AI-Project/HandTrackingModule.py at main · purnakam/AI-Project · GitHub

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
'''Hand Tracking Module'''

import cv2
import mediapipe as mp
import time
import math
import numpy as np

class HandDetector():
    def __init__(self, static_image_mode=False,max_num_hands=2,min_detection_confidence=0.5, min_tracking_confidence=0.5):

        self.mode = static_image_mode
        self.maxHands = max_num_hands
        self.detectioncomf = min_detection_confidence
        self.trackingconf = min_tracking_confidence
        self.tipIds = [4, 8, 12, 16, 20]

        self.mpHands = mp.solutions.hands
        self.hands = self.mpHands.Hands(self.mode,self.maxHands)#,int(self.detectioncomf),int(self.trackingconf))
        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):
        self.lmList = []
        xList = []
        yList = []
        bbox = []


        if self.results.multi_hand_landmarks:
            myHands = self.results.multi_hand_landmarks[handNO]
            for id, lm in enumerate(myHands.landmark):
                # print(id,lm)  # id , landmark
                h, w, c=img.shape  # height,weight ,channel
                cx, cy = int(lm.x*w), int(lm.y*h) # potion of center
                xList.append(cx)
                yList.append(cy)
                # print(id, cx, cy)
                self.lmList.append([id,cx,cy])
                if draw:
                    cv2.circle(img, (cx,cy), 8, (255,0,255), cv2.FILLED)

            xmin, xmax = min(xList), max(xList)
            ymin, ymax = min(yList), max(yList)
            bbox = xmin, ymin, xmax, ymax

            if draw:
                cv2.rectangle(img, (xmin - 20, ymin - 20), (xmax + 20, ymax + 20), (0,255,0, 2))

        return self.lmList , bbox

    def fingerup(self):
        fingers = []

        # Thumb
        if self.lmList[self.tipIds[0]][1] > self.lmList[self.tipIds[0] - 1][1]:
            fingers.append(1)
        else:
            fingers.append(0)

        # Fingers
        for id in range(1, 5):

            if self.lmList[self.tipIds[id]][2] < self.lmList[self.tipIds[id] - 2][2]:
                fingers.append(1)
            else:
                fingers.append(0)

        # total_fingers = fingers.count(1)

        return fingers , #total_fingers

    def findDistance(self, p1, p2, img, draw=True,r=15, t=3):
        x1, y1 = self.lmList[p1][1:]
        x2, y2 = self.lmList[p2][1:]
        cx, cy = (x1 + x2) // 2, (y1 + y2) // 2

        if draw:
            cv2.line(img, (x1, y1), (x2, y2), (255, 0, 255), t)
            cv2.circle(img, (x1, y1), r, (255, 0, 255), cv2.FILLED)
            cv2.circle(img, (x2, y2), r, (255, 0, 255), cv2.FILLED)
            cv2.circle(img, (cx, cy), r, (0, 0, 255), cv2.FILLED)
        length = math.hypot(x2 - x1, y2 - y1)

        return length, img, [x1, y1, x2, y2, cx, cy]


def main():
    prevTime = 0
    currentTime = 0
    cap = cv2.VideoCapture(0)
    detector = HandDetector()
    while True:
        success, img=cap.read()

        # Flip the frame horizontally to remove mirror effect
        flipped_img = cv2.flip(img, 1)

        img = detector.findHands(flipped_img)
        lmList = detector.findposition(flipped_img)
        if len(lmList) != 0:
            pass
            #  print(lmList[4])

        currentTime=time.time()
        fps = 1/(currentTime-prevTime)
        prevTime = currentTime

        cv2.putText(flipped_img, str(int(fps)), (10,70), cv2.FONT_HERSHEY_SIMPLEX, 3, (255,0,255), 3) #(img,fps,pos,font,scale,color,thickness)

        cv2.imshow('Image',flipped_img)
        cv2.waitKey(1)


if __name__ == "__main__":
    main()