Skip to content

Instantly share code, notes, and snippets.

@eqs

eqs/Zebrafish_Notebook.ipynb

Created June 10, 2020 13:44
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save eqs/ea3ac4f628236cafc1a7d524817653d2 to your computer and use it in GitHub Desktop.
Save eqs/ea3ac4f628236cafc1a7d524817653d2 to your computer and use it in GitHub Desktop.
Download ZIP
Tracking Zebrafish by Tracktor
Display the source blob
Display the rendered blob
Raw
Zebrafish_Notebook.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# ゼブラフィッシュのトラッキングをやる\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"モジュールの読み込み"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'modules/tracktor/examples\\\\tracktor.py'"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# examplesの中のtracktor.pyへのパスを通しておく\n",
"import sys\n",
"sys.path.append('modules/tracktor/examples/')\n",
"\n",
"from tqdm import tqdm\n",
"\n",
"import numpy as np\n",
"import pandas as pd\n",
"import cv2\n",
"\n",
"import tracktor as tr\n",
"\n",
"tr.__file__"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"ツールの設定"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"video_path = 'modules/tracktor/videos/zebrafish_video.mp4'\n",
"\n",
"# トラッキングID\n",
"t_id = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H']\n",
"colours = [(0, 0, 255), (0, 255, 255), (255, 0, 255), (255, 255, 255),\n",
" (255, 255, 0),(255, 0, 0), (0, 255, 0), (0, 0, 0)]\n",
"\n",
"# 個体数\n",
"n_individuals = 5\n",
"# 個体が複数いるかどうかのフラグ\n",
"multi_object = n_individuals > 1\n",
"\n",
"# Adaptive Thresholdingのパラメタ\n",
"block_size = 51\n",
"offset = 25\n",
"\n",
"# 個体検出用のパラメタ（小さすぎる/でかすぎる個体を除くためのもの）\n",
"min_area = 50\n",
"max_area = 1000"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"個体追跡の実行"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 動画を開く\n",
"video = cv2.VideoCapture(video_path)\n",
"video.isOpened()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|███████████████████████████████████████████████████████████████████████████▉| 14994/15000 [09:55<00:00, 30.92it/s]"
]
}
],
"source": [
"# 位置をいれておく変数\n",
"loc_prev = np.zeros((n_individuals, 2)).tolist()\n",
"loc_curr = np.zeros((n_individuals, 2)).tolist()\n",
"df = []\n",
"\n",
"nframes = int(video.get(cv2.CAP_PROP_FRAME_COUNT))\n",
"pbar = tqdm(total=nframes)\n",
"\n",
"while True:\n",
" \n",
" pbar.update(1)\n",
" ok, image = video.read()\n",
" \n",
" if not ok:\n",
" break\n",
" \n",
" frame_idx = video.get(cv2.CAP_PROP_POS_FRAMES)\n",
"\n",
" image_bin = tr.colour_to_thresh(image, block_size, offset)\n",
"\n",
" final, contours, loc_prev, loc_curr = tr.detect_and_draw_contours(image, image_bin,\n",
" loc_prev, loc_curr,\n",
" min_area, max_area)\n",
" \n",
" if len(loc_curr) != n_individuals:\n",
" contours, loc_curr = tr.apply_k_means(contours, n_individuals, loc_curr)\n",
"\n",
"\n",
" row_idx, col_idx = tr.hungarian_algorithm(loc_prev, loc_curr)\n",
"\n",
" final, loc_curr, df = tr.reorder_and_draw(final, colours, n_individuals, col_idx,\n",
" loc_curr, df, multi_object, frame_idx)\n",
"\n",
" # Create output dataframe\n",
" for i in range(n_individuals):\n",
" df.append([frame_idx, loc_curr[i][0], loc_curr[i][1], t_id[i]])\n",
"\n",
"# リストをpandasのDataFrameに変換する\n",
"df = pd.DataFrame(df, columns = ['frame','pos_x','pos_y', 'id'])"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"video.release()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>frame</th>\n",
" <th>pos_x</th>\n",
" <th>pos_y</th>\n",
" <th>id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>184.785185</td>\n",
" <td>59.246914</td>\n",
" <td>A</td>\n",
" </tr>\n",
" <tr>\n",
" <td>1</td>\n",
" <td>1.0</td>\n",
" <td>782.726437</td>\n",
" <td>70.147126</td>\n",
" <td>B</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>1.0</td>\n",
" <td>301.841339</td>\n",
" <td>121.573508</td>\n",
" <td>C</td>\n",
" </tr>\n",
" <tr>\n",
" <td>3</td>\n",
" <td>1.0</td>\n",
" <td>195.685083</td>\n",
" <td>289.246777</td>\n",
" <td>D</td>\n",
" </tr>\n",
" <tr>\n",
" <td>4</td>\n",
" <td>1.0</td>\n",
" <td>229.135250</td>\n",
" <td>328.037274</td>\n",
" <td>E</td>\n",
" </tr>\n",
" <tr>\n",
" <td>5</td>\n",
" <td>2.0</td>\n",
" <td>178.861979</td>\n",
" <td>60.221354</td>\n",
" <td>A</td>\n",
" </tr>\n",
" <tr>\n",
" <td>6</td>\n",
" <td>2.0</td>\n",
" <td>781.649930</td>\n",
" <td>66.481172</td>\n",
" <td>B</td>\n",
" </tr>\n",
" <tr>\n",
" <td>7</td>\n",
" <td>2.0</td>\n",
" <td>302.521262</td>\n",
" <td>120.418381</td>\n",
" <td>C</td>\n",
" </tr>\n",
" <tr>\n",
" <td>8</td>\n",
" <td>2.0</td>\n",
" <td>194.862847</td>\n",
" <td>290.975694</td>\n",
" <td>D</td>\n",
" </tr>\n",
" <tr>\n",
" <td>9</td>\n",
" <td>2.0</td>\n",
" <td>227.624044</td>\n",
" <td>330.831694</td>\n",
" <td>E</td>\n",
" </tr>\n",
" <tr>\n",
" <td>10</td>\n",
" <td>3.0</td>\n",
" <td>174.192848</td>\n",
" <td>60.541507</td>\n",
" <td>A</td>\n",
" </tr>\n",
" <tr>\n",
" <td>11</td>\n",
" <td>3.0</td>\n",
" <td>783.514170</td>\n",
" <td>62.967611</td>\n",
" <td>B</td>\n",
" </tr>\n",
" <tr>\n",
" <td>12</td>\n",
" <td>3.0</td>\n",
" <td>303.360000</td>\n",
" <td>119.509630</td>\n",
" <td>C</td>\n",
" </tr>\n",
" <tr>\n",
" <td>13</td>\n",
" <td>3.0</td>\n",
" <td>193.814035</td>\n",
" <td>293.143860</td>\n",
" <td>D</td>\n",
" </tr>\n",
" <tr>\n",
" <td>14</td>\n",
" <td>3.0</td>\n",
" <td>226.002179</td>\n",
" <td>333.840959</td>\n",
" <td>E</td>\n",
" </tr>\n",
" <tr>\n",
" <td>15</td>\n",
" <td>4.0</td>\n",
" <td>169.844125</td>\n",
" <td>60.898082</td>\n",
" <td>A</td>\n",
" </tr>\n",
" <tr>\n",
" <td>16</td>\n",
" <td>4.0</td>\n",
" <td>785.762082</td>\n",
" <td>61.651797</td>\n",
" <td>B</td>\n",
" </tr>\n",
" <tr>\n",
" <td>17</td>\n",
" <td>4.0</td>\n",
" <td>304.232493</td>\n",
" <td>118.819328</td>\n",
" <td>C</td>\n",
" </tr>\n",
" <tr>\n",
" <td>18</td>\n",
" <td>4.0</td>\n",
" <td>192.903955</td>\n",
" <td>294.902072</td>\n",
" <td>D</td>\n",
" </tr>\n",
" <tr>\n",
" <td>19</td>\n",
" <td>4.0</td>\n",
" <td>224.186754</td>\n",
" <td>337.018458</td>\n",
" <td>E</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" frame pos_x pos_y id\n",
"0 1.0 184.785185 59.246914 A\n",
"1 1.0 782.726437 70.147126 B\n",
"2 1.0 301.841339 121.573508 C\n",
"3 1.0 195.685083 289.246777 D\n",
"4 1.0 229.135250 328.037274 E\n",
"5 2.0 178.861979 60.221354 A\n",
"6 2.0 781.649930 66.481172 B\n",
"7 2.0 302.521262 120.418381 C\n",
"8 2.0 194.862847 290.975694 D\n",
"9 2.0 227.624044 330.831694 E\n",
"10 3.0 174.192848 60.541507 A\n",
"11 3.0 783.514170 62.967611 B\n",
"12 3.0 303.360000 119.509630 C\n",
"13 3.0 193.814035 293.143860 D\n",
"14 3.0 226.002179 333.840959 E\n",
"15 4.0 169.844125 60.898082 A\n",
"16 4.0 785.762082 61.651797 B\n",
"17 4.0 304.232493 118.819328 C\n",
"18 4.0 192.903955 294.902072 D\n",
"19 4.0 224.186754 337.018458 E"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head(20)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"df.to_csv('zebrafish.csv', index=False)"
]
}
],
"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": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
@eqs
Copy link
Author

eqs commented Jun 10, 2020

https://nbviewer.jupyter.org/gist/eqs/ea3ac4f628236cafc1a7d524817653d2

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment