🌾🍚 Wheat Localization With Convolutional Neural Networks (CNNs)

Problem Statement

We use wheat everyday in the form of bread, oats and other important breakfast and lunch items. It would be really good if the manual process of detecting wheat and their density is replaced by machine learning and data science. Since there are many forms of wheat, we must be identifying the right kinds of wheat plants so that they could be processed quickly. This could be done with Convolutional Neural Networks (CNNs) and it becomes a computer vision problem.

Convolutional Neural Networks (CNNs)

One of the interesting ways at which we can use CNNs is that we might identify the total number of wheat heads in fields. As a result, it is possible to estimate the density of wheat plants in different locations of the fields. This leads to a good understanding of the field quality. If the condition is poor, appropriate steps could be taken to ensure that wheat plants get adequate supply of nutrients which leads to their high quality production.

It is also important to accurately detect the wheat plants and sometimes the wind could blur the images. In addition to this, there could be factors such as maturity, color, genotype, and head orientation that could make detecting and classifying weed a challenging task.

💻 Training with NVIDIA's RTX 2080 GPU

• GPU-accelerated deep learning frameworks offer flexibility to design and train deep neural networks.
• With cuDNN and Nvidia's graphics drivers, I was able to train the models really quickly by using GPU cores rather than the CPU cores.
• This led to a significant increase in the speed of training and developing convolutional neural networks (CNNs).

👉 Directions to download the repository and run the notebook

This is for the Washington Bike Demand Prediction repository. But the same steps could be followed for this repository.

1. You'll have to download and install Git that could be used for cloning the repositories that are present. The link to download Git is https://git-scm.com/downloads.

  

2. Once "Git" is downloaded and installed, you'll have to right-click on the location where you would like to download this repository. I would like to store it in "Git Folder" location.

  

3. If you have successfully installed Git, you'll get an option called "Gitbash Here" when you right-click on a particular location.

  

4. Once the Gitbash terminal opens, you'll need to write "Git clone" and then paste the link of the repository.

  

5. The link of the repository can be found when you click on "Code" (Green button) and then, there would be a html link just below. Therefore, the command to download a particular repository should be "Git clone html" where the html is replaced by the link to this repository.

  

6. After successfully downloading the repository, there should be a folder with the name of the repository as can be seen below.

  

7. Once the repository is downloaded, go to the start button and search for "Anaconda Prompt" if you have anaconda installed.

  

8. Later, open the jupyter notebook by writing "jupyter notebook" in the Anaconda prompt.

  

9. Now the following would open with a list of directories.

  

10. Search for the location where you have downloaded the repository. Be sure to open that folder.

  

11. You might now run the .ipynb files present in the repository to open the notebook and the python code present in it.

  

It is also important to accurately detect the wheat plants and sometimes the wind could blur the images. In addition to this, there could be factors such as maturity, color, genotype, and head orientation that could make detecting and classifying wheat a challenging task.

Computer Vision

• With the aid of computer vision, it is possible to count the total number of wheat heads present in an image.
• We do this by giving annotated examples of various images and the count of the wheat heads.
• As we are annotating those images, soon the computer vision model learns from the data and labels and predicts the density of wheat plants from an image.
• As a result, one could estimate the total density of wheat plants in a particular area.
• Furthermore, steps can be taken to improve the yield if their density is predicted to be low by the computer vision models and vice-versa.

💻 Training with NVIDIA's RTX 2080 graphics card for Computer Vision Tasks

• GPU-accelerated deep learning frameworks offer flexibility to design and train deep neural networks.
• With cuDNN and Nvidia's graphics drivers, I was able to train the models really quickly by using GPU cores rather than the CPU cores.
• This led to a significant increase in the speed of training and developing convolutional neural networks (CNNs).

👉 Directions to download the repository and run the notebook

This is for the Washington Bike Demand Prediction repository. But the same steps could be followed for this repository.

1. You'll have to download and install Git which could be used for cloning the repositories that are present. The link to download Git is https://git-scm.com/downloads.

  

2. Once "Git" is downloaded and installed, you'll have to right-click on the location where you would like to download this repository. I would like to store it in the "Git Folder" location.

  

3. If you have successfully installed Git, you'll get an option called "Gitbash Here" when you right-click on a particular location.

  

4. Once the Gitbash terminal opens, you'll need to write "Git clone" and then paste the link to the repository.

  

5. The link to the repository can be found when you click on "Code" (Green button) and then, there would be an HTML link just below. Therefore, the command to download a particular repository should be "Git clone HTML" where the HTML is replaced by the link to this repository.

  

6. After successfully downloading the repository, there should be a folder with the name of the repository as can be seen below.

  

7. Once the repository is downloaded, go to the start button and search for "Anaconda Prompt" if you have anaconda installed.

  

8. Later, open the Jupyter notebook by writing "Jupyter notebook" in the Anaconda prompt.

  

9. Now the following would open with a list of directories.

  

10. Search for the location where you have downloaded the repository. Be sure to open that folder.

  

11. You might now run the .ipynb files present in the repository to open the notebook and the python code present in it.

  

That's it, you should be able to read the code now. Thanks.