def detect(self, image_obj, bbox_objs=None, batch_size=2):
if bbox_objs is None:
x2, y2 = image_obj.pil_image_obj.size
bbox_objs = [BoundedBoxObject(0, 0, x2, y2, '', 0, '')]
n_bbox = len(bbox_objs)
result_objects = []
for row_idx, batch_start, batch_end in chunk_with_index(
range(n_bbox), batch_size):
batch_bbox_objs = bbox_objs[batch_start:batch_end]
objs = image_obj.fetch_bbox_pil_objs(batch_bbox_objs)
objects_frame = resize_and_stack_image_objs(self.image_size, objs)
objects_frame = np.transpose(objects_frame, (0, 3, 1, 2))
objects_embedding = self.model.get_faces_feature(objects_frame)
similar_matrix = objects_embedding.dot(
self.registered_images_embedding.T)
detected_idx = similar_matrix.argmax(1)
for idx, bbox in enumerate(batch_bbox_objs):
x1, y1, x2, y2, _, _, _ = bbox
label = self.registered_ids[detected_idx[idx]]
score = similar_matrix[idx, detected_idx[idx]]
if score < self.threshold:
label = self.unknown
result_objects.append(
BoundedBoxObject(x1, y1, x2, y2, label, score, ''))
image_dict = {
'image_id': image_obj.image_id,
'detected_objects': result_objects,
}
detection_result = DetectionResult(image_dict)
return detection_result
def detect(self, image_obj) -> DetectionResult:
frame = np.array(image_obj.pil_image_obj)
if self.resize is not None:
frame = cv2.resize(frame, self.resize)
ori_height, ori_width = frame.shape[:2]
x_scale_up_ratio = ori_width / self.resize[0]
y_scale_up_ratio = ori_height / self.resize[1]
else:
x_scale_up_ratio = 1
y_scale_up_ratio = 1
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
persons = self.person_cascade.detectMultiScale(gray, 1.1, 1)
persons = np.array([[x, y, x + w, y + h] for (x, y, w, h) in persons])
picked_idx = non_max_suppression(persons,
probs=None,
overlapThresh=0.65)
detected_objects = []
for idx in picked_idx:
x1, y1, x2, y2 = persons[idx]
x1 = x1 * x_scale_up_ratio
x2 = x2 * x_scale_up_ratio
y1 = y1 * y_scale_up_ratio
y2 = y2 * y_scale_up_ratio
detected_objects.append(
BoundedBoxObject(x1, y1, x2, y2, 'person', 0, ''))
image_dict = {
'image_id': image_obj.image_id,
'detected_objects': detected_objects,
}
detection_result = DetectionResult(image_dict)
return detection_result
def detect(self, image_obj) -> DetectionResult:
frame = np.array(image_obj.pil_image_obj)
rects, weights = self.hog.detectMultiScale(frame,
winStride=(3, 3),
padding=(16, 16),
scale=1.05)
rects = np.array([[x, y, x + w, y + h] for (x, y, w, h) in rects])
picked_idx = non_max_suppression(rects, probs=None, overlapThresh=0.65)
detected_objects = []
for idx in picked_idx:
x1, y1, x2, y2 = rects[idx]
score = weights[idx][0]
if score < self.threshold:
continue
detected_objects.append(
BoundedBoxObject(x1, y1, x2, y2, 'person', score, ''))
image_dict = {
'image_id': image_obj.image_id,
'detected_objects': detected_objects,
}
detection_result = DetectionResult(image_dict)
return detection_result
def detect_frame(self, frame):
detected_objects = []
ret = self.face_detector.detect_face(frame, det_type=0)
if ret:
bbox, _ = ret
for idx in range(bbox.shape[0]):
x1, y1, x2, y2, score = bbox[idx]
detected_objects.append(BoundedBoxObject(x1, y1, x2, y2, 'face', score, ''))
image_dict = {
'image_id': 'frame',
'detected_objects': detected_objects,
}
detection_result = DetectionResult(image_dict)
return(detection_result)
def detect(self, image_obj) -> DetectionResult:
frame = np.array(image_obj.pil_image_obj)
ori_height, ori_width = frame.shape[:2]
frame_resized = cv2.resize(frame, self.resize)
x_scale_up_ratio = ori_width / self.resize[0]
y_scale_up_ratio = ori_height / self.resize[1]
blob = cv2.dnn.blobFromImage(frame_resized, 0.007843, (300, 300),
(127.5, 127.5, 127.5), False)
# Set to network the input blob
self.net.setInput(blob)
# Prediction of network
detections = self.net.forward()
detected_objects = []
for i in range(detections.shape[2]):
confidence = detections[0, 0, i, 2] # Confidence of prediction
if confidence < self.threshold: # Filter prediction
continue
class_id = int(detections[0, 0, i, 1]) # Class label
label = self.classNames[class_id]
# Object location
x1 = int(detections[0, 0, i, 3] * self.resize[0] *
x_scale_up_ratio)
y1 = int(detections[0, 0, i, 4] * self.resize[1] *
y_scale_up_ratio)
x2 = int(detections[0, 0, i, 5] * self.resize[0] *
x_scale_up_ratio)
y2 = int(detections[0, 0, i, 6] * self.resize[1] *
y_scale_up_ratio)
detected_objects.append(
BoundedBoxObject(x1, y1, x2, y2, label, confidence, ''))
image_dict = {
'image_id': image_obj.image_id,
'detected_objects': detected_objects,
}
detection_result = DetectionResult(image_dict)
return detection_result
def detect(self, image_obj, label='face', train=True):
detected_objects = []
frame = swap_channel_rgb_bgr(np.array(image_obj.pil_image_obj))
ret = self.face_detector.detect_face(frame, det_type=0)
if ret:
bbox, _ = ret
# boundingboxes shape n, 5
for idx in range(bbox.shape[0]):
x1, y1, x2, y2, score = bbox[idx]
if train:
score=1
detected_objects.append(BoundedBoxObject(x1, y1, x2, y2, label, score, ''))
image_dict = {
'image_id': image_obj.image_id,
'detected_objects': detected_objects,
}
detection_result = DetectionResult(image_dict)
return detection_result