neural_network/frame_diff/.ipynb_checkpoints/frame_diff-checkpoint.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "d8731107-ae34-4759-a7be-c590f025b8d7",
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "69a79561-8c31-4867-bc56-c25ca2dda93a",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"加权平均灰度处理\"\"\"\n",
    "def frame_gray(frame):\n",
    "    return np.dot(frame[..., :], np.array([0.114, 0.578, 0.299]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b275698e-9437-44f7-a793-96a64942e491",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"帧差法\"\"\"\n",
    "def diff_algorithm(curr, next, threshold):\n",
    "    curr = frame_gray(curr)\n",
    "    next = frame_gray(next)\n",
    "    diff = np.abs(curr - next)\n",
    "    diff[np.where(diff < threshold)] = 0\n",
    "    diff[np.where(diff >= threshold)] = 255\n",
    "    return diff"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "0331ed3e-761f-4e21-9465-558e49cdd442",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2, 2, 2, 3)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(2, 2) + (2,3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ab51ab14-d78e-411d-81ca-8635ca5dc4e2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(range(5 * 3 - 1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "df7c110d-c845-4751-af8f-c28709b9b7aa",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"腐蚀\"\"\"\n",
    "def dilate(gray, kernel):\n",
    "    h_k, w_k = kernel.shape[0], kernel.shape[1]\n",
    "    h_g, w_g =  gray.shape[0], gray.shape[1]\n",
    "    h, w = h_g + (h_k // 2) * 2, w_g + (w_k // 2) * 2\n",
    "    size = np.maximum(h, w)\n",
    "    temp = np.ones((size, size)) * 255\n",
    "    temp[h_k // 2: h - (h_k // 2), w_k // 2: w - (w_k // 2)] = gray\n",
    "    return temp\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e0c94bfd-ec08-4ec4-a599-71c635fc74f5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'膨胀'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"\"\"膨胀\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "bac46e68-03ad-4961-a729-77f36e155fe5",
   "metadata": {},
   "outputs": [],
   "source": [
    "def image_preprocessing(frame,kernel_1,kernel_2):\n",
    "    frame = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)#rgb转hsv\n",
    "    frame = cv2.dilate(frame, kernel_1, 1)#膨胀\n",
    "    frame = cv2.erode(frame, kernel_2, iterations=1)#腐蚀\n",
    "    return frame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "d21a5933-b44a-494d-a37a-c63973fd4a73",
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import numpy as np\n",
    "cap = cv2.VideoCapture(0)\n",
    "kernel_1 = np.ones((3, 3), dtype=np.uint8) # 卷积核变为4*4\n",
    "kernel_2 = np.ones((3, 3), dtype=np.uint8)\n",
    "ret, curr_frame = cap.read()\n",
    "curr_frame = image_preprocessing(curr_frame, kernel_1, kernel_2)\n",
    "while True:\n",
    "    ret, next_frame = cap.read()\n",
    "    if ret:\n",
    "        next_frame = image_preprocessing(next_frame, kernel_1, kernel_2)\n",
    "        diff = cv2.absdiff(next_frame, curr_frame)\n",
    "        _, thresh = cv2.threshold(diff, 30, 255, cv2.THRESH_BINARY)\n",
    "        gaussian = cv2.GaussianBlur(thresh, (3, 3), 0)\n",
    "        gaussian = cv2.flip(gaussian, 180)\n",
    "        cv2.imshow('video', gaussian)\n",
    "        k = cv2.waitKey(30) & 0xff\n",
    "        if k == 27:\n",
    "            break\n",
    "    else:\n",
    "        break\n",
    "    curr_frame = next_frame\n",
    "cv2.destroyAllWindows()\n",
    "cap.release()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a3aeb064-bf91-4c65-ac9f-f26db688fc33",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cb0c8568-4002-448d-8740-057b839422a3",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}