Skip to content

Commit

Permalink
final before writee up and submit
Browse files Browse the repository at this point in the history
  • Loading branch information
@lawga
lawga committed Dec 28, 2018
1 parent f9cd7cf commit 8a3d068
Show file tree
Hide file tree
Showing 16 changed files with 3,360 additions and 3,402 deletions.
315 changes: 313 additions & 2 deletions .ipynb_checkpoints/Final - Fixed all-checkpoint.ipynb
View file
Original file line number Diff line number Diff line change
@@ -1,6 +1,317 @@
{
"cells": [],
"metadata": {},
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(540, 960, 3)\n",
"Currently processing image: ./test_images/challenge_Moment.jpg\n",
"(540, 960, 3)\n",
"Currently processing image: ./test_images/solidWhiteCurve.jpg\n",
"(540, 960, 3)\n",
"Currently processing image: ./test_images/solidWhiteRight.jpg\n",
"(540, 960, 3)\n",
"Currently processing image: ./test_images/solidYellowCurve.jpg\n",
"(540, 960, 3)\n",
"Currently processing image: ./test_images/solidYellowCurve2.jpg\n",
"(540, 960, 3)\n",
"Currently processing image: ./test_images/solidYellowLeft.jpg\n",
"(540, 960, 3)\n",
"Currently processing image: ./test_images/whiteCarLaneSwitch.jpg\n"
]
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"import cv2\n",
"import os\n",
"import array\n",
"from os.path import join, basename\n",
"import matplotlib.image as mpimg\n",
"from lane_finding import lane_finding_pipeline\n",
"import numpy as np\n",
"\n",
"\n",
"# Import everything needed to edit/save/watch video clips\n",
"from moviepy.editor import VideoFileClip\n",
"from IPython.display import HTML\n",
"\n",
"if __name__ == '__main__':\n",
"\n",
" verbose = True\n",
" #if verbose:\n",
" #plt.ion()\n",
" # figManager = plt.get_current_fig_manager()\n",
" #figManager.window.showMaximized()\n",
"\n",
" input_image_list = os.listdir(\"test_images/\")\n",
" input_image_dir = \"./test_images/\"\n",
" input_image_list = [join(input_image_dir, name) for name in input_image_list]\n",
" image_out_dir = 'test_images_output'\n",
"\n",
"\n",
" for image in input_image_list:\n",
" # Read in the image\n",
" image_raw = mpimg.imread(image)\n",
" image_raw_resized = cv2.resize(image_raw, dsize=(960,540), interpolation=cv2.INTER_CUBIC)\n",
" \n",
" imshape = image_raw_resized.shape\n",
" print (imshape)\n",
" imshape = image_raw.shape\n",
" vertices = np.array([[(100,imshape[0]),(450, 320), (520,320), (925,imshape[0])]], dtype=np.int32)\n",
" img_out = lane_finding_pipeline(image_raw, vertices)\n",
" out_path = join(image_out_dir, basename(image))\n",
" mpimg.imsave(out_path, img_out)\n",
"\n",
" print('Currently processing image: {}'.format(image))\n",
" \n",
" \n",
"\n",
" \n",
" \n",
" def process_image(image):\n",
" # NOTE: The output you return should be a color image (3 channel) for processing video below\n",
" # TODO: put your pipeline here,\n",
" # you should return the final output (image where lines are drawn on lanes)\n",
" \n",
" image = cv2.resize(image, dsize=(960,540), interpolation=cv2.INTER_CUBIC)\n",
" \n",
" #vertices = np.array([[(180,imshape[0]-50),(480, 320), (530,320), (825,imshape[0]-50)]], dtype=np.int32)\n",
" vertices = np.array([[(100,imshape[0]),(450, 320), (520,320), (925,imshape[0])]], dtype=np.int32)\n",
" result = lane_finding_pipeline(image, vertices)\n",
"\n",
" return result\n",
" \n",
" \n",
" \n",
" "
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[MoviePy] >>>> Building video test_videos_output/solidWhiteRight.mp4\n",
"[MoviePy] Writing video test_videos_output/solidWhiteRight.mp4\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|█████████▉| 221/222 [00:11<00:00, 19.92it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[MoviePy] Done.\n",
"[MoviePy] >>>> Video ready: test_videos_output/solidWhiteRight.mp4 \n",
"\n",
"CPU times: user 4.29 s, sys: 670 ms, total: 4.96 s\n",
"Wall time: 12.9 s\n"
]
}
],
"source": [
"white_output = 'test_videos_output/solidWhiteRight.mp4'\n",
"## To speed up the testing process you may want to try your pipeline on a shorter subclip of the video\n",
"## To do so add .subclip(start_second,end_second) to the end of the line below\n",
"## Where start_second and end_second are integer values representing the start and end of the subclip\n",
"## You may also uncomment the following line for a subclip of the first 5 seconds\n",
"#clip1 = VideoFileClip(\"test_videos/solidWhiteRight.mp4\").subclip(0,2)\n",
"clip1 = VideoFileClip(\"test_videos/solidWhiteRight.mp4\")\n",
"white_clip = clip1.fl_image(process_image) #NOTE: this function expects color images!!\n",
"%time white_clip.write_videofile(white_output, audio=False)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"\n",
" <video width=\"960\" height=\"540\" controls>\n",
" <source src=\"test_videos_output/solidWhiteRight.mp4\">\n",
" </video>\n",
" "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"HTML(\"\"\"\n",
" <video width=\"960\" height=\"540\" controls>\n",
" <source src=\"{0}\">\n",
" </video>\n",
" \"\"\".format(white_output))"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"def process_image(image):\n",
" # NOTE: The output you return should be a color image (3 channel) for processing video below\n",
" # TODO: put your pipeline here,\n",
" # you should return the final output (image where lines are drawn on lanes)\n",
" \n",
" image = cv2.resize(image, dsize=(960,540), interpolation=cv2.INTER_CUBIC)\n",
" \n",
" vertices = np.array([[(180,imshape[0]-50),(370, 360), (600,360), (825,imshape[0]-50)]], dtype=np.int32)\n",
" result = lane_finding_pipeline(image, vertices)\n",
"\n",
" return result"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[MoviePy] >>>> Building video test_videos_output/challenge.mp4\n",
"[MoviePy] Writing video test_videos_output/challenge.mp4\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 251/251 [00:15<00:00, 18.40it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[MoviePy] Done.\n",
"[MoviePy] >>>> Video ready: test_videos_output/challenge.mp4 \n",
"\n",
"CPU times: user 7.35 s, sys: 700 ms, total: 8.05 s\n",
"Wall time: 16.7 s\n"
]
}
],
"source": [
"challenge_output = 'test_videos_output/challenge.mp4'\n",
"## To speed up the testing process you may want to try your pipeline on a shorter subclip of the video\n",
"## To do so add .subclip(start_second,end_second) to the end of the line below\n",
"## Where start_second and end_second are integer values representing the start and end of the subclip\n",
"## You may also uncomment the following line for a subclip of the first 5 seconds\n",
"#clip3 = VideoFileClip('test_videos/challenge.mp4').subclip(4,6)\n",
"clip3 = VideoFileClip('test_videos/challenge.mp4')\n",
"challenge_clip = clip3.fl_image(process_image)\n",
"%time challenge_clip.write_videofile(challenge_output, audio=False)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"<video width=\"960\" height=\"540\" controls>\n",
" <source src=\"test_videos_output/challenge.mp4\">\n",
"</video>\n"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"HTML(\"\"\"\n",
"<video width=\"960\" height=\"540\" controls>\n",
" <source src=\"{0}\">\n",
"</video>\n",
"\"\"\".format(challenge_output))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"image = mpimg.imread('./test_images/challenge_Moment.jpg')\n",
"image_raw_resized = cv2.resize(image, dsize=(960,540), interpolation=cv2.INTER_CUBIC)\n",
"\n",
"imshape = image_raw_resized.shape\n",
"print (imshape)\n",
"vertices = np.array([[(180,imshape[0]-50),(370, 360), (600,360), (825,imshape[0]-50)]], dtype=np.int32)\n",
"img_out = lane_finding_pipeline(image_raw_resized, vertices)\n",
"out_path = './test_images_output/challenge_Moment.jpg'\n",
"mpimg.imsave(out_path, img_out)\n",
"\n",
"print('Currently processing image: {}'.format('challenge_Moment.jpg'))"
]
},
{
"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": "3.5.2"
},
"widgets": {
"state": {},
"version": "1.1.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Loading

0 comments on commit 8a3d068

Please sign in to comment.