山东枣庄滕州网站建设,广州注册监理公司,做推文的编辑网站,营销型网站 开源程序手势识别系列文章目录
手势识别是一种人机交互技术#xff0c;通过识别人的手势动作#xff0c;从而实现对计算机、智能手机、智能电视等设备的操作和控制。
1. opencv实现手部追踪#xff08;定位手部关键点#xff09;
2.opencv实战项目 实现手势跟踪并返回位置信息通过识别人的手势动作从而实现对计算机、智能手机、智能电视等设备的操作和控制。
1. opencv实现手部追踪定位手部关键点
2.opencv实战项目 实现手势跟踪并返回位置信息封装调用
3.手势识别-手势音量控制opencv
4.opencv实战项目 手势识别-手势控制鼠标
5.opencv实战项目 手势识别-手部距离测量
6.opencv实战项目 手势识别-实现尺寸缩放效果
未完待续 目录 手势识别系列文章目录
1.HandTraqckModule模块
2、主模块 本项目是使用了谷歌开源的框架mediapipe里面有非常多的模型提供给我们使用例如面部检测身体检测手部检测等 代码需要用到opencv HandTraqckModule模块 mediapipe模块
1.HandTraqckModule模块
如下
定义 HandDetector 类用于检测手势并提取相关信息
class HandDetector:def __init__(self, modeFalse, maxHands2, detectionCon0.5, minTrackCon0.5):# 初始化函数设置参数self.mode modeself.maxHands maxHandsself.detectionCon detectionConself.minTrackCon minTrackCon# 初始化 Mediapipe 模块和相关对象self.mpHands mp.solutions.handsself.hands self.mpHands.Hands(static_image_modeself.mode, max_num_handsself.maxHands,min_detection_confidenceself.detectionCon, min_tracking_confidenceself.minTrackCon)self.mpDraw mp.solutions.drawing_utilsself.tipIds [4, 8, 12, 16, 20]self.fingers []self.lmList []findHands 函数在图像中找到手部并返回手部信息以及绘制的图像。 def findHands(self, img, drawTrue, flipTypeTrue):# 找到手部并绘制相关信息imgRGB cv2.cvtColor(img, cv2.COLOR_BGR2RGB)self.results self.hands.process(imgRGB)allHands []# 处理每个检测到的手if self.results.multi_hand_landmarks:for handType, handLms in zip(self.results.multi_handedness, self.results.multi_hand_landmarks):# 提取手部关键点和边界框信息myHand {}mylmList []xList []yList []for id, lm in enumerate(handLms.landmark):px, py int(lm.x * w), int(lm.y * h)mylmList.append([px, py])xList.append(px)yList.append(py)# 计算边界框信息xmin, xmax min(xList), max(xList)ymin, ymax min(yList), max(yList)boxW, boxH xmax - xmin, ymax - yminbbox xmin, ymin, boxW, boxHcx, cy bbox[0] (bbox[2] // 2), bbox[1] (bbox[3] // 2)myHand[lmList] mylmListmyHand[bbox] bboxmyHand[center] (cx, cy)# 根据手的方向进行翻转if flipType:if handType.classification[0].label Right:myHand[type] Leftelse:myHand[type] Rightelse:myHand[type] handType.classification[0].labelallHands.append(myHand)# 绘制手部信息if draw:self.mpDraw.draw_landmarks(img, handLms, self.mpHands.HAND_CONNECTIONS)cv2.rectangle(img, (bbox[0] - 20, bbox[1] - 20), (bbox[0] bbox[2] 20, bbox[1] bbox[3] 20),(255, 0, 255), 2)cv2.putText(img, myHand[type], (bbox[0] - 30, bbox[1] - 30), cv2.FONT_HERSHEY_PLAIN,2, (255, 0, 255), 2)if draw:return allHands, imgelse:return allHandsfingersUp 函数检测手指的状态返回一个列表表示手指是否抬起。 def fingersUp(self, myHand):# 检测手指状态返回列表表示手指是否抬起myHandType myHand[type]myLmList myHand[lmList]if self.results.multi_hand_landmarks:fingers []# 大拇指if myHandType Right:if myLmList[self.tipIds[0]][0] myLmList[self.tipIds[0] - 1][0]:fingers.append(1)else:fingers.append(0)else:if myLmList[self.tipIds[0]][0] myLmList[self.tipIds[0] - 1][0]:fingers.append(1)else:fingers.append(0)# 其他四指for id in range(1, 5):if myLmList[self.tipIds[id]][1] myLmList[self.tipIds[id] - 2][1]:fingers.append(1)else:fingers.append(0)return fingersfindDistance 函数计算两点间的距离可选是否在图像上绘制。 def findDistance(self, p1, p2, imgNone):# 计算两点间的距离可绘制在图像上x1, y1 p1x2, y2 p2cx, cy (x1 x2) // 2, (y1 y2) // 2length math.hypot(x2 - x1, y2 - y1)info (x1, y1, x2, y2, cx, cy)if img is not None:cv2.circle(img, (x1, y1), 15, (255, 0, 255), cv2.FILLED)cv2.circle(img, (x2, y2), 15, (255, 0, 255), cv2.FILLED)cv2.line(img, (x1, y1), (x2, y2), (255, 0, 255), 3)cv2.circle(img, (cx, cy), 15, (255, 0, 255), cv2.FILLED)return length, info, imgelse:return length, infoHandTraqckModule模块整体代码 Hand Tracking Module
import cv2
import mediapipe as mp
import mathclass HandDetector:Finds Hands using the mediapipe library. Exports the landmarksin pixel format. Adds extra functionalities like finding howmany fingers are up or the distance between two fingers. Alsoprovides bounding box info of the hand found.def __init__(self, modeFalse, maxHands2, detectionCon0.5, minTrackCon0.5)::param mode: In static mode, detection is done on each image: slower:param maxHands: Maximum number of hands to detect:param detectionCon: Minimum Detection Confidence Threshold:param minTrackCon: Minimum Tracking Confidence Thresholdself.mode modeself.maxHands maxHandsself.detectionCon detectionConself.minTrackCon minTrackConself.mpHands mp.solutions.handsself.hands self.mpHands.Hands(static_image_modeself.mode, max_num_handsself.maxHands,min_detection_confidenceself.detectionCon, min_tracking_confidence self.minTrackCon)self.mpDraw mp.solutions.drawing_utilsself.tipIds [4, 8, 12, 16, 20]self.fingers []self.lmList []def findHands(self, img, drawTrue, flipTypeTrue):Finds hands in a BGR image.:param img: Image to find the hands in.:param draw: Flag to draw the output on the image.:return: Image with or without drawingsimgRGB cv2.cvtColor(img, cv2.COLOR_BGR2RGB)self.results self.hands.process(imgRGB)allHands []h, w, c img.shapeif self.results.multi_hand_landmarks:for handType,handLms in zip(self.results.multi_handedness,self.results.multi_hand_landmarks):myHand{}## lmListmylmList []xList []yList []for id, lm in enumerate(handLms.landmark):px, py int(lm.x * w), int(lm.y * h)mylmList.append([px, py])xList.append(px)yList.append(py)## bboxxmin, xmax min(xList), max(xList)ymin, ymax min(yList), max(yList)boxW, boxH xmax - xmin, ymax - yminbbox xmin, ymin, boxW, boxHcx, cy bbox[0] (bbox[2] // 2), \bbox[1] (bbox[3] // 2)myHand[lmList] mylmListmyHand[bbox] bboxmyHand[center] (cx, cy)if flipType:if handType.classification[0].label Right:myHand[type] Leftelse:myHand[type] Rightelse:myHand[type] handType.classification[0].labelallHands.append(myHand)## drawif draw:self.mpDraw.draw_landmarks(img, handLms,self.mpHands.HAND_CONNECTIONS)cv2.rectangle(img, (bbox[0] - 20, bbox[1] - 20),(bbox[0] bbox[2] 20, bbox[1] bbox[3] 20),(255, 0, 255), 2)cv2.putText(img,myHand[type],(bbox[0] - 30, bbox[1] - 30),cv2.FONT_HERSHEY_PLAIN,2,(255, 0, 255),2)if draw:return allHands,imgelse:return allHandsdef findPosition(self, img, handNo0, drawTrue):Finds landmarks of a single hand and puts them in a listin pixel format. Also finds the bounding box around the hand.:param img: main image to find hand in:param handNo: hand id if more than one hand detected:param draw: Flag to draw the output on the image.:return: list of landmarks in pixel format; bounding boxxList []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.shapepx, 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 - yminbbox xmin, ymin, boxW, boxHcx, 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, bboxInfodef fingersUp(self,myHand):Finds how many fingers are open and returns in a list.Considers left and right hands separately:return: List of which fingers are upmyHandType myHand[type]myLmList myHand[lmList]if self.results.multi_hand_landmarks:fingers []# Thumbif myHandType Right:if myLmList[self.tipIds[0]][0] myLmList[self.tipIds[0] - 1][0]:fingers.append(1)else:fingers.append(0)else:if myLmList[self.tipIds[0]][0] myLmList[self.tipIds[0] - 1][0]:fingers.append(1)else:fingers.append(0)# 4 Fingersfor id in range(1, 5):if myLmList[self.tipIds[id]][1] myLmList[self.tipIds[id] - 2][1]:fingers.append(1)else:fingers.append(0)return fingersdef findDistance(self,p1, p2, imgNone):Find the distance between two landmarks based on theirindex numbers.:param p1: Point1:param p2: Point2:param img: Image to draw on.:param draw: Flag to draw the output on the image.:return: Distance between the pointsImage with output drawnLine informationx1, y1 p1x2, y2 p2cx, cy (x1 x2) // 2, (y1 y2) // 2length math.hypot(x2 - x1, y2 - y1)info (x1, y1, x2, y2, cx, cy)if img is not None:cv2.circle(img, (x1, y1), 15, (255, 0, 255), cv2.FILLED)cv2.circle(img, (x2, y2), 15, (255, 0, 255), cv2.FILLED)cv2.line(img, (x1, y1), (x2, y2), (255, 0, 255), 3)cv2.circle(img, (cx, cy), 15, (255, 0, 255), cv2.FILLED)return length,info, imgelse:return length, infodef main():cap cv2.VideoCapture(0)detector HandDetector(detectionCon0.8, maxHands2)while True:# Get image framesuccess, img cap.read()# Find the hand and its landmarkshands, img detector.findHands(img) # with draw# hands detector.findHands(img, drawFalse) # without drawif hands:# Hand 1hand1 hands[0]lmList1 hand1[lmList] # List of 21 Landmark pointsbbox1 hand1[bbox] # Bounding box info x,y,w,hcenterPoint1 hand1[center] # center of the hand cx,cyhandType1 hand1[type] # Handtype Left or Rightfingers1 detector.fingersUp(hand1)if len(hands) 2:# Hand 2hand2 hands[1]lmList2 hand2[lmList] # List of 21 Landmark pointsbbox2 hand2[bbox] # Bounding box info x,y,w,hcenterPoint2 hand2[center] # center of the hand cx,cyhandType2 hand2[type] # Hand Type Left or Rightfingers2 detector.fingersUp(hand2)# Find Distance between two Landmarks. Could be same hand or different handslength, info, img detector.findDistance(lmList1[8], lmList2[8], img) # with draw# length, info detector.findDistance(lmList1[8], lmList2[8]) # with draw# Displaycv2.imshow(Image, img)cv2.waitKey(1)if __name__ __main__:main()2、主模块
原理 当检测到两只手时并且两只手的拇指和食指都抬起时通过计算拇指指尖之间的距离来获取初始距离 startDist。 当两只手的拇指和食指都抬起时计算当前拇指指尖之间的距离并根据距离变化来调整缩放因子 scale。这个变化可以通过当前距离减去初始距离得到。 根据计算得到的 scale 值调整图像的尺寸将另一张图像按照 scale 进行缩放。
这样当你用两只手的拇指和食指模拟捏取的动作时可以实现图像的放大和缩小效果。两只手之间的距离越大图像缩小得越多两只手之间的距离越小图像放大得越多。
这个应用可以在许多场景中使用比如在展示图像、视频播放或地图应用中通过手势来实现图像的交互式缩放效果。这个示例展示了手势识别在图像处理和交互中的潜在应用。 导入所需的库
import cv2
from HandTrackingModule import *配置摄像头创建手势检测器对象
cap cv2.VideoCapture(0)
cap.set(3, 1280) # 设置摄像头的宽度
cap.set(4, 720) # 设置摄像头的高度detector HandDetector(detectionCon0.8) # 创建手势检测器对象设置检测置信度阈值定义变量用于手势缩放操作
startDist None # 用于存储初始距离
scale 0 # 缩放值
cx, cy 500, 500 # 缩放中心的坐标进入主循环读取视频帧并执行手势识别和图像操作
while True:success, img cap.read() # 读取视频帧hands, img detector.findHands(img) # 手势检测# 读取一张图像用于操作img1 cv2.imread(cvarduino.jpg)if len(hands) 2:# 如果检测到两只手if detector.fingersUp(hands[0]) [1, 1, 0, 0, 0] and \detector.fingersUp(hands[1]) [1, 1, 0, 0, 0]:lmList1 hands[0][lmList] # 第一只手的关键点列表lmList2 hands[1][lmList] # 第二只手的关键点列表# 计算两个手指尖之间的距离作为缩放参考if startDist is None:length, info, img detector.findDistance(lmList1[8], lmList2[8], img)startDist lengthlength, info, img detector.findDistance(lmList1[8], lmList2[8], img)scale int((length - startDist) // 2) # 计算缩放值cx, cy info[4:] # 获取缩放中心的坐标print(scale) # 打印缩放值else:startDist Nonetry:h1, w1, _ img1.shapenewH, newW ((h1 scale) // 2) * 2, ((w1 scale) // 2) * 2img1 cv2.resize(img1, (newW, newH))# 在指定位置绘制缩放后的图像img[cy - newH // 2:cy newH // 2, cx - newW // 2:cx newW // 2] img1except:passcv2.imshow(Image, img) # 显示处理后的图像cv2.waitKey(1) # 等待按键主模块
全部代码:
import cv2
# from cvzone.HandTrackingModule import HandDetector
from HandTrackingModule import *
cap cv2.VideoCapture(0)
cap.set(3, 1280)
cap.set(4, 720)detector HandDetector(detectionCon0.8)
startDist None
scale 0
cx, cy 500,500
while True:success, img cap.read()hands, img detector.findHands(img)img1 cv2.imread(cvarduino.jpg)if len(hands) 2:# print(Zoom Gesture)# print(detector.fingersUp(hands[0]),detector.fingersUp(hands[1]))if detector.fingersUp(hands[0]) [1, 1, 0, 0, 0] and \detector.fingersUp(hands[1]) [1, 1, 0, 0, 0]:# print(zhenque )lmList1 hands[0][lmList]lmList2 hands[1][lmList]# point 8 is the tip of the index fingerif startDist is None:length, info, img detector.findDistance(lmList1[8], lmList2[8], img)# print(length)startDist lengthlength, info, img detector.findDistance(lmList1[8], lmList2[8], img)scale int((length - startDist) // 2)cx, cy info[4:]print(scale)else:startDist Nonetry:h1, w1, _ img1.shapenewH, newW ((h1scale)//2)*2, ((w1scale)//2)*2img1 cv2.resize(img1, (newW,newH))img[cy-newH//2:cy newH//2, cx-newW//2:cx newW//2] img1except:passcv2.imshow(Image, img)cv2.waitKey(1)有遇到的问题欢迎评论区留言
