{ "cells": [ { "cell_type": "markdown", "metadata": { "_cell_guid": "1daa2af8-7ba3-a2f0-350d-024c88a8a5e4" }, "source": "" }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "c4863690-638e-e1cf-ded4-579c28947b4f" }, "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": "e48db052-94e7-4a31-474a-70b1c82d6355" }, "source": "" }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "c841483c-2fd0-2835-989b-51833680361f" }, "outputs": [], "source": [ "import sys\n", "arg = sys.argv[1:]\n", "\n", "if('-f' in arg):\n", " arg = ['Advance', '32', 'Black', '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": "9913b8b7-2874-bb5a-77c6-4debdcad86c1" }, "source": "" }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "74bc6c11-8fb1-da23-314a-6374f6d1824b" }, "outputs": [], "source": [ "Path_Type = \"{0}/{1}_{2}_{3}\".format(arg[3], arg[0], arg[1], arg[2])\n", "Path_Type" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "2a862cf6-fb49-f7cf-7b70-f9e25b0972b6" }, "outputs": [], "source": [ "Path_Sealion = \"./\" # \"/home/paperspace/Project/Sealion/{0}/\".format(Path_Type) # \n", "Path_Train = \"../input/Train/\" # \"/home/paperspace/Project/Sealion/TrainSmall2/Train/\" # \n", "Path_Dotted = \"../input/TrainDotted/\" # \"/home/paperspace/Project/Sealion/TrainSmall2/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": "code", "execution_count": null, "metadata": { "_cell_guid": "0646d6bc-a4fa-1590-e925-32fed3f50948" }, "outputs": [], "source": [ "\"\"\"\n", "if not os.path.exists(\"/home/paperspace/Project/Sealion/{0}\".format(Path_Type)):\n", " os.makedirs(\"/home/paperspace/Project/Sealion/{0}\".format(Path_Type))\n", "if not os.path.exists(\"/home/paperspace/Project/Sealion/{0}/labels\".format(Path_Type)):\n", " os.makedirs(\"/home/paperspace/Project/Sealion/{0}/labels\".format(Path_Type))\n", "if not os.path.exists(\"/home/paperspace/Project/Sealion/{0}/JPEGImages\".format(Path_Type)):\n", " os.makedirs(\"/home/paperspace/Project/Sealion/{0}/JPEGImages\".format(Path_Type))\n", "\"\"\"" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "81f3cb6c-d17c-49c8-3bf5-6141921ec47e" }, "outputs": [], "source": [ "\n", "if not os.path.exists(\"./labels\"):\n", " os.makedirs(\"./labels\")\n", "if not os.path.exists(\"./JPEGImages\"):\n", " os.makedirs(\"./JPEGImages\")\n" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "ca5c0b88-9824-b3f4-5b35-b41cb3cd2265" }, "source": "" }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "6086b42a-fa53-ea92-819b-c7f627c5ebef" }, "outputs": [], "source": [ "Sub_Im_Size = (416,416)\n", "\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": "5d924280-0451-56c2-e4f6-e5cc60bbd837" }, "source": "" }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "ab28bea7-90b2-62bd-c2be-ea9d448e1c31" }, "outputs": [], "source": [ "def get_blobs(filename):\n", " # read the Train and Train Dotted images\n", " image_1 = cv2.imread(Path_Dotted + filename)\n", " image_2 = cv2.imread(Path_Train + filename)\n", " \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": "e09fb49a-100c-3616-735d-e5400370db74" }, "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" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "a6e0d005-0852-d5dd-5e63-4443838f4c88" }, "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": "d641cbb1-f92f-2716-53dc-db0c04c76996" }, "outputs": [], "source": [ "def get_dict_range_basic(filename, blobs):\n", " Dict_range = {}\n", " ori_image = cv2.imread(Path_Train + filename)\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=ori_image.shape[1], y_max=ori_image.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": "962d6150-d201-6714-e8cc-bb6011949265" }, "outputs": [], "source": [ "def get_dict_range_advance(filename, blobs):\n", " level = 30\n", " Dict_range = {}\n", " ori_image = cv2.imread(Path_Train + filename)\n", " dot_image = cv2.imread(Path_Dotted + filename)\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", " # 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(True):\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, x)\n", " if(x_left == x):\n", " break\n", " print(\"Augment x_left {0},{1}\".format(x,y))\n", " else:\n", " break\n", "\n", " # augment right side\n", " while(True):\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, ori_image.shape[1]-x)\n", " if(x_right == ori_image.shape[1]-x):\n", " break\n", " print(\"Augment x_right {0},{1}\".format(x,y))\n", " else:\n", " break\n", " \n", " # augment up side\n", " while(True):\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, y)\n", " if(y_up == y):\n", " break\n", " print(\"Augment y_up {0},{1}\".format(x,y))\n", " else:\n", " break\n", " \n", " # augment down side\n", " \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": "2ea464ff-d67f-a1c0-cdff-c383b3e5d851" }, "outputs": [], "source": [ "def parse_image_black(filename):\n", " ## open sub_image_names file\n", " sub_image_names = open(Path_Sealion + \"Train.txt\", '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", " ### get coordinate of all sea lions\n", " Dict_range = {}\n", " blobs = get_blobs(filename)\n", " \n", " ### get xy_range info for all sea_lion\n", " if(arg[0] == 'Basic'):\n", " Dict_range = get_dict_range_basic(filename, blobs)\n", " elif(arg[0] == 'Advance'):\n", " Dict_range = get_dict_range_advance(filename, 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", " \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 + 'labels/{0}_{1}.txt'.format(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 + 'JPEGImages/{0}_{1}.jpg'.format(filename[:-4], cnt),sub_image)\n", " #cv2.imwrite('{0}_{1}.png'.format(filename[:-4], cnt),sub_image)\n", " sub_image_names.write(Path_Sealion + 'JPEGImages/{0}_{1}.jpg'.format(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": "0d5c492c-197a-9860-0214-13b491b6b288" }, "outputs": [], "source": [ "def parse_image_whole(filename):\n", " ## open sub_image_names file\n", " sub_image_names = open(Path_Sealion + \"Train.txt\", '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", " ### get coordinate of all sea lions\n", " blobs = get_blobs(filename)\n", " \n", " ### get xy_range info for all sea_lion\n", " if(arg[0] == 'Basic'):\n", " Dict_range = get_dict_range_basic(filename, blobs)\n", " elif(arg[0] == 'Advance'):\n", " Dict_range = get_dict_range_advance(filename, 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", " \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", "\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 + 'labels/{0}_{1}.txt'.format(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 + 'JPEGImages/{0}_{1}.jpg'.format(filename[:-4], cnt), sub_image)\n", " #cv2.imwrite('{0}_{1}.png'.format(filename[:-4], cnt),sub_image)\n", " sub_image_names.write(Path_Sealion + 'JPEGImages/{0}_{1}.jpg'.format(filename[:-4], cnt))\n", " sub_image_names.write(\"\\n\")\n", " ant_file.close()\n", " sub_image_names.close()" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "293de9b3-8a17-2109-ec9a-ee582391a6ef" }, "source": "" }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "514d222e-433d-4de7-fd37-deb4f1c05915" }, "outputs": [], "source": [ "### remove Train.txt if exist\n", "if os.path.exists(Path_Sealion + \"Train.txt\"):\n", " os.remove(Path_Sealion + \"Train.txt\")\n", "\n", "for filename in file_names:\n", " if filename[-3:] == 'jpg':\n", " parse_image_black(filename)\n", " \n", " \"\"\"\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": "e798d145-8e33-e375-4116-9d61c0791155" }, "source": "" }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "2c403884-9283-e70f-ce50-0217ce95626b", "collapsed": true }, "outputs": [], "source": "" }, { "cell_type": "markdown", "metadata": { "_cell_guid": "5d23d47d-36d4-ef24-65ce-a22626bf2640" }, "source": "" }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "755fe3ea-dfde-e095-5336-9b027ccb41fe", "collapsed": true }, "outputs": [], "source": "" } ], "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 }