class TLD_IVMIT:
def __init__(self, frame, window, init_frames_count = 20):
self.buffer = [cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)]
self.position = Position(self.buffer, *window)
self.learning_component = LearningComponent(self.position.calculate_patch())
self.detector = Detector(self.position, self.learning_component)
self.tracker = Tracker(self.position)
self.is_visible = True
self.integrator = Integrator(self.learning_component)
self.init_frames_count = init_frames_count
self.detected_windows = None
self.tracked_window = None
def start(self, frame):
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
if self.init_frames_count == 0:
start = time()
self.tracked_window = self.tracker.track(frame, self.position)
self.buffer[0] = frame
print "Tracking:", time()- start
start = time()
self.detected_windows = self.detector.detect(self.position, self.tracked_window is not None)
print "Detected windows count:", len(self.detected_windows)
print "Detection:", time()- start
start = time()
# filtered_detected_windows = [(window, patch, proba) for window, patch, proba in self.detected_windows if proba > 0.7]
single_window, self.is_visible = self.integrator.get_single_window(self.position, self.detected_windows, self.tracked_window)
print "Integration:", time()- start
if self.is_visible:
self.position.update(*single_window)
# start = time()
# self.learning_component.n_expert()
# self.learning_component.p_expert()
# print "Update training set:", time()- start
else:
self.tracked_window = self.tracker.track(frame, self.position)
self.buffer[0] = frame
if self.tracked_window is not None:
i = 0
while i < 5:
self.position.update(x=np.random.randint(0,self.buffer[0].shape[1]-self.position.width))
if self.position.is_correct() and windows_intersection(self.position.get_window(), self.tracked_window) == 0:
self.learning_component.update_negatives(self.position.calculate_patch())
i += 1
self.position.update(*self.tracked_window)
self.learning_component.update_positives(self.position.calculate_patch())
self.init_frames_count -= 1
else:
self.init_frames_count = 0
self.is_visible = False
return self.position
max_test_count = max_train_count
start_time = time.time()
positive_samples = get_samples(folder, pos_list, samples_subfolder, max_train_count+max_test_count)
negative_samples = get_samples(folder, neg_list, "", 5*max_train_count+max_test_count)
positive_patches = [Position(cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY), 0, 0, frame.shape[1], frame.shape[0]).calculate_patch() for frame in positive_samples]
negative_patches = [Position(cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY), 0, 0, frame.shape[1], frame.shape[0]).calculate_patch() for frame in negative_samples]
print "Positive samples:", len(positive_samples)
print "Negative samples:", len(negative_samples)
print "Generate training set:", time.time() - start_time
print
start_time = time.time()
learning_component = LearningComponent(positive_patches[0])
detector = Detector(learning_component)
for patch in positive_patches[1:max_train_count]:
learning_component.update_positives(patch)
for patch in negative_patches[:5*max_train_count]:
learning_component.update_negatives(patch)
print "Update training set:", time.time() - start_time
print
start_time = time.time()
detector.ensemble_classifier.relearn()
print "Learn detector:", time.time() - start_time
print
for param in xrange(10):
print "Param:", param/10.0
detector.threshold_patch_variance = 0.3
detector.threshold_ensemble = param/10.0
detector.nearest_neighbor_classifier.tetta = 0.4