-
Notifications
You must be signed in to change notification settings - Fork 0
/
train.py
95 lines (78 loc) · 3.27 KB
/
train.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
import copy
import csv
import itertools
import cv2
import numpy as np
import mediapipe as mp
import landmark_utils as u
mp_drawing = mp.solutions.drawing_utils
mp_drawing_styles = mp.solutions.drawing_styles
mp_hands = mp.solutions.hands
def main():
# For webcam input:
cap = cv2.VideoCapture(0)
number = 0
with mp_hands.Hands(
model_complexity=0,
min_detection_confidence=0.5,
min_tracking_confidence=0.5) as hands:
while cap.isOpened():
success, image = cap.read()
if not success:
print("Ignoring empty camera frame.")
# If loading a video, use 'break' instead of 'continue'.
continue
receivedKey = cv2.waitKey(20)
number = receivedKey - 48
# To improve performance, optionally mark the image as not writeable to
# pass by reference.
image.flags.writeable = False
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
results = hands.process(image)
# Draw the hand annotations on the image.
image.flags.writeable = True
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
if results.multi_hand_landmarks and number in [0, 1, 2, 3]:
for hand_landmarks in results.multi_hand_landmarks:
landmark_list = u.calc_landmark_list(image, hand_landmarks)
pre_processed_landmark_list = u.pre_process_landmark(
landmark_list)
log_csv(number, pre_processed_landmark_list)
mp_drawing.draw_landmarks(
image,
hand_landmarks,
mp_hands.HAND_CONNECTIONS,
mp_drawing_styles.get_default_hand_landmarks_style(),
mp_drawing_styles.get_default_hand_connections_style())
final = cv2.flip(image, 1)
text = ""
if number == -1:
text = "Press key for gesture number"
else:
text = "Gesture: {}".format(number)
cv2.putText(final, text, (10, 30), cv2.FONT_HERSHEY_DUPLEX, 1, 255)
# Flip the image horizontally for a selfie-view display.
cv2.imshow('MediaPipe Hands', final)
if cv2.waitKey(5) & 0xFF == 27:
break
cap.release()
def calc_bounding_rect(image, landmarks):
image_width, image_height = image.shape[1], image.shape[0]
landmark_array = np.empty((0, 2), int)
for _, landmark in enumerate(landmarks.landmark):
landmark_x = min(int(landmark.x * image_width), image_width - 1)
landmark_y = min(int(landmark.y * image_height), image_height - 1)
landmark_point = [np.array((landmark_x, landmark_y))]
landmark_array = np.append(landmark_array, landmark_point, axis=0)
x, y, w, h = cv2.boundingRect(landmark_array)
return [x, y, x + w, y + h]
def log_csv(number, landmark_list):
if number > 9 or number == -1:
pass
csv_path = csv_path = 'model/keypoint_classifier/keypoint.csv'
with open(csv_path, 'a', newline="") as f:
writer = csv.writer(f)
writer.writerow([number, *landmark_list])
return
if __name__ == '__main__':
main()