Raspberry Pi Image Processing

The goal of this project is to integrate machine learning with the Raspberry Pi 4, leveraging the computational power of the Intel Neural Compute Stick 2 in order to get sufficient speeds to identify patches of weeds in farm plots.

=Problem Definition= Current computers suffer from being heavy and using high amounts of electricity. This prevents them from being carried by drones, which means that any sort of aerial image recognition is impossible.

=Background= With the advent of artificial intelligence, computers are now able to manage computationally-heavy tasks, such as facial recognition and self-driving vehicles. However, machine learning is typically limited by the processing speed of the computer, and is usually limited to bulky computers that are stationary or draw large amounts of power. The purpose of this project is to demonstrate the viability of machine learning on smaller machines, such as the Raspberry Pi, which could then be used for crop identification via drones. Since big computers are too heavy to be carried by a drone, the extremely light-weight Raspberry Pi would eliminate the problem of weight as well as the problem of high power draw.

=Deliverables=
 * Develop a benchmark for speed comparisons between the Raspberry Pi with the NCS2, and a standard computer with a modern processor and graphics card.
 * Implement a pre-trained artificial neural network with the Raspberry Pi.
 * Use a standard image processing library to process images in real-time.
 * Compare processing times between the computer and the Raspberry Pi.

=Value Proposition Statement= Most modern farmers use small, Kerosene-fueled airplanes to spray pesticides onto their fields. Our goal is to instead, use a small computing system atop a drone to detect weeds and trigger a spraying mechanism in order to save farmers time and money. If successful, modern farmers won’t need to use small airplanes that are dangerous, use fossil fuels, take up space, and pollute the atmosphere. Our weed spraying drone will be easier to store, cost-effective, more accurate, and require brief human interaction. This could improve the quantity as well as quality of foods. Our object detection will allow us to target exact locations that need spraying, so it will reduce the amount of toxic chemicals going into the soil. Our project will be using a raspberry pi to explore the benefits of using smaller computers to do computationally heavy tasks with computer weight limits.

=Design Considerations=

=Project Learning=
 * Utilize pre-trained models on the TensorFlow Github, which allows us to get a prototype up and running quicker.
 * Incorporating the NCS2 with the Raspberry Pi is well-documented and supported by the Raspberry Pi operating system.

=Final Design= TBA

=Validation=

=Team Members=

Tori Gehring
Mechanical Engineering Student

Hometown: Gig Harbor, WA

Hobbies/Interests: My professional interests have always been geared towards helping people and making a difference, and thus I have been interested in the bio-med and bioengineering fields. In my free time I enjoy several board sports, including snowboarding, wake surfing and longboarding. Along with this I am an avid rock climber.

Plan for Future: I don’t have a set plan for what I will do after college, but at this point am determined to pass the PE exam as soon as possible.

Email: osbo8726@vandals.uidaho.edu

Jon Gift
Computer Engineering Student

Hometown: Arco, Id

Intersests include building and programing computer systems. Designing applications for implementation on microcontrollers and FPGA's. Ultimately would like to get into building and designing prosthetics or new medical technologies. Also spend time cooking, playing baseball and target shooting.

Email: pach7646@vandals.uidaho.edu

Isabel Hinkle
Biological Systems Engineering Student

Hometown: Worland, Wyoming

I enjoy skiing, reading, playing video games, and writing.

My future goals are to go into Biomedical Engineering.

Email: staa1939@vandals.uidaho.edu

Oshan Karki
Biological Systems Engineering Student

Hometown: Fargo, North Dakota

Hobbies/Interests: My professional interests center around the application of ergonomics in engineering, I apply this at my current internship working on the Advanced Accessible Pedestrian System. At the University of Idaho, I am a member of the Concrete Canoe Club in addition to being the president of the Agricultural and Biological Engineering Club and the secretary/fundraising chair to the Civil Engineering Club. In my spare time, I enjoy reading, cooking, and playing tennis.

Plan for the future: Eventually, I would love to have an engineering career focusing on how medical devices can be more functional for the user.

Email: swan5849@vandals.uidaho.edu =Additional Documentation=

Project Schedule

Gantt & Meetings

Meeting Minutes

Meeting Minutes

Presentations

Snapshot

Client Interview

Interview Summary