{ "cells": [ { "cell_type": "markdown", "metadata": { "_cell_guid": "8c845e6f-3f0a-40ee-867e-b829f3fce103" }, "source": [ "# Argument setting" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "2ea30baf-0060-be1f-ec0c-c277670a87dd" }, "outputs": [], "source": [ "AUG_METHOD = \"Rotate_180\" # \"None\" or string in AUG_METHOD_List\n", "SYSTEM = \"Kaggle\" # \"Paperspace\" # \n", "AUG_METHOD_List = [\"Flip\", \"Rotate_90\", \"Rotate_180\", \"Rotate_270\", \"Flip_Rotate_90\", \"Flip_Rotate_180\", \"Flip_Rotate_270\"]" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "9692f1be-8335-6f6b-efc6-9c567b24f809" }, "source": [ "# import module" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "81d8b005-b955-c31c-d22a-c6c31077457e" }, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd\n", "import os\n", "import cv2\n", "import matplotlib.pyplot as plt\n", "import skimage.feature\n", "#%matplotlib inline\n", "\n", "#from subprocess import check_output\n", "#print(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "ffcf2c0b-b5ba-bff5-3582-a94ee779e758" }, "source": [ "# parse arg" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "08415fd9-e7f2-c783-55e6-7d0d3c445f45" }, "outputs": [], "source": [ "import sys\n", "arg = sys.argv[1:]\n", "\n", "if('-f' in arg):\n", " arg = ['Basic', '32', 'Whole', 'Train']\n", "else:\n", " new_arg = []\n", " if('Basic' in arg):\n", " idx = arg.index('Basic')\n", " new_arg.append('Basic')\n", " new_arg.append(arg[idx+1])\n", " elif('Advance' in arg):\n", " idx = arg.index('Advance')\n", " new_arg.append('Advance')\n", " new_arg.append(arg[idx+1])\n", " else:\n", " print(\"Please enter \\\"Basic\\\" or \\\"Advance\\\".\")\n", " \n", " if('Whole' in arg):\n", " new_arg.append('Whole')\n", " elif('Black' in arg):\n", " new_arg.append('Black')\n", " else:\n", " print(\"Please enter \\\"Whole\\\" or \\\"Black\\\".\")\n", " \n", " if('Test' in arg):\n", " new_arg.append('Test')\n", " elif('Train' in arg):\n", " new_arg.append('Train')\n", " else:\n", " print(\"Please enter \\\"Test\\\" or \\\"Train\\\".\")\n", " \n", " arg = new_arg" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "7f7f88ab-93b0-a090-7219-7d82085e747e" }, "source": [ "# read files" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "0d49442f-a126-3603-be58-d21f3200e03b" }, "outputs": [], "source": [ "Path_Type = \"{0}/{1}_{2}_{3}\".format(arg[3], arg[0], arg[1], arg[2])\n", "Path_Type\n", "PS_Root_Path = \"/home/paperspace/Project/Sealion\"\n", "\n", "if (AUG_METHOD == \"None\"):\n", " AUG_Add_Path = \"\" \n", "elif (AUG_METHOD in AUG_METHOD_List):\n", " AUG_Add_Path = \"Augment/{0}/\".format(AUG_METHOD) " ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "98a9158d-9e38-b191-8246-cf612816916a" }, "outputs": [], "source": [ "Path_Sealion = \"{0}/{1}/\".format(PS_Root_Path, Path_Type) if SYSTEM == \"Paperspace\" else \"./\"\n", "Path_Train = \"{0}/TrainSmall2/Train/\".format(PS_Root_Path) if SYSTEM == \"Paperspace\" else \"../input/Train/\" \n", "Path_Dotted = \"{0}/TrainSmall2/TrainDotted/\".format(PS_Root_Path) if SYSTEM == \"Paperspace\" else \"../input/TrainDotted/\" # \n", "file_names = os.listdir(Path_Train)\n", "file_names = sorted(file_names, key=lambda \n", " item: (int(item.partition('.')[0]) if item[0].isdigit() else float('inf'), item))\n", "\n", "file_names = file_names[1:2]\n", "print(file_names)" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "33cd3904-8858-e39f-790f-b8eb0cf3dbf6" }, "source": [ "# Create directory " ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "83c9bb8a-87d0-09f7-655f-82265861d9bf" }, "outputs": [], "source": [ "if(SYSTEM == \"Paperspace\"):\n", " if(AUG_METHOD == \"None\"):\n", " if not os.path.exists(\"{0}/{1}\".format(PS_Root_Path, Path_Type)):\n", " os.makedirs(\"{0}/{1}\".format(PS_Root_Path, Path_Type))\n", " if not os.path.exists(\"{0}/{1}/labels\".format(PS_Root_Path, Path_Type)):\n", " os.makedirs(\"{0}/{1}/labels\".format(PS_Root_Path, Path_Type)) \n", " if not os.path.exists(\"{0}/{1}/JPEGImages\".format(PS_Root_Path, Path_Type)):\n", " os.makedirs(\"{0}/{1}/JPEGImages\".format(PS_Root_Path, Path_Type)) \n", " if not os.path.exists(\"{0}/{1}/DotImages\".format(PS_Root_Path, Path_Type)):\n", " os.makedirs(\"{0}/{1}/DotImages\".format(PS_Root_Path, Path_Type)) \n", "\n", " elif(AUG_METHOD in AUG_METHOD_List):\n", " if not os.path.exists(\"{0}/{1}\".format(PS_Root_Path, Path_Type)):\n", " os.makedirs(\"{0}/{1}\".format(PS_Root_Path, Path_Type))\n", " if not os.path.exists(\"{0}/{1}/Augment\".format(PS_Root_Path, Path_Type)):\n", " os.makedirs(\"{0}/{1}/Augment\".format(PS_Root_Path, Path_Type)) \n", " if not os.path.exists(\"{0}/{1}/Augment/{2}\".format(PS_Root_Path, Path_Type, AUG_METHOD)):\n", " os.makedirs(\"{0}/{1}/Augment/{2}\".format(PS_Root_Path, Path_Type, AUG_METHOD)) \n", " if not os.path.exists(\"{0}/{1}/Augment/{2}/JPEGImages\".format(PS_Root_Path, Path_Type, AUG_METHOD)):\n", " os.makedirs(\"{0}/{1}/Augment/{2}/JPEGImages\".format(PS_Root_Path, Path_Type, AUG_METHOD)) \n", " if not os.path.exists(\"{0}/{1}/Augment/{2}/DotImages\".format(PS_Root_Path,Path_Type, AUG_METHOD)):\n", " os.makedirs(\"{0}/{1}/Augment/{2}/DotImages\".format(PS_Root_Path, Path_Type, AUG_METHOD)) \n", " if not os.path.exists(\"{0}/{1}/Augment/{2}/labels\".format(PS_Root_Path, Path_Type, AUG_METHOD)):\n", " os.makedirs(\"{0}/{1}/Augment/{2}/labels\".format(PS_Root_Path, Path_Type, AUG_METHOD)) \n", " \n", " else:\n", " print(\"Wrong in AUG_METHOD!\")\n", " \n", " \n", "elif(SYSTEM == \"Kaggle\"):\n", " if(AUG_METHOD == \"None\"):\n", " if not os.path.exists(\"./labels\"):\n", " os.makedirs(\"./labels\")\n", " if not os.path.exists(\"./JPEGImages\"):\n", " os.makedirs(\"./JPEGImages\")\n", " if not os.path.exists(\"./DotImages\"):\n", " os.makedirs(\"./DotImages\") \n", "\n", " elif(AUG_METHOD in AUG_METHOD_List):\n", " if not os.path.exists(\"./Augment\"):\n", " os.makedirs(\"./Augment\") \n", " if not os.path.exists(\"./Augment/{0}\".format(AUG_METHOD)):\n", " os.makedirs(\"./Augment/{0}\".format(AUG_METHOD)) \n", " if not os.path.exists(\"./Augment/{0}/JPEGImages\".format(AUG_METHOD)):\n", " os.makedirs(\"./Augment/{0}/JPEGImages\".format(AUG_METHOD)) \n", " if not os.path.exists(\"./Augment/{0}/DotImages\".format(AUG_METHOD)):\n", " os.makedirs(\"./Augment/{0}/DotImages\".format(AUG_METHOD)) \n", " if not os.path.exists(\"./Augment/{0}/labels\".format(AUG_METHOD)):\n", " os.makedirs(\"./Augment/{0}/labels\".format(AUG_METHOD))\n", " \n", " else:\n", " print(\"Wrong in AUG_METHOD!\")\n", "\n", "else:\n", " print(\"Wrong in SYSTEM!\")" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "4efe57a3-01b6-8bc5-816c-fee8cac6fc30" }, "source": [ " # generate sub_image_template" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "947a2300-1f58-b1f4-52d7-e3df126a9e11" }, "outputs": [], "source": [ "Sub_Im_Size = (416,416)\n", "\n", "if(arg[2] == 'Black'):\n", " image_tmp = cv2.imread(Path_Train + file_names[0])\n", " image_tmp = image_tmp[:Sub_Im_Size[1],:Sub_Im_Size[0],:]\n", " image_tmp = cv2.absdiff(image_tmp,image_tmp)\n", "\n", " plt.imshow(cv2.cvtColor(image_tmp, cv2.COLOR_BGR2RGB))\n", " cv2.imwrite('sub_im_template.jpg',image_tmp)" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "141fb606-b9ae-ca5c-e3e0-300b70a65838" }, "source": [ "# augment image function" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "ffebce4f-cc14-babf-e565-af7a240f3885" }, "outputs": [], "source": [ "from scipy import ndimage\n", "\n", "def augment(image, method):\n", " if(method == \"Flip\"):\n", " image = image[::-1]\n", " elif(method[:6] == \"Rotate\"):\n", " image = ndimage.rotate(image, int(method[7:]))\n", " elif(method[:11] == \"Flip_Rotate\"):\n", " image = image[::-1]\n", " image = ndimage.rotate(image, int(method[12:]))\n", " \n", " return image" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "778c5b6e-4e54-2f09-c2b3-4bd89fb27e6b" }, "source": [ "# parse image" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "24d2abad-07f8-14fb-5613-708a5c191749" }, "outputs": [], "source": [ "def get_blobs(image_1, image_2):\n", " # absolute difference between Train and Train Dotted\n", " image_3 = cv2.absdiff(image_1,image_2)\n", " \n", " # mask out blackened regions from Train Dotted\n", " mask_1 = cv2.cvtColor(image_1, cv2.COLOR_BGR2GRAY)\n", " mask_1[mask_1 < 20] = 0\n", " mask_1[mask_1 > 0] = 255\n", " \n", " mask_2 = cv2.cvtColor(image_2, cv2.COLOR_BGR2GRAY)\n", " mask_2[mask_2 < 20] = 0\n", " mask_2[mask_2 > 0] = 255\n", " \n", " image_3 = cv2.bitwise_or(image_3, image_3, mask=mask_1)\n", " image_3 = cv2.bitwise_or(image_3, image_3, mask=mask_2) \n", " \n", " # convert to grayscale to be accepted by skimage.feature.blob_log\n", " image_3 = cv2.cvtColor(image_3, cv2.COLOR_BGR2GRAY)\n", " \n", " # detect blobs\n", " blobs = skimage.feature.blob_log(image_3, min_sigma=3, max_sigma=4, num_sigma=1, threshold=0.02)\n", " \n", " return blobs" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "71836ad9-e1be-4a7f-35c2-c939692641af" }, "outputs": [], "source": [ "# classes = [\"adult_males\", \"subadult_males\", \"pups\", \"juveniles\", \"adult_females\"]\n", "\n", "def get_species(r,g,b): \n", " if r > 200 and g < 50 and b < 50: # RED\n", " return 0 \n", " elif r > 200 and g > 200 and b < 50: # MAGENTA\n", " return 1 \n", " elif r < 100 and g < 100 and 150 < b < 200: # GREEN\n", " return 2\n", " elif r < 100 and 100 < g and b < 100: # BLUE\n", " return 3\n", " elif r < 150 and g < 50 and b < 100: # BROWN\n", " return 4\n", " else:\n", " return -1" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "ce390624-9575-00ba-ae8e-7fc04b4e3603" }, "outputs": [], "source": [ "def get_xy_range_basic(x, y, x_max, y_max, size):\n", " ### x_left, x_right, y_up, y_down\n", " x_left = min(size, x)\n", " x_right = min(size, x_max-x-1)\n", " y_up = min(size, y)\n", " y_down = min(size, y_max-y-1)\n", " return (x_left, x_right, y_up, y_down)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "8eddbc59-4f88-2589-439d-9f60149eef0a" }, "outputs": [], "source": [ "def get_dict_range_basic(shape, blobs):\n", " Dict_range = {}\n", " \n", " for blob in blobs:\n", " # get the coordinates for each blob\n", " y, x, s = blob\n", " \n", " # get basic xy_range\n", " xy_range = get_xy_range_basic(x=x, y=y, x_max=shape[1], y_max=shape[0], size=int(arg[1])/2)\n", " \n", " # save range info \n", " Dict_range[(x,y)] = xy_range\n", " \n", " return Dict_range" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "f85ff2fb-49f0-b8ff-6a41-71324f18dd54" }, "outputs": [], "source": [ "MAX_SUB_IM_HALF_LEN = 48\n", "\n", "def get_dict_range_advance(ori_image, dot_image, blobs):\n", " Dict_range = {}\n", " s_size = int(arg[1])/8\n", " \n", " for blob in blobs:\n", " # get the coordinates for each blob\n", " y, x, s = blob\n", " \n", " # get species\n", " g,b,r = dot_image[int(y)][int(x)][:]\n", " species = get_species(r,g,b)\n", " \n", " # get basic xy_range\n", " xy_range = get_xy_range_basic(x=x, y=y, x_max=ori_image.shape[1], y_max=ori_image.shape[0], size=int(arg[1])/2)\n", " x_left = xy_range[0] \n", " x_right = xy_range[1]\n", " y_up = xy_range[2]\n", " y_down = xy_range[3]\n", " \n", " # set augmenting threshold for sea_lion\n", " level = 45\n", " \n", " # augment xy_range\n", " if(species != 2):\n", " mid_im = ori_image[int(y-s_size):int(y+s_size), int(x-s_size):int(x+s_size), :]\n", " mid_abs = np.linalg.norm(np.mean(mid_im, axis=(0,1)))\n", " \n", " # augment left side\n", " while(x_left != x and x_left != MAX_SUB_IM_HALF_LEN):\n", " # get three sub_sub_image on left\n", " left_mid_im = ori_image[ int(y-s_size):int(y+s_size), int(x-x_left):int(x-x_left+2*s_size), :]\n", " left_up_im = ori_image[int(y-3*s_size):int(y-s_size), int(x-x_left):int(x-x_left+2*s_size), :]\n", " left_down_im = ori_image[int(y+s_size):int(y+3*s_size), int(x-x_left):int(x-x_left+2*s_size), :]\n", " \n", " # calculate distance\n", " left_mid_abs = np.linalg.norm(np.mean( left_mid_im, axis=(0,1)))\n", " left_up_abs = np.linalg.norm(np.mean( left_up_im, axis=(0,1)))\n", " left_down_abs = np.linalg.norm(np.mean( left_down_im, axis=(0,1)))\n", " \n", " # augment if proper\n", " if(abs(mid_abs-left_mid_abs) < level or abs(mid_abs-left_up_abs) < level or abs(mid_abs-left_down_abs) < level): \n", " x_left = min(x_left+s_size, MAX_SUB_IM_HALF_LEN, x)\n", " #print(\"Augment x_left {0},{1}\".format(x,y))\n", " else:\n", " break\n", "\n", " # augment right side\n", " while(x_right != ori_image.shape[1]-x and x_right != MAX_SUB_IM_HALF_LEN):\n", " # get three sub_sub_image on right\n", " right_mid_im = ori_image[ int(y-s_size):int(y+s_size), int(x+x_right-2*s_size):int(x+x_right), :]\n", " right_up_im = ori_image[int(y-3*s_size):int(y-s_size), int(x+x_right-2*s_size):int(x+x_right), :]\n", " right_down_im = ori_image[int(y+s_size):int(y+3*s_size), int(x+x_right-2*s_size):int(x+x_right), :]\n", " \n", " # calculate distance\n", " right_mid_abs = np.linalg.norm(np.mean( right_mid_im, axis=(0,1)))\n", " right_up_abs = np.linalg.norm(np.mean( right_up_im, axis=(0,1)))\n", " right_down_abs = np.linalg.norm(np.mean( right_down_im, axis=(0,1)))\n", " \n", " # augment if proper\n", " if(abs(mid_abs-right_mid_abs) < level or abs(mid_abs-right_up_abs) < level or abs(mid_abs-right_down_abs) < level):\n", " x_right = min(x_right+s_size, MAX_SUB_IM_HALF_LEN, ori_image.shape[1]-x)\n", " #print(\"Augment x_right {0},{1}\".format(x,y))\n", " else:\n", " break\n", " \n", " # augment up side\n", " while(y_up != y and y_up != MAX_SUB_IM_HALF_LEN):\n", " # get three sub_sub_image on up\n", " up_mid_im = ori_image[int(y-y_up):int(y-y_up+2*s_size), int(x-s_size):int(x+s_size), :]\n", " up_left_im = ori_image[int(y-y_up):int(y-y_up+2*s_size), int(x-3*s_size):int(x-s_size), :]\n", " up_right_im = ori_image[int(y-y_up):int(y-y_up+2*s_size), int(x+s_size):int(x+3*s_size), :]\n", " \n", " # calculate distance\n", " up_mid_abs = np.linalg.norm(np.mean( up_mid_im, axis=(0,1)))\n", " up_left_abs = np.linalg.norm(np.mean( up_left_im, axis=(0,1)))\n", " up_right_abs = np.linalg.norm(np.mean( up_right_im, axis=(0,1)))\n", " \n", " # augment if proper\n", " if(abs(mid_abs-up_mid_abs) < level or abs(mid_abs-up_left_abs) < level or abs(mid_abs-up_right_abs) < level):\n", " y_up = min(y_up+s_size, MAX_SUB_IM_HALF_LEN, y)\n", " #print(\"Augment y_up {0},{1}\".format(x,y))\n", " else:\n", " break\n", " \n", " # augment down side\n", " while(y_down != ori_image.shape[0]-y and y_down != MAX_SUB_IM_HALF_LEN):\n", " # get three sub_sub_image on down\n", " down_mid_im = ori_image[int(y+y_down-2*s_size):int(y+y_down), int(x-s_size):int(x+s_size), :]\n", " down_left_im = ori_image[int(y+y_down-2*s_size):int(y+y_down), int(x-3*s_size):int(x-s_size), :]\n", " down_right_im = ori_image[int(y+y_down-2*s_size):int(y+y_down), int(x+s_size):int(x+3*s_size), :]\n", " \n", " # calculate distance\n", " down_mid_abs = np.linalg.norm(np.mean( down_mid_im, axis=(0,1)))\n", " down_left_abs = np.linalg.norm(np.mean( down_left_im, axis=(0,1)))\n", " down_right_abs = np.linalg.norm(np.mean( down_right_im, axis=(0,1)))\n", " \n", " # augment if proper\n", " if(abs(mid_abs-down_mid_abs) < level or abs(mid_abs-down_left_abs) < level or abs(mid_abs-down_right_abs) < level):\n", " y_down = min(y_down+s_size, MAX_SUB_IM_HALF_LEN, ori_image.shape[0]-y)\n", " #print(\"Augment y_down {0},{1}\".format(x,y))\n", " else:\n", " break\n", " \n", " # save range info \n", " Dict_range[(x,y)] = (x_left, x_right, y_up, y_down)\n", " \n", " return Dict_range" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "9f102608-ea02-bef8-dd06-ca93bede229c" }, "outputs": [], "source": [ "def parse_image_black(filename):\n", " ## open sub_image_names file\n", " sub_image_names = open(Path_Sealion + \"{0}Train.txt\".format(AUG_Add_Path), 'a')\n", " \n", " ### get original image\n", " ori_image = cv2.imread(Path_Train + filename)\n", " dot_image = cv2.imread(Path_Dotted + filename)\n", " cnt = 0\n", " \n", " ### flip origin image\n", " ori_image = augment(ori_image, AUG_METHOD)\n", " dot_image = augment(dot_image, AUG_METHOD)\n", " \n", " ### get coordinate of all sea lions\n", " Dict_range = {}\n", " blobs = get_blobs(ori_image, dot_image)\n", " \n", " ### get xy_range info for all sea_lion\n", " if(arg[0] == 'Basic'):\n", " Dict_range = get_dict_range_basic(ori_image.shape, blobs)\n", " elif(arg[0] == 'Advance'):\n", " Dict_range = get_dict_range_advance(ori_image, dot_image, blobs)\n", " \n", " ### output sub_image and annotation file for each blob\n", " Delete_Key_List = []\n", " for key in list(Dict_range.keys()): \n", " if(key in Dict_range):\n", " # add cnt for new sub_image name\n", " cnt += 1\n", " \n", " # get x, y, xy_range in original image\n", " main_x = int(key[0])\n", " main_y = int(key[1])\n", " xy_range = Dict_range[key]\n", " \n", " ### get basic sub_image\n", " sub_image = cv2.imread('sub_im_template.jpg') \n", " sub_x_center = int(sub_image.shape[1]/2)\n", " sub_y_center = int(sub_image.shape[0]/2)\n", " sub_image[int(sub_y_center-xy_range[2]):int(sub_y_center+xy_range[3]), int(sub_x_center-xy_range[0]):int(sub_x_center+xy_range[1]), :] = ori_image[int(main_y-xy_range[2]):int(main_y+xy_range[3]), int(main_x-xy_range[0]):int(main_x+xy_range[1]), :]\n", " del Dict_range[key]\n", " \n", " ### get species\n", " g,b,r = dot_image[int(main_y)][int(main_x)][:]\n", " species = get_species(r,g,b)\n", " if(species == -1):\n", " continue\n", " \n", " # get pos info for annotation file\n", " x_pos = float(sub_x_center)/float(Sub_Im_Size[0])\n", " y_pos = float(sub_y_center)/float(Sub_Im_Size[0])\n", " x_len = float(xy_range[0]+xy_range[1])/float(Sub_Im_Size[0])\n", " y_len = float(xy_range[2]+xy_range[3])/float(Sub_Im_Size[0])\n", " element = [x_pos, y_pos, x_len, y_len]\n", " \n", " # save species info in annotation file\n", " ant_file = open(Path_Sealion + '{0}labels/{1}_{2}.txt'.format(AUG_Add_Path, filename[:-4], cnt), 'w')\n", " ant_file.write(str(species) + \" \" + \" \".join([str(x) for x in element]) + '\\n')\n", " \n", " \n", " ### include other sea lion\n", " # max min coordinate for including image based on origin image\n", " x_min = max(main_x - sub_image.shape[1]/2 + 1, 0)\n", " x_max = min(main_x + sub_image.shape[1]/2 - 1, ori_image.shape[1])\n", " y_min = max(main_y - sub_image.shape[0]/2 + 1, 0)\n", " y_max = min(main_y + sub_image.shape[0]/2 - 1, ori_image.shape[0])\n", " \n", " for ex_key in list(Dict_range.keys()):\n", " if(ex_key[0] > x_min and ex_key[0] < x_max and ex_key[1] > y_min and ex_key[1] < y_max):\n", " ### coordinate of ex_sea_lion in origin image\n", " ex_range = Dict_range[ex_key]\n", " ex_left = int(ex_key[0] - ex_range[0])\n", " ex_right = int(ex_key[0] + ex_range[1])\n", " ex_up = int(ex_key[1] - ex_range[2])\n", " ex_down = int(ex_key[1] + ex_range[3])\n", " if(ex_left > x_min and ex_right < x_max and ex_up > y_min and ex_down < y_max):\n", " ### sub_image's coordinate where ex_sea_lion put \n", " in_up = int(sub_y_center - main_y + ex_key[1] - ex_range[2])\n", " in_down = int(sub_y_center - main_y + ex_key[1] + ex_range[3])\n", " in_left = int(sub_x_center - main_x + ex_key[0] - ex_range[0])\n", " in_right = int(sub_x_center - main_x + ex_key[0] + ex_range[1])\n", " sub_image[ in_up:in_down, in_left:in_right, :] = ori_image[ex_up:ex_down, ex_left:ex_right, :]\n", " del Dict_range[ex_key]\n", " \n", " ### get species for include sea_lion\n", " g,b,r = dot_image[int(ex_key[1])][int(ex_key[0])][:]\n", " species = get_species(r,g,b)\n", " \n", " # get pos info for annotation file\n", " x_pos = float(sub_x_center - main_x + ex_key[0])/float(Sub_Im_Size[0])\n", " y_pos = float(sub_y_center - main_y + ex_key[1])/float(Sub_Im_Size[0])\n", " x_len = float(ex_range[0]+ex_range[1])/float(Sub_Im_Size[0])\n", " y_len = float(ex_range[2]+ex_range[3])/float(Sub_Im_Size[0])\n", " element = [x_pos, y_pos, x_len, y_len]\n", " \n", " # save species info in annotation file\n", " ant_file.write(str(species) + \" \" + \" \".join([str(x) for x in element]) + '\\n') \n", " \n", " cv2.imwrite(Path_Sealion + '{0}JPEGImages/{1}_{2}.jpg'.format(AUG_Add_Path, filename[:-4], cnt),sub_image)\n", " sub_image_names.write(Path_Sealion + '{0}JPEGImages/{1}_{2}.jpg'.format(AUG_Add_Path, filename[:-4], cnt))\n", " sub_image_names.write(\"\\n\")\n", " ant_file.close()\n", " sub_image_names.close()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "5f013ad6-3c01-99ce-8aa6-90e44b6f9f49" }, "outputs": [], "source": [ "def parse_image_whole(filename):\n", " ## open sub_image_names file\n", " sub_image_names = open(Path_Sealion + \"{0}Train.txt\".format(AUG_Add_Path), 'a')\n", " \n", " ### get original image\n", " ori_image = cv2.imread(Path_Train + filename)\n", " dot_image = cv2.imread(Path_Dotted + filename)\n", " cnt = 0\n", " \n", " ### flip origin image\n", " ori_image = augment(ori_image, AUG_METHOD)\n", " dot_image = augment(dot_image, AUG_METHOD)\n", " \n", " ### get coordinate of all sea lions\n", " blobs = get_blobs(ori_image, dot_image)\n", " \n", " ### get xy_range info for all sea_lion\n", " if(arg[0] == 'Basic'):\n", " Dict_range = get_dict_range_basic(ori_image.shape, blobs)\n", " elif(arg[0] == 'Advance'):\n", " Dict_range = get_dict_range_advance(ori_image, dot_image, blobs) \n", " \n", " ### output sub_image and annotation file for each blob\n", " Used_Key_Set = set()\n", " for key in Dict_range.keys(): \n", " if(key not in Used_Key_Set):\n", " # add cnt for new sub_image name\n", " cnt += 1\n", " \n", " # get x, y, xy_range in original image\n", " main_x = int(key[0])\n", " main_y = int(key[1])\n", " xy_range = Dict_range[key]\n", " \n", " # adjust main_x main_y if sea_lion close to boundary\n", " if(main_x - Sub_Im_Size[0]/2 < 0):\n", " main_x = Sub_Im_Size[0]/2\n", " if(main_x + Sub_Im_Size[0]/2 > ori_image.shape[1]):\n", " main_x = ori_image.shape[1] - Sub_Im_Size[0]/2\n", " if(main_y - Sub_Im_Size[1]/2 < 0):\n", " main_y = Sub_Im_Size[1]/2\n", " if(main_y + Sub_Im_Size[1]/2 > ori_image.shape[0]):\n", " main_y = ori_image.shape[0] - Sub_Im_Size[1]/2\n", " \n", " # get_sub_image\n", " sub_image = ori_image[int(main_y - Sub_Im_Size[1]/2) : int(main_y + Sub_Im_Size[1]/2), int(main_x - Sub_Im_Size[0]/2) : int(main_x + Sub_Im_Size[0]/2), :]\n", " sub_image_dot = dot_image[int(main_y - Sub_Im_Size[1]/2) : int(main_y + Sub_Im_Size[1]/2), int(main_x - Sub_Im_Size[0]/2) : int(main_x + Sub_Im_Size[0]/2), :]\n", " \n", " # record key as used_key\n", " Used_Key_Set.add(key)\n", " \n", " ### get species\n", " g,b,r = dot_image[int(key[1])][int(key[0])][:]\n", " species = get_species(r,g,b)\n", " if(species == -1):\n", " continue\n", "\n", " # get pos info for annotation file\n", " x_pos = float(key[0]-(main_x-Sub_Im_Size[0]/2))/float(Sub_Im_Size[0])\n", " y_pos = float(key[1]-(main_y-Sub_Im_Size[1]/2))/float(Sub_Im_Size[1])\n", " x_len = float(xy_range[0]+xy_range[1])/float(Sub_Im_Size[0])\n", " y_len = float(xy_range[2]+xy_range[3])/float(Sub_Im_Size[1])\n", " element = [x_pos, y_pos, x_len, y_len]\n", " \n", " # save species info in annotation file\n", " ant_file = open(Path_Sealion + '{0}labels/{1}_{2}.txt'.format(AUG_Add_Path, filename[:-4], cnt), 'w')\n", " ant_file.write(str(species) + \" \" + \" \".join([str(x) for x in element]) + '\\n')\n", " \n", " \n", " ### include other sea lion\n", " # max min coordinate for including image based on origin image\n", " x_min = max(main_x - sub_image.shape[1]/2 + 1, 0)\n", " x_max = min(main_x + sub_image.shape[1]/2 - 1, ori_image.shape[1])\n", " y_min = max(main_y - sub_image.shape[0]/2 + 1, 0)\n", " y_max = min(main_y + sub_image.shape[0]/2 - 1, ori_image.shape[0])\n", " \n", " for ex_key in Dict_range.keys():\n", " if(ex_key != key and ex_key[0] > x_min and ex_key[0] < x_max and ex_key[1] > y_min and ex_key[1] < y_max):\n", " ### coordinate of ex_sea_lion in origin image\n", " ex_range = Dict_range[ex_key]\n", " ex_left = int(ex_key[0] - ex_range[0])\n", " ex_right = int(ex_key[0] + ex_range[1])\n", " ex_up = int(ex_key[1] - ex_range[2])\n", " ex_down = int(ex_key[1] + ex_range[3])\n", " \n", " ### sub_image's coordinate where ex_sea_lion put \n", " Used_Key_Set.add(ex_key)\n", "\n", " ### get species for include sea_lion\n", " g,b,r = dot_image[int(ex_key[1])][int(ex_key[0])][:]\n", " species = get_species(r,g,b)\n", " \n", " # get pos info for annotation file\n", " x_pos = float(ex_key[0]-(main_x-Sub_Im_Size[0]/2))/float(Sub_Im_Size[0])\n", " y_pos = float(ex_key[1]-(main_y-Sub_Im_Size[1]/2))/float(Sub_Im_Size[1])\n", " \n", " # adjust real size of include sea_lion due to be close to boarder\n", " ex_left_size = min(ex_range[0], ex_key[0]-(main_x-Sub_Im_Size[0]/2))\n", " ex_right_size = min(ex_range[1], (main_x+Sub_Im_Size[0]/2)-ex_key[0])\n", " ex_up_size = min(ex_range[2], ex_key[1]-(main_y-Sub_Im_Size[1]/2))\n", " ex_down_size = min(ex_range[3], (main_y+Sub_Im_Size[1]/2)-ex_key[1])\n", " \n", " x_len = float(ex_left_size+ex_right_size)/float(Sub_Im_Size[0])\n", " y_len = float(ex_up_size+ex_down_size)/float(Sub_Im_Size[1])\n", " element = [x_pos, y_pos, x_len, y_len]\n", " \n", " # save species info in annotation file\n", " ant_file.write(str(species) + \" \" + \" \".join([str(x) for x in element]) + '\\n') \n", " \n", " cv2.imwrite(Path_Sealion + '{0}JPEGImages/{1}_{2}.jpg'.format(AUG_Add_Path, filename[:-4], cnt), sub_image)\n", " cv2.imwrite(Path_Sealion + '{0}DotImages/{1}_{2}.jpg'.format(AUG_Add_Path, filename[:-4], cnt), sub_image_dot)\n", " #cv2.imwrite('{0}_{1}.png'.format(filename[:-4], cnt),sub_image)\n", " sub_image_names.write(Path_Sealion + '{0}JPEGImages/{1}_{2}.jpg'.format(AUG_Add_Path, filename[:-4], cnt))\n", " sub_image_names.write(\"\\n\")\n", " ant_file.close()\n", " sub_image_names.close()" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "52180aee-d484-fef9-6b2c-3cc44866097a" }, "source": [ "# Run Main Code" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "1c0c40e1-372e-ce11-a001-999ac60d4257" }, "source": [ "## remove Train.txt if exist" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "a73b937c-c9c2-5a61-aa50-c745765471de" }, "outputs": [], "source": [ "if os.path.exists(Path_Sealion + \"{0}Train.txt\".format(AUG_Add_Path)):\n", " os.remove(Path_Sealion + \"{0}Train.txt\".format(AUG_Add_Path))\n", "\n", "for filename in file_names:\n", " if filename[-3:] == 'jpg':\n", " parse_image_whole(filename)\n", " \n", " \"\"\"\n", " print(\"Parsing {0}\".format(filename))\n", " if(arg[2] == 'Black'):\n", " parse_image_black(filename)\n", " elif(arg[2] == 'Whole'):\n", " parse_image_whole(filename)\n", " else:\n", " print(\"Wrong in argument\")\n", " \"\"\"" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "a25b85ac-c9e3-3e8e-7929-941d79ba0a67" }, "source": [ "# remove sub_image template" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "1c814340-31dc-81ca-8fb0-00f3e63f5627" }, "outputs": [], "source": [ "if(arg[2] == 'Black'):\n", " os.remove('sub_im_template.jpg')" ] } ], "metadata": { "_change_revision": 0, "_is_fork": false, "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": "3.6.0" } }, "nbformat": 4, "nbformat_minor": 0 }