape(1, -1, 2), H).reshape(-1, 2)
|
|
|
|
track = TrackedTarget(target=target, p0=p0, p1=p1, H=H, quad=quad)
|
|
tracked.append(track)
|
|
tracked.sort(key = lambda t: len(t.p0), reverse=True)
|
|
return tracked
|
|
|
|
def detect_features(self, frame):
|
|
'''detect_features(self, frame) -> keypoints, descrs'''
|
|
keypoints, descrs = self.detector.detectAndCompute(frame, None)
|
|
if descrs is None: # detectAndCompute returns descs=None if no keypoints found
|
|
descrs = []
|
|
return keypoints, descrs |