{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Global Wheat Detection\n## Problem Overview:","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"Open up your pantry and you’re likely to find several wheat products. Indeed, your morning toast or cereal may rely upon this common grain. Its popularity as a food and crop makes wheat widely studied. To get large and accurate data about wheat fields worldwide, plant scientists use image detection of \"wheat heads\"—spikes atop the plant containing grain. These images are used to estimate the density and size of wheat heads in different varieties. Farmers can use the data to assess health and maturity when making management decisions in their fields.\n\nHowever, accurate wheat head detection in outdoor field images can be visually challenging. There is often overlap of dense wheat plants, and the wind can blur the photographs. Both make it difficult to identify single heads. Additionally, appearances vary due to maturity, color, genotype, and head orientation. Finally, because wheat is grown worldwide, different varieties, planting densities, patterns, and field conditions must be considered. Models developed for wheat phenotyping need to generalize between different growing environments. Current detection methods involve one- and two-stage detectors (Yolo-V3 and Faster-RCNN), but even when trained with a large dataset, a bias to the training region remains.\n\nThe Global Wheat Head Dataset is led by nine research institutes from seven countries: the University of Tokyo, Institut national de recherche pour l’agriculture, l’alimentation et l’environnement, Arvalis, ETHZ, University of Saskatchewan, University of Queensland, Nanjing Agricultural University, and Rothamsted Research. These institutions are joined by many in their pursuit of accurate wheat head detection, including the Global Institute for Food Security, DigitAg, Kubota, and Hiphen.\n\nIn this competition, you’ll detect wheat heads from outdoor images of wheat plants, including wheat datasets from around the globe. Using worldwide data, you will focus on a generalized solution to estimate the number and size of wheat heads. To better gauge the performance for unseen genotypes, environments, and observational conditions, the training dataset covers multiple regions. You will use more than 3,000 images from Europe (France, UK, Switzerland) and North America (Canada). The test data includes about 1,000 images from Australia, Japan, and China.\n\nWheat is a staple across the globe, which is why this competition must account for different growing conditions. Models developed for wheat phenotyping need to be able to generalize between environments. If successful, researchers can accurately estimate the density and size of wheat heads in different varieties. With improved detection farmers can better assess their crops, ultimately bringing cereal, toast, and other favorite dishes to your table. ","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"# Data\nMore details on the data acquisition and processes are available at https://www.kaggle.com/c/global-wheat-detection/data\n\nData Format: The data is images of wheat fields, with bounding boxes for each identified wheat head. Not all images include wheat heads / bounding boxes. The images were recorded in many locations around the world.\n\nThe CSV data is simple - the image ID matches up with the filename of a given image, and the width and height of the image are included, along with a bounding box. There is a row in train.csv for each bounding box. Not all images have bounding boxes.\n\n**Goal:** The goal is to predict bounding boxes around each wheat head in images that have them. If there are no wheat heads, you must predict no bounding boxes.\n\n**File Structure:**\n\n* train.csv - the training data\n* sample_submission.csv - a sample submission file in the correct format\n* train.zip - training images\n* test.zip - test images\n\n**Fields in csv:**\n\n* image_id - the unique image ID\n* width, height - the width and height of the images\n* bbox - a bounding box, formatted as a Python-style list of [xmin, ymin, width, height].","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Posing this as a Deep Learning porblem.\n\n* We have images and their corresponding bounding boxes in the data.\n* Given these 2 as input to the model we need to precit the bounding boxes around each wheat head in a given image from the test data.\n* This prediction involves object detection in the images and plotting bounding boxes around it.\n* we can use techniques like Faster RCNN or Yolo v3 to do these tasks.\n\n\n## Metics:\n\n* This competition is evaluated on the mean average precision at different intersection over union (IoU) thresholds. The IoU of a set of predicted bounding boxes and ground truth bounding boxes is calculated as:\n                           \n![image.png](attachment:image.png)","attachments":{"image.png":{"image/png":"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"}},"execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nimport pandas as pd\nimport numpy as np\n\nfrom glob import glob\nfrom PIL import Image\nimport cv2\n\n# import data visualization\nimport matplotlib.pyplot as plt\nimport matplotlib.patches as patches\nimport seaborn as sns\n\nfrom bokeh.plotting import figure\nfrom bokeh.io import output_notebook, show, output_file\nfrom bokeh.models import ColumnDataSource, HoverTool, Panel\nfrom bokeh.models.widgets import Tabs\n\n# import data augmentation\nimport albumentations as albu\nfrom ast import literal_eval\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Set up Paths","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAIN_DIR = '../input/global-wheat-detection/train/'\nTEST_DIR = '../input/global-wheat-detection/test/'\nTRAIN_CSV_PATH = '../input/global-wheat-detection/train.csv'\n\n# Glob the directories and get the lists of train and test images\ntrain_path = glob(TRAIN_DIR + '*')\ntest_path = glob(TEST_DIR + '*')\n\n\nprint('Number of train images are :', len(os.listdir(TRAIN_DIR)))\nprint('Number of test  images are :', len(os.listdir(TEST_DIR)))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* We only have 10 test images and those are very low. \n* we have 3422 train images which are low as well for training a deep neural network model so data augmentation and transfer learning techniques will sure come in handy a lot.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Constructing Dataframe","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv(TRAIN_CSV_PATH)\nprint(train_df.head(5))\nprint('\\n')\nprint('Number of rows are ',train_df.shape[0])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Each row cosists of an image id, shape of image,Bbox and source details\n* Bbox details are given in a list of elements, so we need to seperate them in diffenret columns for better use.\n* Have to do sanity check on image shapes and then have to see how many images given per source and observe how the images changes according to the source.\n* There are total of 147793 rows, which implies that each images contains multiple bounding boxes as we olny have 3422 images in total.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Basic Check ","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def grader_1(train_df):\n    if (train_df['width'].unique() == train_df['height'].unique() == [1024]):\n        print('All train images given are of shape 1024x1024')\n    else:\n        print('Not all train images are of same shape')\ngrader_1(train_df)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Sorting dataframe by images and splitting Bbox","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"all_train_images = pd.DataFrame([i.split('/')[-1][:-4] for i in train_path])\nall_train_images.columns=['image_id']\n\n#Merging on image_id column to get sorted list of images_id according to the images that we have in the path directory.\nall_train_images = all_train_images.merge(train_df, on='image_id', how='left')\n\n# replace nan values with zeros\nall_train_images['bbox'] = all_train_images.bbox.fillna('[0,0,0,0]')\n\n# split bbox column\nbbox_items = all_train_images.bbox.str.split(',', expand=True)\nall_train_images['bbox_xmin'] = bbox_items[0].str.strip('[ ').astype(float)\nall_train_images['bbox_ymin'] = bbox_items[1].str.strip(' ').astype(float)\nall_train_images['bbox_width'] = bbox_items[2].str.strip(' ').astype(float)\nall_train_images['bbox_height'] = bbox_items[3].str.strip(' ]').astype(float)\n\nprint(all_train_images.head)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"all_train_images.columns","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* We made a dataframe wiht the imageid that we have in the train directory.\n* Then we made this dataframe merge on the dataframe we loaded and then merged on image id so that we get an image and followed by its bounding boxes in a ordered fashion instead of random.\n* I filled bbox column with [0,0,0,0] where there is no bbox.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Check for no Bbox ","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"print('{} images without wheat heads.'.format(len(all_train_images) - len(train_df)))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"There are 49 images where there are no bouding boxes present in the given data of images.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Adding Bbox area column ","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_bbox_area(bbox):\n    bbox = literal_eval(bbox)\n    return bbox[2] * bbox[3]\n\nall_train_images['bbox_area'] = all_train_images['bbox'].apply(get_bbox_area)\nall_train_images = all_train_images.drop(['bbox'],axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.hist(all_train_images['bbox_area'].value_counts(), bins=30)\nplt.title('Histogram for Bbox area feature')\nplt.xlabel('Bounding boxes')\nplt.ylabel('Area')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"As organizers say, there are many bounding boxes for each image, and not all images include wheat heads / bounding boxes.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"all_train_images.bbox_area.max()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Maximum are of a bounding box is 529788.\n* The distribution of individual areas of bounding boxes has a very long tail. It would be interesting to look at the images with those large bounding boxes.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Calculating Average bbox area based on source","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"Avg_df = all_train_images.groupby('source',as_index=False)['bbox_area'].mean()\nprint(Avg_df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.bar(Avg_df['source'],Avg_df['bbox_area'],align='center')\nplt.title('Bar plot for avg Bbox area feature')\nplt.xlabel('Source')\nplt.ylabel('Avg Area')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Source named inrae_1 images are having most avergae bounding bix area. so we may intrepert that the images from this source might have more wheat heads and eventually more bboxes.\n* There is no clear speratability in average bounding boxes. so most of them have almost same average bounding box ares.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## EDA on source of the images","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"#Reference : https://matplotlib.org/3.1.1/gallery/pie_and_polar_charts/pie_and_donut_labels.html#sphx-glr-gallery-pie-and-polar-charts-pie-and-donut-labels-py\n\ncounts = dict(all_train_images.source.value_counts())\nfig,ax = plt.subplots(figsize=(8,8))\n\nwedges, texts, autotexts = ax.pie(list(counts.values()), autopct='%1.1f%%',shadow=True, startangle=90);\nax.legend(wedges, list(counts.keys()),\n          title=\"Sources\",\n          loc=\"center\",\n          bbox_to_anchor=(1, 0, 0.5, 1))\n\nplt.setp(autotexts, size=15);\n\nax.set_title(\"Data Distribution based on Sources\");\nplt.show();\nsns.countplot(x='source', data=all_train_images);\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* I noticed that images came from differnet sources and each source contributed differnet amout of images for the training.\n* Most of the images are produced by arvalis_1 source followed by ethz_1.\n* We should not call this as imbalanced right as above bar graph indicated sources of the images but not the class labels.\n* Total 7 sources out of which 3 are minority and 4 are majority","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Analysing bounding boxes per image","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"uniqueimages = all_train_images['image_id'].unique()\nprint('Number of unique images are ', len(uniqueimages))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, (ax1, ax2) = plt.subplots(1,2)\n\n\nfig.set_size_inches(16,5)\nax1.hist(all_train_images['image_id'].value_counts(), bins=30)\nax1.set_title('Number of spikes per image')\nax1.set_xlabel('Bounding boxes')\nax1.set_ylabel('Images')\n\n\n#values = unique_categories[unique_categories.unique_values <= 25].unique_values\nax2.set_xlim(112,118)\nax2.set_ylim(0,10)\nax2.hist(all_train_images['image_id'].value_counts(), bins=30)\nax2.set_title('Zooming left part of histogram')\nax2.set_xlabel('Bounding boxes')\nax2.set_ylabel('Images')\nax2.grid(True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Max number of bounding boxes is 116, whereas min (annotated) number is 1.\n* Most of the images have 20-50 wheat spikes on them.\n* There are very few images with more than 80 bouinding boxes per image.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Plotting some Images with bouding boxes","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_all_bboxes(df,image_id):\n    image_boxes = df[df['image_id'] == image_id]\n    bboxes = []\n    for _,row in image_boxes.iterrows():\n        bboxes.append((row.bbox_xmin, row.bbox_ymin, row.bbox_width, row.bbox_height))\n    return bboxes\n\ndef plot_random_image(df,rows = 3,cols = 3):\n    fig,ax = plt.subplots(rows,cols,figsize=(12,12))\n    for row in range(rows):\n        for col in range(cols):\n            index = np.random.randint(len(df),size=1)[0]\n            img_id = df.iloc[index].image_id\n            img = Image.open(TRAIN_DIR + img_id + '.jpg')\n            ax[row, col].imshow(img)\n            \n            bboxes = get_all_bboxes(df, img_id)\n            \n            for box in bboxes:\n                add_box = patches.Rectangle((box[0],box[1]),box[2],box[3],linewidth=1,edgecolor='r',facecolor='none')\n                ax[row, col].add_patch(add_box)\n            \n            ax[row, col].axis('off')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_random_image(all_train_images)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Observed that there are numerous amount of bounding boxes per image.\n* And there are some images with fewer number of bounding boxes. \n* I think its best to see maximum and minimum number of bounding boxes in the given data.\n* Images are of different kinds, i think images that came from a source are alike and other sources ae of diffent kind of images.\n* We can see images taken at different lighting conditions and plant maturity stages!","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Visualising images by their source","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_random_image(all_train_images[all_train_images.source == 'ethz_1'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Most of the images from this source conatin more number of bounding boxes per image.\n* Density of wheat heads are more in this source of images.\n* Images have dark green color shit mostly.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_random_image(all_train_images[all_train_images.source == 'arvalis_3'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Images have very low bounding boes to high bounding boxes count.\n* Some images have a lot of background data compared to wheat heads.\n* Images might be taken in different ligh conditions.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_random_image(all_train_images[all_train_images.source == 'usask_1'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Images have very low bounding boes to high bounding boxes count.\n* Some images have a lot of background data compared to wheat heads.\n* Images might be taken in different ligh conditions.\n* Images contain mostly leaves instead of wheat heads. so this might be an indication on these are overgrown plants may be??","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_random_image(all_train_images[all_train_images.source == 'rres_1'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Color of the leaves showcase yellow tint rather than green.\n* Avergae number of boudning boxes. \n* Mostly taken in dark lighting conitions.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_random_image(all_train_images[all_train_images.source == 'arvalis_1'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Images look so bright.\n* Most of the images are taken in bright day light conditions.\n* Images have average to more bounding boxes. so its good.\n* Most images have green adn brown tint.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_random_image(all_train_images[all_train_images.source == 'inrae_1'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Some of the wheat heads are longer than remaining images.\n* So big boundign boxes are found.\n* Images are taken in decent light conditons.\n* Dark Green tint can eb found across the images.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_random_image(all_train_images[all_train_images.source == 'arvalis_2'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Images are taken in brighter conditions.\n* less wheat heads compared to other stuff in the images.\n* Wheat heads are almost same color as leaves...so it might be harder to detect a litle bit.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Visualising images with no bounding boxes and source","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"all_train_images['source'] = all_train_images['source'].fillna('No source')\nall_train_images.source.unique()\n\nprint('No of images with no boxes are ',all_train_images[all_train_images['source']=='No source'].shape[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_random_image(all_train_images[all_train_images['source']=='No source']);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* Observed that there are images with no bounding boxes present in it.\n* We can label them as no box labels when we are modelling.\n* Total 49 of that kind of images are present in the data.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Lets visualize images based on size of bounding boxes","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"large_boxes_ids = all_train_images[all_train_images['bbox_area'] > 200000].image_id\nplot_random_image(all_train_images[all_train_images.image_id.isin(large_boxes_ids)])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* We can see there are huge bouidng boxes in the images, but those boxes contain little to no wheat heads.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"small_boxes_ids = all_train_images[(all_train_images['bbox_area'] < 50) & (all_train_images['bbox_area'] > 0)].image_id\nplot_random_image(all_train_images[all_train_images.image_id.isin(small_boxes_ids)])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* If you look very close, you can probably see those tinyest bounding boxes near the corners and borders of the images. Probably, the boundries were drawn first, than the images were cut into several ones. That is why we see those strange small bounsing boxes in the corners.\n\n* It is not necessary to clean these, because they won't have much effect on the IOU metric.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Observations from the above analysis\n\n* It is evident from the above image analysis that each type of source has specific types of wheat images. This is probably dependent on the region of data collection and time of the year when the particular data was collected.\n* There are some images with no bounding boxes at all.\n* Count of bounding boxes will vary from a min of 1 to max of 116.\n* Most of the images conatin an average of 20 to 60 bounding boxes.\n* Images given are taken from different lighting conditions at differen plant growth level.\n* Bounding boxes are messy!\n1. Giant bounding boxes should be filtered out by area and removed before model training.\n1. Micro bounding boxes. These can stay. They won't have much effect on the IOU metric.\n1. Some spikes are not surrounded by a bounding box (missing bounding boxes).","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"## Possible Approaches for Prediction\n\n* We can directly create an object detection neural network for this problem. But it would try to find wheat in every picture even if it doesn't have any. This might result in false positives.\n* Another approach is to create a classification + object detection ensemble model which would first classify whether the image has any wheat or not. The images that are classified as having wheats will be passed to the object detector for bounding box detection. This would reduce the problem of false positives but might lead to some false negatives","execution_count":null}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}