def __init__(
self,
num_features=kMinNumFeatureDefault,
num_levels=3, # number of pyramid levels for detector
scale_factor=1.2, # detection scale factor (if it can be set, otherwise it is automatically computed)
detector_type=FeatureDetectorTypes.FAST,
descriptor_type=FeatureDescriptorTypes.NONE,
match_ratio_test=kRatioTest,
tracker_type=FeatureTrackerTypes.LK):
super().__init__(num_features=num_features,
num_levels=num_levels,
scale_factor=scale_factor,
detector_type=detector_type,
descriptor_type=descriptor_type,
tracker_type=tracker_type)
self.feature_manager = feature_manager_factory(
num_features=num_features,
num_levels=num_levels,
scale_factor=scale_factor,
detector_type=detector_type,
descriptor_type=descriptor_type)
#if num_levels < 3:
# Printer.green('LkFeatureTracker: forcing at least 3 levels on LK pyr optic flow')
# num_levels = 3
optic_flow_num_levels = max(kLkPyrOpticFlowNumLevelsMin, num_levels)
Printer.green('LkFeatureTracker: num levels on LK pyr optic flow: ',
optic_flow_num_levels)
# we use LK pyr optic flow for matching
self.lk_params = dict(winSize=(21, 21),
maxLevel=optic_flow_num_levels,
criteria=(cv2.TERM_CRITERIA_EPS
| cv2.TERM_CRITERIA_COUNT, 30, 0.01))
def __init__(
self,
num_features=kMinNumFeatureDefault,
num_levels=1, # number of pyramid levels for detector
scale_factor=1.2, # detection scale factor (if it can be set, otherwise it is automatically computed)
detector_type=FeatureDetectorTypes.FAST,
descriptor_type=FeatureDescriptorTypes.ORB,
match_ratio_test=kRatioTest,
tracker_type=FeatureTrackerTypes.DES_FLANN):
super().__init__(num_features=num_features,
num_levels=num_levels,
scale_factor=scale_factor,
detector_type=detector_type,
descriptor_type=descriptor_type,
match_ratio_test=match_ratio_test,
tracker_type=tracker_type)
self.feature_manager = feature_manager_factory(
num_features=num_features,
num_levels=num_levels,
scale_factor=scale_factor,
detector_type=detector_type,
descriptor_type=descriptor_type)
if tracker_type == FeatureTrackerTypes.DES_FLANN:
self.matching_algo = FeatureMatcherTypes.FLANN
elif tracker_type == FeatureTrackerTypes.DES_BF:
self.matching_algo = FeatureMatcherTypes.BF
else:
raise ValueError("Unmanaged matching algo for feature tracker %s" %
self.tracker_type)
# init matcher
self.matcher = feature_matcher_factory(norm_type=self.norm_type,
ratio_test=match_ratio_test,
type=self.matching_algo)
#img = cv2.imread('../data/kitti06-12.png',cv2.IMREAD_COLOR)
#img = cv2.imread('../data/kitti06-435.png',cv2.IMREAD_COLOR)
img = cv2.imread('../data/kitti06-12-color.png', cv2.IMREAD_COLOR)
#img = cv2.imread('../data/mars1.png')
num_features = 2000
# select your tracker configuration (see the file feature_tracker_configs.py)
feature_tracker_config = FeatureTrackerConfigs.TEST
feature_tracker_config['num_features'] = num_features
feature_manager_config = FeatureManagerConfigs.extract_from(
feature_tracker_config)
print('feature_manager_config: ', feature_manager_config)
feature_manager = feature_manager_factory(**feature_manager_config)
des = None
# loop for measuring time performance
N = 20
for i in range(N):
timer.start()
# just detect keypoints
#kps = feature_manager.detect(img)
# detect keypoints and compute descriptors
kps, des = feature_manager.detectAndCompute(img)
timer.refresh()