04-Cam Shift Tracking.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Capture Video Stream"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cap = cv2.VideoCapture('Video/face_track.mp4')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## take first frame of the video"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ret, frame = cap.read()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## setup the initial tracking window"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "face_casc = cv2.CascadeClassifier('Haarcascades/haarcascade_frontalface_default.xml')\n",
    "\n",
    "face_rects = face_casc.detectMultiScale(frame)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## convert the list to a tuple"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "face+x, face_y, w, h = tuple(face_rects[0])\n",
    "\n",
    "track_window = (face_x, face_y, w, h) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## setup the list to a tuple"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "roi = frame[face_y:face_y+h, face_x:face_x+w]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## HSV color maping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "hsv_roi = cv2cvtColor(roi, cv2.COLOR_BGR2HSV)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Histogram to target on each frame for the meanshift calculation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "roi_hist = cv2.calcHist([hsv_roi], [0], None, [180], [0, 180])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## normalise the histogarm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cv2.normalize(roi_hist, roi_hist, 0, 255, cv2.NORM_MINMAX)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## set the termination criteria\n",
    "#### 10 iterations or move 1 point"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "term_crit = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, 10, 1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Magic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# while loop\n",
    "while True:\n",
    "    \n",
    "    # capture video\n",
    "    ret, farme = cap.read()\n",
    "    \n",
    "    # if statement\n",
    "    if ret == True:\n",
    "        \n",
    "        # frame in HSV\n",
    "        hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)\n",
    "        \n",
    "        # calculate the base of ROI\n",
    "        dest_roi = cv2.calcBackProject([hsv], [0], roi_hist, [0, 180], 1)\n",
    "        \n",
    "        # Camshift to get the new coordinates of reactangle\n",
    "        ret, track_window = cv2.camShift(dest_roi, track_window, term_crit)\n",
    "        \n",
    "        # Draw rectangle on image\n",
    "        pts1 = cv2.boxPoints(ret)\n",
    "        pts2 = np.int0(pts)\n",
    "        img2 = cv2.polylines(frame, [pts], True, (0, 255, 0), 5)\n",
    "        \n",
    "        # Open new window and display\n",
    "        cv2.imshow('Cam Shift', img2)\n",
    "        \n",
    "        # Close Window\n",
    "        if cv2.waitKey(50) & 0xFF == 27:\n",
    "            break\n",
    "        \n",
    "    #else\n",
    "    else:\n",
    "        break\n",
    "\n",
    "# Release and Destroy\n",
    "cap.release()\n",
    "cv2.destroyAllWindows()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}