-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbackend.py
161 lines (128 loc) · 6.67 KB
/
backend.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
import numpy as np
import cv2
import mediapipe as mp
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense
import os
os.environ["TF_ENABLE_ONEDNN_OPTS"] = "0"
mp_drawing = mp.solutions.drawing_utils
mp_holistic = mp.solutions.holistic
actions = []
for action in os.listdir("E:\Dataset"):
if len(os.listdir(os.path.join("E:\Dataset",action)))<40:
continue
actions.append(action)
def mediapipe_detection(image, model):
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) # COLOR CONVERSION BGR 2 RGB
image.flags.writeable = False # Image is no longer writeable
results = model.process(image) # Make prediction
image.flags.writeable = True # Image is now writeable
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR) # COLOR COVERSION RGB 2 BGR
return image, results
def draw_landmarks(image, results):
mp_drawing.draw_landmarks(image, results.pose_landmarks, mp_holistic.POSE_CONNECTIONS) # Draw pose connections
mp_drawing.draw_landmarks(image, results.left_hand_landmarks, mp_holistic.HAND_CONNECTIONS) # Draw left hand connections
mp_drawing.draw_landmarks(image, results.right_hand_landmarks, mp_holistic.HAND_CONNECTIONS)
def draw_styled_landmarks(image, results):
# Draw pose connections
mp_drawing.draw_landmarks(image, results.pose_landmarks, mp_holistic.POSE_CONNECTIONS,
mp_drawing.DrawingSpec(color=(80,22,10), thickness=2, circle_radius=4),
mp_drawing.DrawingSpec(color=(80,44,121), thickness=2, circle_radius=2)
)
# Draw left hand connections
mp_drawing.draw_landmarks(image, results.left_hand_landmarks, mp_holistic.HAND_CONNECTIONS,
mp_drawing.DrawingSpec(color=(121,22,76), thickness=2, circle_radius=4),
mp_drawing.DrawingSpec(color=(121,44,250), thickness=2, circle_radius=2)
)
# Draw right hand connections
mp_drawing.draw_landmarks(image, results.right_hand_landmarks, mp_holistic.HAND_CONNECTIONS,
mp_drawing.DrawingSpec(color=(245,117,66), thickness=2, circle_radius=4),
mp_drawing.DrawingSpec(color=(245,66,230), thickness=2, 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)
lh = 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)
rh = 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,lh, rh])
model = Sequential()
model.add(LSTM(64, return_sequences=True, activation='relu', input_shape=(40,258)))
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.save("E:\Model.h5")
cap = cv2.VideoCapture(0)
# Initiate holistic model
with mp_holistic.Holistic(min_detection_confidence=0.5, min_tracking_confidence=0.5) as holistic:
while cap.isOpened():
ret, frame = cap.read()
# Make detections
image, results = mediapipe_detection(frame, holistic)
# Export keypoints
keypoints = Extract_KeyPoints(results)
if len(sequence) == 30:
res = model.predict(np.expand_dims(sequence, axis=0))[0]
print(actions[np.argmax(res)])
predictions.append(np.argmax(res))
cv2.imshow('Raw Webcam Feed', image)
if cv2.waitKey(10) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
print(results)
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
# 1. New detection variables
sequence = []
sentence = []
predictions = []
threshold = 0.5
cap = cv2.VideoCapture(0)
# Set mediapipe model
with mp_holistic.Holistic(min_detection_confidence=0.5, min_tracking_confidence=0.5) as holistic:
while cap.isOpened():
cv2.imshow('OpenCV Feed', image)
# 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[-40:]
if len(sequence) == 40:
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()