-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdetect.py
138 lines (105 loc) · 5.7 KB
/
detect.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
import cv2
import numpy as np
import mediapipe as mp
mp_holistic = mp.solutions.holistic
mp_drawing = mp.solutions.drawing_utils
def mediapipe_detection(image, model):
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image.flags.writeable = False
results = model.process(image)
image.flags.writeable = True
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
return image, results
def draw_landmarks(image, results):
mp_drawing.draw_landmarks(image, results.face_landmarks, mp_holistic.FACEMESH_CONTOURS)
mp_drawing.draw_landmarks(image, results.pose_landmarks, mp_holistic.POSE_CONNECTIONS)
mp_drawing.draw_landmarks(image, results.left_hand_landmarks, mp_holistic.HAND_CONNECTIONS)
mp_drawing.draw_landmarks(image, results.right_hand_landmarks, mp_holistic.HAND_CONNECTIONS)
def draw_styled_landmarks(image, results):
mp_drawing.draw_landmarks(image, results.face_landmarks, mp_holistic.FACEMESH_CONTOURS,
mp_drawing.DrawingSpec(color=(255, 0, 0), thickness=1, circle_radius=1),
mp_drawing.DrawingSpec(color=(0, 255, 0), thickness=1, circle_radius=1)
)
mp_drawing.draw_landmarks(image, results.pose_landmarks, mp_holistic.POSE_CONNECTIONS,
mp_drawing.DrawingSpec(color=(0, 0, 255), thickness=4, circle_radius=4),
mp_drawing.DrawingSpec(color=(255, 255, 0), thickness=4, circle_radius=2)
)
mp_drawing.draw_landmarks(image, results.left_hand_landmarks, mp_holistic.HAND_CONNECTIONS,
mp_drawing.DrawingSpec(color=(0, 153, 0), thickness=4, circle_radius=4),
mp_drawing.DrawingSpec(color=(0, 255, 0), thickness=4, circle_radius=2)
)
mp_drawing.draw_landmarks(image, results.right_hand_landmarks, mp_holistic.HAND_CONNECTIONS,
mp_drawing.DrawingSpec(color=(255, 100, 100), thickness=4, circle_radius=4),
mp_drawing.DrawingSpec(color=(255, 0, 0), thickness=4, circle_radius=2)
)
def extract_keypoints(results):
pose = np.array([[res.x, res.y, res.z, res.visibility] for res in results.pose_landmarks.landmark]).flatten() if results.pose_landmarks else np.zeros(33*4)
face = np.array([[res.x, res.y, res.z] for res in results.face_landmarks.landmark]).flatten() if results.face_landmarks else np.zeros(468*3)
left_hand = np.array([[res.x, res.y, res.z] for res in results.left_hand_landmarks.landmark]).flatten() if results.left_hand_landmarks else np.zeros(21*3)
right_hand = np.array([[res.x, res.y, res.z] for res in results.right_hand_landmarks.landmark]).flatten() if results.right_hand_landmarks else np.zeros(21*3)
return np.concatenate([pose, face, left_hand, right_hand])
actions = np.array(['hello', 'thanks', 'iloveyou'])
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense
from tensorflow.keras.callbacks import TensorBoard
model = Sequential()
model.add(LSTM(64, return_sequences=True, activation='relu', input_shape=(30, 1662)))
model.add(LSTM(128, return_sequences=True, activation='relu'))
model.add(LSTM(64, return_sequences=False, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(32, activation='relu'))
model.add(Dense(actions.shape[0], activation='softmax'))
model.compile(optimizer='Adam', loss='categorical_crossentropy', metrics=['categorical_accuracy'])
model.load_weights('saved_model.h5')
from scipy import stats
colors = [(245,117,16), (117,245,16), (16,117,245)]
def prob_viz(res, actions, input_frame, colors):
output_frame = input_frame.copy()
for num, prob in enumerate(res):
cv2.rectangle(output_frame, (0,60+num*40), (int(prob*100), 90+num*40), colors[num], -1)
cv2.putText(output_frame, actions[num], (0, 85+num*40), cv2.FONT_HERSHEY_SIMPLEX, 1, (255,255,255), 2, cv2.LINE_AA)
return output_frame
sequence = []
sentence = []
predictions = []
threshold = 0.5
cap = cv2.VideoCapture(0)
with mp_holistic.Holistic(min_detection_confidence=0.5, min_tracking_confidence=0.5) as holistic:
while cap.isOpened():
# Read feed
ret, frame = cap.read()
# Make detections
image, results = mediapipe_detection(frame, holistic)
print(results)
# Draw landmarks
draw_styled_landmarks(image, results)
# 2. Prediction logic
keypoints = extract_keypoints(results)
sequence.append(keypoints)
sequence = sequence[-30:]
if len(sequence) == 30:
res = model.predict(np.expand_dims(sequence, axis=0))[0]
print(actions[np.argmax(res)])
predictions.append(np.argmax(res))
#3. Viz logic
if np.unique(predictions[-10:])[0]==np.argmax(res):
if res[np.argmax(res)] > threshold:
if len(sentence) > 0:
if actions[np.argmax(res)] != sentence[-1]:
sentence.append(actions[np.argmax(res)])
else:
sentence.append(actions[np.argmax(res)])
if len(sentence) > 5:
sentence = sentence[-5:]
# Viz probabilities
image = prob_viz(res, actions, image, colors)
cv2.rectangle(image, (0,0), (640, 40), (245, 117, 16), -1)
cv2.putText(image, ' '.join(sentence), (3,30),
cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2, cv2.LINE_AA)
# Show to screen
cv2.imshow('OpenCV Feed', image)
# Break gracefully
if cv2.waitKey(10) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()