yahboom
HomeLearn
Solution
Blog
Online Store
About Us
EN/中文
AI View Depth camera📖
01.Linux basic course
  • 1.Introduction to Linux system
  • 2.Ubuntu file system
  • 3.Ubuntu common commands
  • 4.Ubuntu common editors
  • 5.Ubuntu software operation commands
  • 6.Virtual machine installation
  • 7.SSH remote control
  • 8.VNC remote control
  • 9.Transfer files remotely
  • 10.Driver library and communication
  • 11.Static IP and hotspot mode
  • 12.Bind device ID
  • 13.Capacity expansion and resource allocation
  • 14.Update system software sources
  • 15.Set root user password
  • 16.sudo free password
  • 17.Connect to WiFi network
  • 18.View system version
  • 19.Customized service management
  • 20.Back up system image
02.ROS1-camera usage course
  • 1. Camera usage instructions
  • 2. Environment Construction
  • 3. Camera recording video
03.ROS1-OpenCV course
  • 1.Opencv Source CV Introduction
  • 2.Image reading and display
  • 3.Picture writing
  • 4.Picture Quality
  • 5.Pixel Operation
  • 6.Picture scaling
  • 7.Picture cutting
  • 8.Picture translation
  • 9.Picture mirroring
  • 10.Affine transformation
  • 11.Picture rotation
  • 12.Perspective transformation
  • 13.Grayscale processing
  • 14.Image binarization
  • 15.Edge detection
  • 16.Line segment drawing
  • 17.Rectangle and circle drawing
  • 18.Text and picture drawing
4.ROS1-basic course
  • 1.ROS introduction
  • 2.ROS installation
  • 3.ROS common command tools
  • 4.ROS workspace
  • 5.ROS function package
  • 6.ROS node
  • 7.ROS topic publisher
  • 8.ROS topic subscribers
  • 9.ROS service client
  • 10.ROS service server
  • 11.ROS action client
  • 12.ROS action server
  • 13.ROS custom message reception
  • 14.ROS-launch file
  • 15.ROS-TF transformation
  • 16.ROS parameter service
  • 17.ROS-rviz use
  • 18.ROS-rqt tool usage
  • 19.Topic message recording and playback
  • 20.urdf model introduction
  • 21.gazebo introduction
  • 22.ROS distributed communication
5.ROS1-Mediapipe course
  • 1.Hand detection
  • 2.Posture detection
  • 3.Overall detection
  • 4.Face detection
  • 5.Face recognition
  • 6.Face effects
  • 7.3D object recognition
  • 8.Brush
  • 9.Finger control
  • 10.Gesture recognition
6.ROS+Opencv application
  • 1.Camera calibration
  • 2.QR code
  • 3.Human body pose estimation
  • 4.Target detection
  • 5.ROS+Opencv basics
  • 6.Face recognition
  • 7.Harris corner detection
  • 8.Target tracking algorithm
  • 9.Contour moment
  • 10.Polygon outline
  • 11.Discrete Fourier transform algorithm
  • 12.Edge detection algorithm
  • 13.Face detection algorithm
  • 14.Optical flow detection algorithm
  • 15.Contour detection
  • 16.General contour detection
  • 17.Feature point tracking
  • 18.HLS color filtering
  • 19.Hough circle detection
  • 20.Hough line detection
  • 21.HSV color filtering
  • 22.LK optical flow algorithm
  • 23.Human body detection algorithm
  • 24.Phase-related displacement detection
  • 25.Image pyramid sampling algorithm
  • 26.RGB color filtering
  • 27.Clear background detection algorithm
  • 28.Simplified optical flow algorithm
  • 29.Simple filter
  • 30.Threshold image processing
  • 31.Watershed segmentation algorithm
  • 32.View point cloud data
  • 33.AR vision
  • 34.AR QR code tracking
  • 35.Color tracking
  • 36.Object tracking
07.ROS2-camera usage course
  • Instructions for using camera
08.ROS2-basic course
  • 1.Introduction to ROS2
  • 2.ROS2 install Humble
  • 3.ROS2 development environment
  • 4.ROS2 workspace
  • 5.ROS2 function package
  • 6.ROS2 node
  • 7.ROS2 topic communication
  • 8.ROS2 service communication
  • 9.ROS2 action communication
  • 10.ROS2 custom interface message
  • 11.ROS2 parameter service case
  • 12.ROS2 meta-function package
  • 13.ROS2 distributed communication
  • 14.ROS2 DDS
  • 15.ROS2 time related API
  • 16.ROS2 common command tools
  • 17.ROS2 rviz2 use
  • 18.ROS2 rqt toolbox
  • 19.ROS2 Launch startup file configuration
  • 20.ROS2 recording and playback tool
  • 21.ROS2 URDF model
  • 22.ROS2 Gazebo simulation platform
  • 23.ROS2 TF2 coordinate transformation
09.ROS2-OpenCV course
  • 1. ROS+opencv application
  • 2. QR code creation and recognition
  • 3. AR vision
10.ROS2-Mediapipe course
  • 1.Hand detection
  • 2.Posture detection
  • 3.Overall detection
  • 4.Face detection
  • 5.Personal insurance identification
11.ROS2-Depth camera course
  • 1. Use of depth camera
  • 2. Camera internal parameter calibration
  • 3. Color tracking
  • 4. KCF object tracking
  • 5. ORB_SLAM2 basics
  • 6. ORB_SLAM2 PCL mapping
  • 7. ORB_SLAM2 Octomap mapping
12.Bracket installation video
  • Bracket installation video
Download
  • VM_ROS1
  • VM_ROS2
  • Code-ROS1
  • Code-ROS2
  • 3D_File
  • ROS_Basic_VM
Download ZIP

Welcome to AI View Depth camera repository

10.Gesture recognition

10.Gesture recognition

Gesture recognition

The potential recognition designed based on the right direction can accurately recognize when specific conditions are met. The recognizable gestures include: [Zero, One, Two, Three, Four, Five, Six, Seven, Eight, Okay, Rock, Thumb_up (like), Thumb_down (thumb down), Heart_single (single)], totaling 14 categories.

1) Start

Input following command:

cd /home/yahboom/orbbec_ws/src/yahboomcar_mediapipe/scripts
python3 11_GestureRecognition.py

image-20231016115537786

2) Code

Code path: /home/yahboom/orbbec_ws/src/yahboomcar_mediapipe/scripts/11_GestureRecognition.py

​x
#!/usr/bin/env python3
# encoding: utf-8
import math
import time
import cv2 as cv
import numpy as np
import mediapipe as mp

class handDetector:
    def __init__(self, mode=False, maxHands=2, detectorCon=0.5, trackCon=0.5):
        self.tipIds = [4, 8, 12, 16, 20]
        self.mpHand = mp.solutions.hands
        self.mpDraw = mp.solutions.drawing_utils
        self.hands = self.mpHand.Hands(
            static_image_mode=mode,
            max_num_hands=maxHands,
            min_detection_confidence=detectorCon,
            min_tracking_confidence=trackCon
        )
        self.lmList = []
        self.lmDrawSpec = mp.solutions.drawing_utils.DrawingSpec(color=(0, 0, 255), thickness=-1, circle_radius=6)
        self.drawSpec = mp.solutions.drawing_utils.DrawingSpec(color=(0, 255, 0), thickness=2, circle_radius=2)

    def get_dist(self, point1, point2):
        x1, y1 = point1
        x2, y2 = point2
        return abs(math.sqrt(math.pow(abs(y1 - y2), 2) + math.pow(abs(x1 - x2), 2)))

    def calc_angle(self, pt1, pt2, pt3):
        point1 = self.lmList[pt1][1], self.lmList[pt1][2]
        point2 = self.lmList[pt2][1], self.lmList[pt2][2]
        point3 = self.lmList[pt3][1], self.lmList[pt3][2]
        a = self.get_dist(point1, point2)
        b = self.get_dist(point2, point3)
        c = self.get_dist(point1, point3)
        try:
            radian = math.acos((math.pow(a, 2) + math.pow(b, 2) - math.pow(c, 2)) / (2 * a * b))
            angle = radian / math.pi * 180
        except:
            angle = 0
        return abs(angle)


    def findHands(self, frame, draw=True):
        self.lmList = []
        img = np.zeros(frame.shape, np.uint8)
        img_RGB = cv.cvtColor(frame, cv.COLOR_BGR2RGB)
        self.results = self.hands.process(img_RGB)
        if self.results.multi_hand_landmarks:
            for i in range(len(self.results.multi_hand_landmarks)):
                if draw: self.mpDraw.draw_landmarks(frame, self.results.multi_hand_landmarks[i], self.mpHand.HAND_CONNECTIONS, self.lmDrawSpec, self.drawSpec)
                self.mpDraw.draw_landmarks(img, self.results.multi_hand_landmarks[i], self.mpHand.HAND_CONNECTIONS, self.lmDrawSpec, self.drawSpec)
                for id, lm in enumerate(self.results.multi_hand_landmarks[i].landmark):
                    h, w, c = frame.shape
                    cx, cy = int(lm.x * w), int(lm.y * h)
                    self.lmList.append([id, cx, cy])
        return frame, img

    def frame_combine(slef,frame, src):
        if len(frame.shape) == 3:
            frameH, frameW = frame.shape[:2]
            srcH, srcW = src.shape[:2]
            dst = np.zeros((max(frameH, srcH), frameW + srcW, 3), np.uint8)
            dst[:, :frameW] = frame[:, :]
            dst[:, frameW:] = src[:, :]
        else:
            src = cv.cvtColor(src, cv.COLOR_BGR2GRAY)
            frameH, frameW = frame.shape[:2]
            imgH, imgW = src.shape[:2]
            dst = np.zeros((frameH, frameW + imgW), np.uint8)
            dst[:, :frameW] = frame[:, :]
            dst[:, frameW:] = src[:, :]
        return dst

    def fingersUp(self):
        fingers=[]
        # Thumb
        if (self.calc_angle(self.tipIds[0],
                            self.tipIds[0] - 1,
                            self.tipIds[0] - 2) > 150.0) and (
                self.calc_angle(
                    self.tipIds[0] - 1,
                    self.tipIds[0] - 2,
                    self.tipIds[0] - 3) > 150.0): fingers.append(1)
        else:
            fingers.append(0)
        # 4 finger
        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)
        return fingers

    def get_gesture(self):
        gesture = ""
        fingers = self.fingersUp()
        if self.lmList[self.tipIds[0]][2] > self.lmList[self.tipIds[1]][2] and \
                self.lmList[self.tipIds[0]][2] > self.lmList[self.tipIds[2]][2] and \
                self.lmList[self.tipIds[0]][2] > self.lmList[self.tipIds[3]][2] and \
                self.lmList[self.tipIds[0]][2] > self.lmList[self.tipIds[4]][2] : gesture = "Thumb_down"

        elif self.lmList[self.tipIds[0]][2] < self.lmList[self.tipIds[1]][2] and \
                self.lmList[self.tipIds[0]][2] < self.lmList[self.tipIds[2]][2] and \
                self.lmList[self.tipIds[0]][2] < self.lmList[self.tipIds[3]][2] and \
                self.lmList[self.tipIds[0]][2] < self.lmList[self.tipIds[4]][2] and \
                self.calc_angle(self.tipIds[1] - 1, self.tipIds[1] - 2, self.tipIds[1] - 3) < 150.0 : gesture = "Thumb_up"
        if fingers.count(1) == 3 or fingers.count(1) == 4:
            if fingers[0] == 1 and (
                    self.get_dist(self.lmList[4][1:], self.lmList[8][1:])<self.get_dist(self.lmList[4][1:], self.lmList[5][1:])
            ): gesture = "OK"
            elif fingers[2] == fingers[3] == 0: gesture = "Rock"
            elif fingers.count(1) == 3: gesture = "Three"
            else: gesture = "Four"
        elif fingers.count(1) == 0: gesture = "Zero"
        elif fingers.count(1) == 1: gesture = "One"
        elif fingers.count(1) == 2:
            if fingers[0] == 1 and fingers[4] == 1: gesture = "Six"
            elif fingers[0] == 1 and self.calc_angle(4, 5, 8) > 90: gesture = "Eight"
            elif fingers[0] == fingers[1] == 1 and self.get_dist(self.lmList[4][1:], self.lmList[8][1:]) < 50: gesture = "Heart_single"
            else: gesture = "Two"
        elif fingers.count(1)==5:gesture = "Five"
        if self.get_dist(self.lmList[4][1:], self.lmList[8][1:]) < 60 and \
                self.get_dist(self.lmList[4][1:], self.lmList[12][1:]) < 60 and \
                self.get_dist(self.lmList[4][1:], self.lmList[16][1:]) < 60 and \
                self.get_dist(self.lmList[4][1:], self.lmList[20][1:]) < 60 : gesture = "Seven"
        if self.lmList[self.tipIds[0]][2] < self.lmList[self.tipIds[1]][2] and \
                self.lmList[self.tipIds[0]][2] < self.lmList[self.tipIds[2]][2] and \
                self.lmList[self.tipIds[0]][2] < self.lmList[self.tipIds[3]][2] and \
                self.lmList[self.tipIds[0]][2] < self.lmList[self.tipIds[4]][2] and \
                self.calc_angle(self.tipIds[1] - 1, self.tipIds[1] - 2, self.tipIds[1] - 3) > 150.0 : gesture = "Eight"
        return gesture

'''
Zero One Two Three Four Five Six Seven Eight
Ok: OK
Rock: rock
Thumb_up : 点赞
Thumb_down: 拇指向下
Heart_single: 单手比心
'''

if __name__ == '__main__':
    capture = cv.VideoCapture(0)
    capture.set(6, cv.VideoWriter.fourcc('M', 'J', 'P', 'G'))
    capture.set(cv.CAP_PROP_FRAME_WIDTH, 640)
    capture.set(cv.CAP_PROP_FRAME_HEIGHT, 480)
    print("capture get FPS : ", capture.get(cv.CAP_PROP_FPS))
    pTime = cTime = 0
    hand_detector = handDetector(detectorCon=0.75)
    while capture.isOpened():
        ret, frame = capture.read()
        # frame = cv.flip(frame, 1)
        frame, img = hand_detector.findHands(frame, draw=False)
        if len(hand_detector.lmList) != 0:
            totalFingers = hand_detector.get_gesture()
            cv.rectangle(frame, (0, 430), (230, 480), (0, 255, 0), cv.FILLED)
            cv.putText(frame, str(totalFingers), (10, 470), cv.FONT_HERSHEY_PLAIN, 2, (255, 0, 0), 2)
        if cv.waitKey(1) & 0xFF == ord('q'): break
        cTime = time.time()
        fps = 1 / (cTime - pTime)
        pTime = cTime
        text = "FPS : " + str(int(fps))
        cv.putText(frame, text, (10, 30), cv.FONT_HERSHEY_SIMPLEX, 0.9, (0, 0, 255), 1)
        dist = hand_detector.frame_combine(frame, img)
        cv.imshow('dist', dist)
        # cv.imshow('frame', frame)
        # cv.imshow('img', img)
    capture.release()
    cv.destroyAllWindows()

 

Finger control
Camera calibration

COMPANY

  • About us
  • Team Style
  • Blog

LEARNING & EXPLORATION

  • Tutorials
  • Edge AI hardware
  • Educational robots
  • Embedded intelligent hardware

WHERE TO BUY

  • Yahboom Online Store
  • Amazon
  • Alibaba
  • AliExpress
  • Mercado

TECHNOLOGY SUPPORT

  • Email: support@yahboom.com

BE A DISTRIBUTOR

  • Email: sales@yahboom.com
QR Code

Copyright © 2017-2026 Yahboom. All Rights Reserved.

EN/中文