Repository navigation
Expand file tree
/
Copy pathHandTrackingModule.py
More file actions
91 lines (62 loc) · 2.4 KB
/
Copy pathHandTrackingModule.py
File metadata and controls
91 lines (62 loc) · 2.4 KB
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
import cv2
import mediapipe as mp
import time
class handDetector():
def __init__(self, mode = False, maxHands =2, detectionCon =0.5, trackCon = 0.5):
self.mode = mode
self.maxHands = maxHands
self.detectionCon = detectionCon
self.trackCon = trackCon
self.mpHands = mp.solutions.hands
self.hands = self.mpHands.Hands(static_image_mode=self.mode, # Keyword argument
max_num_hands=self.maxHands, # Keyword argument
min_detection_confidence=self.detectionCon, # Keyword argument
min_tracking_confidence=self.trackCon # Keyword argument
)
self.mpDraw = mp.solutions.drawing_utils
def findHands(self,img,draw =True):
imgRGB =cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
self.results = self.hands.process(imgRGB)
#print(results.multi_hand_landmarks)
if self.results.multi_hand_landmarks:
for handLms in self.results.multi_hand_landmarks:
if draw:
self.mpDraw.draw_landmarks(img, handLms ,self.mpHands.HAND_CONNECTIONS)
return img
def findPosition(self,img,handNo =0,draw =True):
lmList =[]
if self.results.multi_hand_landmarks:
myHand = self.results.multi_hand_landmarks[handNo]
for id,lm in enumerate(myHand.landmark):
#print(id,lm)
h,w,c = img.shape
cx,cy = int(lm.x * w),int(lm.y * h)
#print(f"Landmark ID {id}: ({cx}, {cy})")
lmList.append([id,cx,cy])
if draw:
#if id ==0:
cv2.circle(img, (cx,cy), 5 , (255,0,255), cv2.FILLED)
#draw connections & dots
return lmList
def main():
pTime =0
cTime =0
cap = cv2.VideoCapture(0)
if not cap.isOpened():
print("Error: could not open camers.")
exit()
detector =handDetector()
while True:
success, img = cap.read()
img = detector.findHands(img)
lmList = detector.findPosition(img)
if len(lmList) !=0:
print(lmList[4])
cTime =time.time()
fps = 1/(cTime - pTime)
pTime =cTime
cv2.putText(img,str(int(fps)),(10,70),cv2.FONT_HERSHEY_PLAIN,3,(255,0,255),3)
cv2.imshow("image", img)
cv2.waitKey(1)
if __name__ == "__main__":
main()