-
Notifications
You must be signed in to change notification settings - Fork 1
/
detect_mask_video.py
169 lines (139 loc) · 5.25 KB
/
detect_mask_video.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
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
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
95
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
158
159
160
161
162
163
164
165
166
167
168
169
# import the necessary packages
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.models import load_model
from imutils.video import WebcamVideoStream, FileVideoStream, FPS
import numpy as np
import imutils
import time
import cv2
import os
# load our serialized face detector model from disk
prototxtPath = r"face_detector\deploy.prototxt"
weightsPath = r"face_detector\res10_300x300_ssd_iter_140000.caffemodel"
faceNet = cv2.dnn.readNet(prototxtPath, weightsPath)
# load the face mask detector model from disk
maskNet = load_model(r"face_detector\mask_detector.model")
def detect_and_predict_mask(frame, faceNet, maskNet):
# grab the dimensions of the frame and then construct a blob
# from it
(h, w) = frame.shape[:2]
blob = cv2.dnn.blobFromImage(frame, 1.0, (224, 224),
(104.0, 177.0, 123.0))
# pass the blob through the network and obtain the face detections
faceNet.setInput(blob)
detections = faceNet.forward()
# initialize our list of faces, their corresponding locations,
# and the list of predictions from our face mask network
faces = []
locs = []
preds = []
# loop over the detections
for i in range(0, detections.shape[2]):
# extract the confidence (i.e., probability) associated with
# the detection
confidence = detections[0, 0, i, 2]
# filter out weak detections by ensuring the confidence is
# greater than the minimum confidence
if confidence > 0.5:
# compute the (x, y)-coordinates of the bounding box for
# the object
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
# ensure the bounding boxes fall within the dimensions of
# the frame
(startX, startY) = (max(0, startX), max(0, startY))
(endX, endY) = (min(w - 1, endX), min(h - 1, endY))
# extract the face ROI, convert it from BGR to RGB channel
# ordering, resize it to 224x224, and preprocess it
face = frame[startY:endY, startX:endX]
face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
face = cv2.resize(face, (224, 224))
face = img_to_array(face)
face = preprocess_input(face)
# add the face and bounding boxes to their respective
# lists
faces.append(face)
locs.append((startX, startY, endX, endY))
# only make a predictions if at least one face was detected
if len(faces) > 0:
# for faster inference we'll make batch predictions on *all*
# faces at the same time rather than one-by-one predictions
# in the above `for` loop
faces = np.array(faces, dtype="float32")
preds = maskNet.predict(faces, batch_size=32)
# return a 2-tuple of the face locations and their corresponding
# locations
return (locs, preds)
def mask_plot(locs, preds, frame_resized):
# loop over the detected face locations and their corresponding locations
mask_count = {'Mask': 0, 'No Mask':0}
for (box, pred) in zip(locs, preds):
# unpack the bounding box and predictions
(startX, startY, endX, endY) = box
(mask, withoutMask) = pred
# the bounding box and text
label = "Mask" if mask > withoutMask else "No Mask"
color = (0, 255, 0) if label == "Mask" else (0, 0, 255)
# update mask count
mask_count[label] += 1
# include the probability in the label
# label = "{}: {:.2f}%".format(label, max(mask, withoutMask) * 100)
# display the label and bounding box rectangle on the output
cv2.putText(frame_resized, label, (startX, startY - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
cv2.rectangle(frame_resized, (startX, startY), (endX, endY), color, 2)
return mask_count
def predict_mask(output, show_frame, video=0):
if type(video) is int:
print("[INFO] sampling frames from webcam using thread...")
cap = WebcamVideoStream(src=video).start()
else:
print("[INFO] sampling frames from video file using thread...")
cap = FileVideoStream(video, queue_size=256).start()
# video meta data
frame_width = int(cap.stream.get(3))
frame_height = int(cap.stream.get(4))
# output details
out = cv2.VideoWriter(output, cv2.VideoWriter_fourcc(*"MJPG"), 10.0, (frame_width, frame_height))
fps = FPS().start()
# loop over the frames from the video stream
while True:
frame = cap.read()
# Check if frame present
if type(video) == int:
if cap.grabbed==False:
print('failed to grab frame')
break
else:
if cap.more() == False:
print('failed to grab frame')
break
# processing frame
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
frame_resized = cv2.resize(frame, (frame_width, frame_height), interpolation=cv2.INTER_LINEAR)
(locs, preds) = detect_and_predict_mask(frame_resized, faceNet, maskNet)
mask_plot(locs, preds, frame_resized)
# display frame
if show_frame > 0:
cv2.imshow("Output Frames", frame_resized)
key = cv2.waitKey(1) & 0xFF
if key == ord("q"):
break
# update the FPS counter
fps.update()
# writing changes
out.write(frame_resized)
out.release()
cap.stop()
fps.stop()
cv2.destroyAllWindows()
# output message
print(":::Video Write Completed")
print("[INFO] Elasped time: {:.2f}".format(fps.elapsed()))
print("[INFO] Approx. FPS: {:.2f}".format(fps.fps()))
# do a bit of cleanup
cv2.destroyAllWindows()
cap.stop()
if __name__ == "__main__":
predict_mask(video='1.mp4', output='mask2.avi', show_frame=1)