test_feature_homography.py 5.41 KB
Newer Older
wester committed
1 2 3
#!/usr/bin/env python

'''
wester committed
4
Feature homography
wester committed
5 6 7
==================

Example of using features2d framework for interactive video homography matching.
wester committed
8 9
ORB features and FLANN matcher are used. The actual tracking is implemented by
PlaneTracker class in plane_tracker.py
wester committed
10 11 12 13
'''

# Python 2/3 compatibility
from __future__ import print_function
wester committed
14 15 16

import numpy as np
import cv2
wester committed
17 18 19 20 21 22
import sys
PY3 = sys.version_info[0] == 3

if PY3:
    xrange = range

wester committed
23 24
# local modules
from tst_scene_render import TestSceneRender
wester committed
25

wester committed
26
def intersectionRate(s1, s2):
wester committed
27

wester committed
28 29 30 31 32
    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)))
wester committed
33

wester committed
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
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
wester committed
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

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):
wester committed
95
        self.detector = cv2.AKAZE_create(threshold = 0.003)
wester committed
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
        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)
wester committed
158
        if descrs is None:  # detectAndCompute returns descs=None if no keypoints found
wester committed
159
            descrs = []
wester committed
160
        return keypoints, descrs