Pose_Estimation.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# POSE ESTIMATION"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## OVERLAP POSE (NO OUTPUT - LIVE FEED)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import mediapipe as mp\n",
    "\n",
    "video_path = 'INPUT_VIDEO.mp4'\n",
    "\n",
    "mp_drawing = mp.solutions.drawing_utils\n",
    "mp_pose = mp.solutions.pose\n",
    "\n",
    "# Setup mediapipe instance\n",
    "with mp_pose.Pose(min_detection_confidence=0.5, min_tracking_confidence=0.5) as pose:\n",
    "    \n",
    "    cap = cv2.VideoCapture(video_path)\n",
    "\n",
    "    while cap.isOpened():\n",
    "        ret, frame = cap.read()\n",
    "\n",
    "        if not ret:\n",
    "            break\n",
    "\n",
    "        # Recolor image to RGB\n",
    "        image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)\n",
    "        image.flags.writeable = False\n",
    "\n",
    "        # Make detection\n",
    "        results = pose.process(image)\n",
    "\n",
    "        # Recolor back to BGR\n",
    "        image.flags.writeable = True\n",
    "        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)\n",
    "\n",
    "        # Render detections\n",
    "        mp_drawing.draw_landmarks(image, results.pose_landmarks, mp_pose.POSE_CONNECTIONS,\n",
    "                                mp_drawing.DrawingSpec(color=(245,117,66), thickness=2, circle_radius=2), \n",
    "                                mp_drawing.DrawingSpec(color=(245,66,230), thickness=2, circle_radius=2))\n",
    "\n",
    "        cv2.imshow('Mediapipe Feed', image)\n",
    "\n",
    "        if cv2.waitKey(10) & 0xFF == ord('q'):\n",
    "            break\n",
    "\n",
    "    cap.release()\n",
    "    cv2.destroyAllWindows()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## NO OVERLAP POSE (NO OUTPUT - LIVE FEED - BLACK BACKGROUND) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import mediapipe as mp\n",
    "import numpy as np\n",
    "\n",
    "video_path = 'INPUT_VIDEO.mp4'\n",
    "\n",
    "mp_drawing = mp.solutions.drawing_utils\n",
    "mp_pose = mp.solutions.pose\n",
    "\n",
    "# Setup mediapipe instance\n",
    "with mp_pose.Pose(min_detection_confidence=0.5, min_tracking_confidence=0.5) as pose:\n",
    "    \n",
    "    cap = cv2.VideoCapture(video_path)\n",
    "\n",
    "    while cap.isOpened():\n",
    "        ret, frame = cap.read()\n",
    "\n",
    "        if not ret:\n",
    "            break\n",
    "\n",
    "        # Recolor image to RGB\n",
    "        image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)\n",
    "        image.flags.writeable = False\n",
    "\n",
    "        # Make detection\n",
    "        results = pose.process(image)\n",
    "\n",
    "        # Recolor back to BGR\n",
    "        image.flags.writeable = True\n",
    "        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)\n",
    "\n",
    "        # Mask - Black Background\n",
    "        mask = np.zeros_like(image)\n",
    "        # Pose Rendering (only figure)\n",
    "        mp_drawing.draw_landmarks(mask, results.pose_landmarks, mp_pose.POSE_CONNECTIONS,\n",
    "                                mp_drawing.DrawingSpec(color=(245,117,66), thickness=2, circle_radius=2), \n",
    "                                mp_drawing.DrawingSpec(color=(245,66,230), thickness=2, circle_radius=2))\n",
    "\n",
    "        # Mask + transparency\n",
    "        alpha = 0.6  #  transparency parameter\n",
    "        background = np.zeros_like(image)\n",
    "        image = cv2.addWeighted(background, 1, mask, alpha, 0)\n",
    "\n",
    "        cv2.imshow('Mediapipe Feed', image)\n",
    "\n",
    "        if cv2.waitKey(10) & 0xFF == ord('q'):\n",
    "            break\n",
    "\n",
    "    cap.release()\n",
    "    cv2.destroyAllWindows()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## OVERLAP POSE (OUTPUT VIDEO - LIVE FEED)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import mediapipe as mp\n",
    "import numpy as np\n",
    "\n",
    "video_path = 'INPUT_VIDEO.mp4'\n",
    "\n",
    "mp_drawing = mp.solutions.drawing_utils\n",
    "mp_pose = mp.solutions.pose\n",
    "\n",
    "# Setup mediapipe instance\n",
    "with mp_pose.Pose(min_detection_confidence=0.5, min_tracking_confidence=0.5) as pose:\n",
    "    \n",
    "    cap = cv2.VideoCapture(video_path)\n",
    "\n",
    "    # Video properties\n",
    "    width = int(cap.get(3))\n",
    "    height = int(cap.get(4))\n",
    "    fps = cap.get(5)\n",
    "\n",
    "    # VideoWriter object for new output\n",
    "    fourcc = cv2.VideoWriter_fourcc(*'mp4v')  # Códec Selection\n",
    "    out = cv2.VideoWriter('OUTPUT_VIDEO.mp4', fourcc, fps, (width, height))\n",
    "\n",
    "    while cap.isOpened():\n",
    "        ret, frame = cap.read()\n",
    "\n",
    "        if not ret:\n",
    "            break\n",
    "\n",
    "        # Recolor image to RGB\n",
    "        image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)\n",
    "        image.flags.writeable = False\n",
    "\n",
    "        # Make detection\n",
    "        results = pose.process(image)\n",
    "\n",
    "        # Recolor back to BGR\n",
    "        image.flags.writeable = True\n",
    "        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)\n",
    "\n",
    "        # Pose Rendering\n",
    "        mp_drawing.draw_landmarks(image, results.pose_landmarks, mp_pose.POSE_CONNECTIONS,\n",
    "                                   mp_drawing.DrawingSpec(color=(245,117,66), thickness=2, circle_radius=2), \n",
    "                                   mp_drawing.DrawingSpec(color=(245,66,230), thickness=2, circle_radius=2))\n",
    "\n",
    "        # Video Generation\n",
    "        out.write(image)\n",
    "\n",
    "        # Live Feed\n",
    "        cv2.imshow('Mediapipe Feed', image)\n",
    "\n",
    "        if cv2.waitKey(10) & 0xFF == ord('q'):\n",
    "            break\n",
    "\n",
    "    cap.release()\n",
    "    out.release()\n",
    "    cv2.destroyAllWindows()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## NO OVERLAP POSE (OUTPUT VIDEO - LIVE FEED - BLACK BACKGROUND) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import mediapipe as mp\n",
    "import numpy as np\n",
    "\n",
    "video_path = 'INPUT_VIDEO.mp4'\n",
    "output_video_path = 'OUTPUT_VIDEO.mp4'\n",
    "\n",
    "mp_drawing = mp.solutions.drawing_utils\n",
    "mp_pose = mp.solutions.pose\n",
    "\n",
    "# Setup mediapipe instance\n",
    "with mp_pose.Pose(min_detection_confidence=0.5, min_tracking_confidence=0.5) as pose:\n",
    "    \n",
    "    cap = cv2.VideoCapture(video_path)\n",
    "\n",
    "    # Video properties\n",
    "    width = int(cap.get(3))\n",
    "    height = int(cap.get(4))\n",
    "    fps = cap.get(5)\n",
    "\n",
    "    # VideoWriter object for new output\n",
    "    fourcc = cv2.VideoWriter_fourcc(*'mp4v')  # Códec Selection\n",
    "    out = cv2.VideoWriter(output_video_path, fourcc, fps, (width, height))\n",
    "\n",
    "    while cap.isOpened():\n",
    "        ret, frame = cap.read()\n",
    "\n",
    "        if not ret:\n",
    "            break\n",
    "\n",
    "        # Recolor image to RGB\n",
    "        image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)\n",
    "        image.flags.writeable = False\n",
    "\n",
    "        # Make detection\n",
    "        results = pose.process(image)\n",
    "\n",
    "        # Recolor back to BGR\n",
    "        image.flags.writeable = True\n",
    "        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)\n",
    "\n",
    "        # Mask - Black Background\n",
    "        mask = np.zeros_like(image)\n",
    "        # Pose Rendering\n",
    "        mp_drawing.draw_landmarks(mask, results.pose_landmarks, mp_pose.POSE_CONNECTIONS,\n",
    "                                mp_drawing.DrawingSpec(color=(245,117,66), thickness=2, circle_radius=2), \n",
    "                                mp_drawing.DrawingSpec(color=(245,66,230), thickness=2, circle_radius=2))\n",
    "\n",
    "        # Mask + transparency\n",
    "        alpha = 0.6  # Transparency parameter\n",
    "        background = np.zeros_like(image)\n",
    "        image_with_poses = cv2.addWeighted(background, 1, mask, alpha, 0)\n",
    "\n",
    "        # Video Generation\n",
    "        out.write(image_with_poses)\n",
    "\n",
    "        cv2.imshow('Mediapipe Feed', image_with_poses)\n",
    "\n",
    "        if cv2.waitKey(10) & 0xFF == ord('q'):\n",
    "            break\n",
    "\n",
    "    cap.release()\n",
    "    out.release()\n",
    "    cv2.destroyAllWindows()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Original code from:\n",
    "#### [MediaPipePoseEstimation - Nicholas Renotte](https://github.com/nicknochnack/MediaPipePoseEstimation)"
   ]
  }
 ],
 "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": "3.10.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}