TAG Park

分享自己觉得好玩的技术和有趣的游戏理解

0%

基于mediaPipe和OpenCV手势识别

发表于 分类于 ，
本文字数： 62

基于mediaPipe和OpenCV手势识别

手部追踪模块(HandTrackingModule.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
# -*- coding:utf-8 -*-

import cv2
import mediapipe as mp

class HandDetector:
    """
    使用mediapipe库查找手。导出地标像素格式。添加了额外的功能。
    如查找方式，许多手指向上或两个手指之间的距离。而且提供找到的手的边界框信息。
    """
    def __init__(self, mode=False, maxHands=2, detectionCon=0.5, minTrackCon = 0.5):
        """
        :param mode: 在静态模式下，对每个图像进行检测
        :param maxHands: 要检测的最大手数
        :param detectionCon: 最小检测置信度
        :param minTrackCon: 最小跟踪置信度
        """
        self.mode = mode
        self.maxHands = maxHands
        self.modelComplex = False
        self.detectionCon = detectionCon
        self.minTrackCon = minTrackCon

		# 初始化手部识别模型
        self.mpHands = mp.solutions.hands
        self.hands = self.mpHands.Hands(self.mode, self.maxHands, self.modelComplex,
                                        self.detectionCon, self.minTrackCon)
        self.mpDraw = mp.solutions.drawing_utils	# 初始化绘图器
        self.tipIds = [4, 8, 12, 16, 20]			# 指尖列表
        self.fingers = []
        self.lmList = []

    def findHands(self, img, draw=True):
        """
        从图像(BRG)中找到手部。
        :param img: 用于查找手的图像。
        :param draw: 在图像上绘制输出的标志。
        :return: 带或不带图形的图像
        """
        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # 将传入的图像由BGR模式转标准的Opencv模式——RGB模式，
        self.results = self.hands.process(imgRGB)

        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):
        """
        查找单手的地标并将其放入列表中像素格式。还可以返回手部周围的边界框。
        :param img: 要查找的主图像
        :param handNo: 如果检测到多只手，则为手部id
        :param draw: 在图像上绘制输出的标志。(默认绘制矩形框)
        :return: 像素格式的手部关节位置列表；手部边界框
        """

        xList = []
        yList = []
        bbox = []
        bboxInfo =[]
        self.lmList = []
        if self.results.multi_hand_landmarks:
            myHand = self.results.multi_hand_landmarks[handNo]
            for id, lm in enumerate(myHand.landmark):
                h, w, c = img.shape
                px, py = int(lm.x * w), int(lm.y * h)
                xList.append(px)
                yList.append(py)
                self.lmList.append([px, py])
                if draw:
                    cv2.circle(img, (px, py), 5, (255, 0, 255), cv2.FILLED)
            xmin, xmax = min(xList), max(xList)
            ymin, ymax = min(yList), max(yList)
            boxW, boxH = xmax - xmin, ymax - ymin
            bbox = xmin, ymin, boxW, boxH
            cx, cy = bbox[0] + (bbox[2] // 2), \
                     bbox[1] + (bbox[3] // 2)
            bboxInfo = {"id": id, "bbox": bbox,"center": (cx, cy)}

            if draw:
                cv2.rectangle(img, (bbox[0] - 20, bbox[1] - 20),
                              (bbox[0] + bbox[2] + 20, bbox[1] + bbox[3] + 20),
                              (0, 255, 0), 2)

        return self.lmList, bboxInfo

    def fingersUp(self):
        """
        查找列表中打开并返回的手指数。会分别考虑左手和右手
        ：return：竖起手指的列表
        """
        if self.results.multi_hand_landmarks:
            myHandType = self.handType()
            fingers = []
            # Thumb
            if myHandType == "Right":
                if self.lmList[self.tipIds[0]][0] > self.lmList[self.tipIds[0] - 1][0]:
                    fingers.append(1)
                else:
                    fingers.append(0)
            else:
                if self.lmList[self.tipIds[0]][0] < self.lmList[self.tipIds[0] - 1][0]:
                    fingers.append(1)
                else:
                    fingers.append(0)
            # 4 Fingers
            for id in range(1, 5):
                if self.lmList[self.tipIds[id]][1] < self.lmList[self.tipIds[id] - 2][1]:
                    fingers.append(1)
                else:
                    fingers.append(0)
        return fingers

    def handType(self):
        """
        检查传入的手部是左还是右
        ：return: "Right" 或 "Left"
        """
        if self.results.multi_hand_landmarks:
            if self.lmList[17][0] < self.lmList[5][0]:
                return "Right"
            else:
                return "Left"

主函数main.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


# -*- coding:utf-8 -*-
import cv2
from HandTrackingModule import HandDetector
from PIL import Image,ImageDraw,ImageFont
import numpy

#解决中文出现乱码问题
def cv2ImgAddText(img, text, left, top, textColor=(0, 255, 0), textSize=20):
    if (isinstance(img, numpy.ndarray)):  # 判断是否OpenCV图片类型
        img = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
    # 创建一个可以在给定图像上绘图的对象
    draw = ImageDraw.Draw(img)
    # 字体的格式
    fontStyle = ImageFont.truetype(
        "font/simsun.ttc", textSize, encoding="utf-8")
    # 绘制文本
    draw.text((left, top), text, textColor, font=fontStyle)
    # 转换回OpenCV格式
    return cv2.cvtColor(numpy.asarray(img), cv2.COLOR_RGB2BGR)


class Main:
    def __init__(self):
        self.camera = cv2.VideoCapture(0,cv2.CAP_DSHOW)
        self.camera.set(3, 1280)
        self.camera.set(4, 720)

    def Gesture_recognition(self):
        while True:
            self.detector = HandDetector()
            frame, img = self.camera.read()
            img = self.detector.findHands(img)
            lmList, bbox = self.detector.findPosition(img)

            if lmList:
                x_1, y_1 = bbox["bbox"][0], bbox["bbox"][1]
                x1, x2, x3, x4, x5 = self.detector.fingersUp()

                if (x2 == 1 and x3 == 1) and (x4 == 0 and x5 == 0 and x1 == 0):
                    cv2.putText(img, "2_TWO", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
                                (0, 0, 255), 3)
                elif (x2 == 1 and x3 == 1 and x4 == 1) and (x1 == 0 and x5 == 0):
                    cv2.putText(img, "3_THREE", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
                                (0, 0, 255), 3)
                elif (x2 == 1 and x3 == 1 and x4 == 1 and x5 == 1) and (x1 == 0):
                    cv2.putText(img, "4_FOUR", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
                                (0, 0, 255), 3)
                elif x1 == 1 and x2 == 1 and x3 == 1 and x4 == 1 and x5 == 1:
                    cv2.putText(img, "5_FIVE", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
                                (0, 0, 255), 3)
                elif x2 == 1 and (x1 == 0, x3 == 0, x4 == 0, x5 == 0):
                    cv2.putText(img, "1_ONE", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
                                (0, 0, 255), 3)
                elif x1 == 1 and (x2 == 0, x3 == 0, x4 == 0, x5 == 0):
                    img = cv2ImgAddText(img,'杰哥觉得很赞',left = x_1,top=y_1,textColor=(255,0,0),textSize = 45)


            cv2.imshow("camera", img)
            #if cv2.getWindowProperty('camera', cv2.WND_PROP_VISIBLE) < 1:
            #    break
            cv2.waitKey(1)
            if cv2.waitKey(1) & 0xFF == ord("q"):
                 break

if __name__ == '__main__':
    Solution = Main()
    Solution.Gesture_recognition()
-------------本文已结束非常感谢您的阅读-------------
Your help means a lot to me！

欢迎关注我的其它发布渠道