HandTrackingModule.py

# This code is for the server 
# Lets import the libraries
import cv2
import mediapipe as mp
import time
import math
import numpy as np
import socket,pickle,struct,imutils


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(self.mode, self.maxHands,
                                        self.detectionCon, self.trackCon)
        self.mpDraw = mp.solutions.drawing_utils
        self.tipIds = [4, 8, 12, 16, 20]

    def findHands(self, img, canvas, 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)
                    self.mpDraw.draw_landmarks(canvas, handLms,
                                               self.mpHands.HAND_CONNECTIONS)

        return img,canvas

    def findPosition(self, img, canvas, handNo=0, draw=True):
        xList = []
        yList = []
        bbox = []
        self.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)
                xList.append(cx)
                yList.append(cy)
                # print(id, cx, cy)
                self.lmList.append([id, cx, cy])
                if draw:
                    cv2.circle(img, (cx, cy), 5, (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 fingersUp(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)

        # totalFingers = fingers.count(1)

        return fingers

    def findDistance(self, p1, p2, img, draw=True,r=5, 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():
    pTime = 0
    cTime = 0
    cap = cv2.VideoCapture('http://192.168.1.x:8080/video')
    stream = 0
    detector = handDetector()
    # Socket Create
    server_socket = socket.socket(socket.AF_INET,socket.SOCK_STREAM)
    host_name  = socket.gethostname()
    host_ip = socket.gethostbyname(host_name)
    print('HOST IP:',host_ip)
    port = 9999
    socket_address = (host_ip,port)

    # Socket Bind
    server_socket.bind(socket_address)

    # Socket Listen
    server_socket.listen(5)
    print("LISTENING AT:",socket_address)
    
    client_socket,addr = server_socket.accept()
    print('GOT CONNECTION FROM:',addr)
    while True:
        success, img = cap.read()
        canvas = np.zeros((300, 300, 3), dtype="uint8")
        img,canvas = detector.findHands(img,canvas)
        lmList, bbox = detector.findPosition(img,canvas)
        if len(lmList) != 0:
            print(lmList[4])

        cTime = time.time()
        fps = 1 / (cTime - pTime)
        pTime = cTime
        
        img = cv2.rotate(img, cv2.cv2.ROTATE_90_CLOCKWISE)
        canvas = cv2.rotate(canvas, cv2.cv2.ROTATE_90_CLOCKWISE)
        cv2.putText(img, str(int(fps)), (10, 70), cv2.FONT_HERSHEY_PLAIN, 3,(255, 0, 255), 3)
        cv2.putText(canvas, str(int(fps)), (10, 70), cv2.FONT_HERSHEY_PLAIN, 3,(255, 0, 255), 3)    
        if client_socket:
            vid = canvas
            vid = imutils.resize(vid)
            a = pickle.dumps(vid)
            message = struct.pack("Q",len(a))+a
            client_socket.sendall(message)
            if cv2.waitKey(1) == '13':
                client_socket.close()
                    
        cv2.imshow("Image", img)
        cv2.waitKey(1)
        stream = 1

if __name__ == "__main__":
    main()