DinoGame_opencv_finger_count.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Dino Game using OpenCV for finger counting\n",
    "\n",
    "    Saad Bazaz  - i180621\n",
    "    Abraar Raza - i180544\n",
    "\n",
    "Our first attempt of self-made finger detection algorithm, inspired by the following guide:\n",
    "    1. https://gogul.dev/software/hand-gesture-recognition-p1\n",
    "    2. https://gogul.dev/software/hand-gesture-recognition-p2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Installations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install imutils"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import imutils\n",
    "import numpy as np\n",
    "from sklearn.metrics import pairwise\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# For Game Emulation\n",
    "from selenium import webdriver\n",
    "from selenium.webdriver.common.by import By\n",
    "\n",
    "from selenium.webdriver.common.action_chains import ActionChains\n",
    "from selenium.webdriver.common.keys import Keys\n",
    "\n",
    "import time"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Initialize"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# global variables\n",
    "bg = None\n",
    "prev_pos = 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Initialize Selenium Browser\n",
    " \n",
    "# https://sites.google.com/a/chromium.org/chromedriver/home\n",
    "# Download ChromeDriver and extract. Then enter the fullpath here.\n",
    "PATH_TO_CHROME = r\"/Users/saadbazaz/Documents/FAST Studies/Digital Image Processing Lab/Project/Dino-Game-Hand-Gestures/t-rex-runner-gh-pages/chromedriver\"\n",
    "\n",
    "# The link to your Dino Game's index.html\n",
    "DINO_GAME_LINK = r\"/Users/saadbazaz/Documents/FAST Studies/Digital Image Processing Lab/Project/Dino-Game-Hand-Gestures/t-rex-runner-gh-pages/index.html\"\n",
    "\n",
    "\n",
    "browser = webdriver.Chrome(PATH_TO_CHROME)\n",
    "res = browser.get('file://' + DINO_GAME_LINK)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Initialize Selenium Action Chains\n",
    "\n",
    "actions = ActionChains(browser)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Segmentation\n",
    "Separate the foreground (hand) from the background (everything else)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Separate main background"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "#--------------------------------------------------\n",
    "# To find the running average over the background\n",
    "#--------------------------------------------------\n",
    "def run_avg(image, aWeight):\n",
    "    global bg\n",
    "    # initialize the background\n",
    "    if bg is None:\n",
    "        bg = image.copy().astype(\"float\")\n",
    "        return\n",
    "\n",
    "    # compute weighted average, accumulate it and update the background\n",
    "    cv2.accumulateWeighted(image, bg, aWeight)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Separate hand from segmented background"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "#---------------------------------------------\n",
    "# To segment the region of hand in the image\n",
    "#---------------------------------------------\n",
    "def segment(image, threshold=25):\n",
    "    global bg\n",
    "    # find the absolute difference between background and current frame\n",
    "    diff = cv2.absdiff(bg.astype(\"uint8\"), image)\n",
    "\n",
    "    # threshold the diff image so that we get the foreground\n",
    "    thresholded = cv2.threshold(diff, threshold, 255, cv2.THRESH_BINARY)[1]\n",
    "\n",
    "    # get the contours in the thresholded image\n",
    "    (cnts, _) = cv2.findContours(thresholded.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n",
    "\n",
    "    # return None, if no contours detected\n",
    "    if len(cnts) == 0:\n",
    "        return\n",
    "    else:\n",
    "        # based on contour area, get the maximum contour which is the hand\n",
    "        segmented = max(cnts, key=cv2.contourArea)\n",
    "        return (thresholded, segmented)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Recognize Hands using fingers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "#--------------------------------------------------------------\n",
    "# To count the number of fingers in the segmented hand region\n",
    "#--------------------------------------------------------------\n",
    "def count(thresholded, segmented):\n",
    "    # find the convex hull of the segmented hand region\n",
    "    chull = cv2.convexHull(segmented)\n",
    "\n",
    "    # find the most extreme points in the convex hull\n",
    "    extreme_top    = tuple(chull[chull[:, :, 1].argmin()][0])\n",
    "    extreme_bottom = tuple(chull[chull[:, :, 1].argmax()][0])\n",
    "    extreme_left   = tuple(chull[chull[:, :, 0].argmin()][0])\n",
    "    extreme_right  = tuple(chull[chull[:, :, 0].argmax()][0])\n",
    "\n",
    "    # find the center of the palm\n",
    "    cX = int((extreme_left[0] + extreme_right[0]) / 2)\n",
    "    cY = int((extreme_top[1] + extreme_bottom[1]) / 2)\n",
    "\n",
    "    # find the maximum euclidean distance between the center of the palm\n",
    "    # and the most extreme points of the convex hull\n",
    "    distance = pairwise.euclidean_distances([(cX, cY)], Y=[extreme_left, extreme_right, extreme_top, extreme_bottom])[0]\n",
    "    maximum_distance = distance[distance.argmax()]\n",
    "\n",
    "    # calculate the radius of the circle with 80% of the max euclidean distance obtained\n",
    "    radius = int(0.8 * maximum_distance)\n",
    "\n",
    "    # find the circumference of the circle\n",
    "    circumference = (2 * np.pi * radius)\n",
    "\n",
    "    # take out the circular region of interest which has \n",
    "    # the palm and the fingers\n",
    "    circular_roi = np.zeros(thresholded.shape[:2], dtype=\"uint8\")\n",
    "\t\n",
    "    # draw the circular ROI\n",
    "    cv2.circle(circular_roi, (cX, cY), radius, 255, 1)\n",
    "\n",
    "    # take bit-wise AND between thresholded hand using the circular ROI as the mask\n",
    "    # which gives the cuts obtained using mask on the thresholded hand image\n",
    "    circular_roi = cv2.bitwise_and(thresholded, thresholded, mask=circular_roi)\n",
    "\n",
    "    # compute the contours in the circular ROI\n",
    "    (cnts, _) = cv2.findContours(circular_roi.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)\n",
    "\n",
    "    # initalize the finger count\n",
    "    count = 0\n",
    "\n",
    "    # loop through the contours found\n",
    "    for c in cnts:\n",
    "        # compute the bounding box of the contour\n",
    "        (x, y, w, h) = cv2.boundingRect(c)\n",
    "\n",
    "        # increment the count of fingers only if -\n",
    "        # 1. The contour region is not the wrist (bottom area)\n",
    "        # 2. The number of points along the contour does not exceed\n",
    "        #     25% of the circumference of the circular ROI\n",
    "        if ((cY + (cY * 0.25)) > (y + h)) and ((circumference * 0.25) > c.shape[0]):\n",
    "            count += 1\n",
    "\n",
    "    return count"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Segment hand region"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "#---------------------------------------------\n",
    "# To segment the region of hand in the image\n",
    "#---------------------------------------------\n",
    "def segment(image, threshold=25):\n",
    "    global bg\n",
    "    # find the absolute difference between background and current frame\n",
    "    diff = cv2.absdiff(bg.astype(\"uint8\"), image)\n",
    "\n",
    "    # threshold the diff image so that we get the foreground\n",
    "    thresholded = cv2.threshold(diff, threshold, 255, cv2.THRESH_BINARY)[1]\n",
    "\n",
    "    # get the contours in the thresholded image\n",
    "    (cnts, _) = cv2.findContours(thresholded.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n",
    "\n",
    "    # return None, if no contours detected\n",
    "    if len(cnts) == 0:\n",
    "        return\n",
    "    else:\n",
    "        # based on contour area, get the maximum contour which is the hand\n",
    "        segmented = max(cnts, key=cv2.contourArea)\n",
    "        return (thresholded, segmented)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[STATUS] Please wait, calibrating...\n",
      "[STATUS] Calibration successful! You can now put your hand in the box.\n"
     ]
    },
    {
     "ename": "NoSuchWindowException",
     "evalue": "Message: no such window: window was already closed\n  (Session info: chrome=91.0.4472.106)\n",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNoSuchWindowException\u001b[0m                     Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-12-0e7e08bf379b>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m    113\u001b[0m                         \u001b[0mactions\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mActionChains\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbrowser\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    114\u001b[0m                         \u001b[0mactions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkey_up\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mKeys\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDOWN\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 115\u001b[0;31m                         \u001b[0mactions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mperform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    116\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    117\u001b[0m                     \u001b[0mprev_pos\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.8/site-packages/selenium/webdriver/common/action_chains.py\u001b[0m in \u001b[0;36mperform\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m     78\u001b[0m         \"\"\"\n\u001b[1;32m     79\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_driver\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mw3c\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 80\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mw3c_actions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mperform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     81\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     82\u001b[0m             \u001b[0;32mfor\u001b[0m \u001b[0maction\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_actions\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.8/site-packages/selenium/webdriver/common/actions/action_builder.py\u001b[0m in \u001b[0;36mperform\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m     74\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mencoded\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'actions'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     75\u001b[0m                 \u001b[0menc\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"actions\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mencoded\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 76\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdriver\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mCommand\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mW3C_ACTIONS\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0menc\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     77\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     78\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mclear_actions\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.8/site-packages/selenium/webdriver/remote/webdriver.py\u001b[0m in \u001b[0;36mexecute\u001b[0;34m(self, driver_command, params)\u001b[0m\n\u001b[1;32m    319\u001b[0m         \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcommand_executor\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdriver_command\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    320\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mresponse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 321\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0merror_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcheck_response\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    322\u001b[0m             response['value'] = self._unwrap_value(\n\u001b[1;32m    323\u001b[0m                 response.get('value', None))\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.8/site-packages/selenium/webdriver/remote/errorhandler.py\u001b[0m in \u001b[0;36mcheck_response\u001b[0;34m(self, response)\u001b[0m\n\u001b[1;32m    240\u001b[0m                 \u001b[0malert_text\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'alert'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'text'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    241\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mexception_class\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmessage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mscreen\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstacktrace\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0malert_text\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 242\u001b[0;31m         \u001b[0;32mraise\u001b[0m \u001b[0mexception_class\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmessage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mscreen\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstacktrace\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    243\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    244\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_value_or_default\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mobj\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdefault\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mNoSuchWindowException\u001b[0m: Message: no such window: window was already closed\n  (Session info: chrome=91.0.4472.106)\n"
     ]
    }
   ],
   "source": [
    "if __name__ == \"__main__\":\n",
    "    # initialize accumulated weight\n",
    "    accumWeight = 0.5\n",
    "\n",
    "    # get the reference to the webcam\n",
    "    camera = cv2.VideoCapture(0)\n",
    "\n",
    "    # region of interest (ROI) coordinates\n",
    "    top, right, bottom, left = 10, 350, 225, 590\n",
    "\n",
    "    # initialize num of frames\n",
    "    num_frames = 0\n",
    "\n",
    "    # calibration indicator\n",
    "    calibrated = False\n",
    "\n",
    "    # keep looping, until interrupted\n",
    "    while(True):\n",
    "        # get the current frame\n",
    "        (grabbed, frame) = camera.read()\n",
    "\n",
    "        # resize the frame\n",
    "        frame = imutils.resize(frame, width=700)\n",
    "\n",
    "        # flip the frame so that it is not the mirror view\n",
    "        frame = cv2.flip(frame, 1)\n",
    "\n",
    "        # clone the frame\n",
    "        clone = frame.copy()\n",
    "\n",
    "        # get the height and width of the frame\n",
    "        (height, width) = frame.shape[:2]\n",
    "\n",
    "        # get the ROI\n",
    "        roi = frame[top:bottom, right:left]\n",
    "\n",
    "        # convert the roi to grayscale and blur it\n",
    "        gray = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)\n",
    "        gray = cv2.GaussianBlur(gray, (7, 7), 0)\n",
    "\n",
    "        # to get the background, keep looking till a threshold is reached\n",
    "        # so that our weighted average model gets calibrated\n",
    "        if num_frames < 30:\n",
    "            run_avg(gray, accumWeight)\n",
    "            if num_frames == 1:\n",
    "                print(\"[STATUS] Please wait, calibrating...\")\n",
    "            elif num_frames == 29:\n",
    "                print(\"[STATUS] Calibration successful! You can now put your hand in the box.\")\n",
    "        else:\n",
    "            # segment the hand region\n",
    "            hand = segment(gray)\n",
    "\n",
    "            # check whether hand region is segmented\n",
    "            if hand is not None:\n",
    "                # if yes, unpack the thresholded image and\n",
    "                # segmented region\n",
    "                (thresholded, segmented) = hand\n",
    "\n",
    "                # draw the segmented region and display the frame\n",
    "                cv2.drawContours(clone, [segmented + (right, top)], -1, (0, 0, 255))\n",
    "\n",
    "                # count the number of fingers\n",
    "                fingers = count(thresholded, segmented)\n",
    "\n",
    "    \n",
    "                # If one finger is up, jump!\n",
    "                if fingers == 1:\n",
    "                    # print (\"Jump!\")\n",
    "\n",
    "\n",
    "                    if prev_pos == 1:\n",
    "                        pass  \n",
    "                    \n",
    "                    # if the previous state was duck, reverse the duck and jump.\n",
    "                    elif prev_pos == 2:\n",
    "                        actions = ActionChains(browser)                    \n",
    "                        actions.key_up(Keys.DOWN)\n",
    "                        actions.send_keys(Keys.SPACE)\n",
    "                        actions.perform() \n",
    "                    else:\n",
    "                        actions = ActionChains(browser)\n",
    "                        actions.send_keys(Keys.SPACE)\n",
    "                        actions.perform()                 \n",
    "\n",
    "                    prev_pos = 1\n",
    "\n",
    "                # If two fingers are up, duck.                    \n",
    "                elif fingers == 2:\n",
    "                    # print (\"Duck.\")\n",
    "\n",
    "                    \n",
    "                    # if the previous state was jump, reverse the jump and duck.                    \n",
    "                    if prev_pos == 1:\n",
    "                        actions = ActionChains(browser)\n",
    "                        actions.key_down(Keys.DOWN)\n",
    "                        actions.perform()     \n",
    "                    elif prev_pos == 2:\n",
    "                        pass\n",
    "\n",
    "                    else:\n",
    "                        actions = ActionChains(browser)\n",
    "                        actions.key_down(Keys.DOWN)\n",
    "                        actions.perform()                     \n",
    "\n",
    "                    prev_pos = 2\n",
    "\n",
    "\n",
    "                else:\n",
    "                    # print (\"Keep running.\")\n",
    "\n",
    "                    # if the previous state was duck, just reverse the duck.                                        \n",
    "                    if prev_pos == 2:\n",
    "                        actions = ActionChains(browser)                    \n",
    "                        actions.key_up(Keys.DOWN)\n",
    "                        actions.perform() \n",
    "\n",
    "                    prev_pos = 0                   \n",
    "                \n",
    "                # Show the number of fingers as a number\n",
    "                cv2.putText(clone, str(fingers), (70, 45), cv2.FONT_HERSHEY_SIMPLEX, 1, (0,0,255), 2)\n",
    "                \n",
    "                # show the thresholded image\n",
    "                cv2.imshow(\"Thesholded\", thresholded)\n",
    "\n",
    "        # draw the segmented hand\n",
    "        cv2.rectangle(clone, (left, top), (right, bottom), (0,255,0), 2)\n",
    "\n",
    "        # increment the number of frames\n",
    "        num_frames += 1\n",
    "\n",
    "        # display the frame with segmented hand\n",
    "        cv2.imshow(\"Video Feed\", clone)\n",
    "\n",
    "        # observe the keypress by the user\n",
    "        keypress = cv2.waitKey(1) & 0xFF\n",
    "\n",
    "        # if the user pressed \"q\", then stop looping\n",
    "        if keypress == ord(\"q\"):\n",
    "            break\n",
    "    \n",
    "    \n",
    "    # After the loop release the cap object\n",
    "    vid.release()\n",
    "    # Destroy all the windows\n",
    "    cv2.destroyAllWindows()\n",
    "    for i in range (1,5):\n",
    "        cv2.waitKey(1)        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "main__test_segmentation()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}