Week #1: What's happened so far, and what does the future hold?
February 27, 2026
Intro:
Welcome to Week #1 of my blog! Here, I’ll be detailing all aspects of my experience of completing this project. I will be sharing my grand plans, the ups and downs I face throughout the week, what I’ve learned, and what I plan to learn in the future. Let’s begin.
Background:
I currently have some domain expertise regarding this senior project, from my Synopsys Science Fair project from last year. In my science fair project, Measuring and Classifying Wildfires Using a Novel Drone-Based Approach, I designed a DJI F450-style drone kit, and mounted a custom assortment of hardware, including a Raspberry Pi and multiple cameras, to monitor fires and gather data to be used for threat assessment and resource allocation. Through this experience, I acquired the knowledge to design a custom drone build to solve a given problem. While I intend to use brand new parts for this project, I’ll be borrowing some elements of my previous drone that I found optimal to work with. This includes the Pixhawk 2.4.8 flight controller for navigation, and the Raspberry Pi for edge-processing.
My science fair project also provided me the opportunity to gain non-technical expertise and knowledge. I visited a pile burn in Ben Lomond, which provided invaluable insight into what a real fire actually is. The sheer size and intensity of the fire was something that a youtube video simply couldn’t do justice to. I also met many prescribed burners who were extremely passionate about good fire and its benefits, including my external advisor Mr. Jacks, who encouraged me to pursue this project.
Progress:
The final part of this project that I have already completed was a flight mission/drone lookout simulator. I created it as my final project for my Advanced Java class. It served as a proof of concept for my project, and I will use it to run basic simulations of my flight missions, before I actually build my drone and take it on flights. The simulator uses the Dronekit-SITL library, which I am familiar with from my science fair project, as it uses the Dronekit library (Python), for navigation code. Dronekit is a simple library that interfaces well with PyMAVLink, a Python wrapper for the MAVLink communications protocol that many drones use, especially those using ArduCopter, the UAV version of the free autopilot software, ArduPilot. My project used a simple HSV-based color detection model to simulate the fire and smoke detection I aim to complete throughout my senior project.
Current Events:
Now that I’ve swiftly introduced my background, let me discuss the present and the future. Currently, my Raspberry Pi, Raspberry Pi 3 Camera, Raspberry Pi AI HAT+ Accelerator, FLIR Lepton 3.5 thermal sensor module, and PureThermal Mini Pro JST-SR thermal camera interface board have arrived. I will start creating an initial RGB smoke detection and plume tracking pipeline next week with these materials, and will implement thermal detection during Week 3.
This leads me to my first real problem of my senior project. I had originally planned my schedule around my Tarot 680 Pro drone frame arriving by Week 1. This would allow me to complete everything drone-related at the start. I would then move onto the Raspberry Pi and smoke detection work. I had a stable drone platform. However, I had a wrench thrown into my plans by shipping. My frame was slated to arrive by March 25, and I was left droneless for the time being. This led me to having to readjust my schedule and complete my Raspberry Pi and smoke detection work first, and put together my actual drone later. Though it was mildly annoying, I believe I’ve cleared this hurdle, and will continue developing the edge-components.
Next Steps:
The other point of contention on my project is the time of the actual burn. This is where I can actually test my platform. I’ve been told the burn should take place in April. But there is always a possibility it gets pushed up to late March, as weather is the key factor here. This means that I may have to adjust my building and testing schedule down the line. However, this issue is currently out of my control. I will instead focus on what I have right now, a fair bit of computational power and an assortment of camera modules, and I will push on for the time being.
Questions/Outro:
While I’ve provided a some information, I’d like to leave some questions to ponder until next week. Firstly, are there any experiences you’d recommend me to have or sources of knowledge you’d recommend I check out? Doing this during the early weeks of my project may provide me another perspective about my work? Secondly, is there any simulation software that may be particularly helpful for my project? I’d like to simulate the thin air conditions above a fire for me to simulate a drone’s flight in. And finally, are there any potential additions you believe I should make to my project? This can be either to improve its future capability to address its current goals, or provide new functionalities to increase its reach and potential applications?
Thank you for reading, and I hope to see you next week!
Key Terms:
- OS: Operating System
- UAV: Unmanned Aerial Vehicle
Reader Interactions
Comments
Leave a Reply
You must be logged in to post a comment.
Your project is really interesting! I especially like how you’re building a Dronekit-based simulator, that seems like a really smart way to test flight missions and detection methods before actually flying the drone. One question I had was how are you planning to distinguish smoke from similar conditions like fog, dust, or clouds? Are the libraries and pipelines you’re implementing already designed to address this?
Thank you for asking this, as it’s something I wanted to address. I’m planning for my detection pipeline to use the standard Raspberry Pi camera for plume/smoke detection. Then, the output will be passed to the thermal camera. If the thermal camera is detecting significant heat, it should be smoke, otherwise it’s likely fog, dust, or clouds.
This project could be really helpful in the real world! I like how you are using Raspberry Pi and thermal camera modules for detection. One thing I am curious about is how you are going to combine RGB smoke detection with thermal detection. Will both systems work independently, or will you integrate both into one detection pipeline?
That’s a good question! I plan to use the rgb-camera’s smoke detection (which uses a CNN so it’s not exactly RGB detection) for smoke tracking and initial fire detection. The thermal camera will confirm any possible fires that the rgb camera detects with a thermal reading.
I think the intent of this project is really important. As we’ve seen over the last few years, California is very prone to wildfires, so exploring ways to prevent them is incredibly valuable. It was especially interesting to read about pile burns and how fire can actually be used in a positive way to reduce wildfire risk. As you continue developing the project, it might also be interesting to look into places to implement this structure and different ways outside of controlled burns in which this project will be beneficial. Overall, your project seems very well thought out, and I’m excited to see how it progresses, particularly with the planned burn in April.
That’s a good idea. The original intent of my science fair platform last year was to keep the project expandable. I’ll implement that thought process with this project too.
Hi Anav! I think we’re doing similar projects since mine is also computer vision related. Using AI for wildfire detection sounds interesting and definitely impactful, and I like that you’re combining it with a physical drone. For your AI, are you planning to base it off any existing computer vision model, like CNN or ResNet, or building something else?
Hi Yujie! I plan to use a YOLOV8 model for this project, as I’m familiar with it from previous projects, and it’s architecture is well suited for this on-the-go object detection. There is also the opportunity to experiment with different model sizes (nano, small, etc.) and see which is best suited for my application.
I love the idea of your project and the real world applications. It seems like it could be really useful in regions that have a high fire risk or places that could be irrecoverably damaged by fires. I’d like to ask a bit more about the background of your project and am curious about the cost of manufacturing these drones and what is the distance that the drones can observe from? For the AI portion, how might you minimize any false positives that could occur? I’m looking forward to any success and conclusions you draw from this project and hope to see more.
Thank you for these questions. As a bulk response, I’d say it’s all still subject to testing. I need to test the effective range of these camera systems during live demos, and potentially before that if I use matches or something like a barbecue grill to simulate fire. For the AI portion, I will probably have to use these fire sources as well, before I go testing in the field.
I think it’s cool that you’re building on and advancing a previous project that you’ve worked on. I really like this project idea as I think it’s very prevalent to current environmental concerns due to climate change especially in regions like California. I was wondering if this were to be successful what kinds of real world situations do you think something like this would be very useful for? I was also wondering if there’s a way to minimize the effects of external weather conditions which may throw off the detection? I look forward to seeing how your project progresses and the results.
Thank you for your kind words! I believe my project would be useful for pile burns, as well as most other types of prescribed burns. I’m only confident about pile burns for now because that’s the only type I’ve attended, but future testing will allow me to conclude whether it will be useful for other burn types as well. As for external weather conditions, most modern flight controllers utilize an extended kalman filter internally to fuse sensor data, allowing motors to receive varying levels of current to stabilize, in windy conditions.