Skip to the content
2 layers23 × 24.2 mmFD PCB, the printed circuit board in 3D

This repository aims to detect fires at an early stage and classify the type of fire using sensor-fusion techniques and machine learning. The project is from the University of Texas at Austin's engineering senior design group Spring 2026.

Size
23 × 24.2 mm
Copper layers
2
Thickness
1.6 mm
Parts
6
Nets
7
Pads
9
Tracks, vias
5, 0
Routed
Yes
KiCad
KiCad 8.0 (file 20240108)
Created
28 Jan 2026
Updated
27 Apr 2026

Overview

FD PCB is an open-source printed circuit board by CaptainOrangeSparrow, from the CaptainOrangeSparrow/early-fire-detection-classifier repository on GitHub. It is a 2-layer board of 23 × 24.2 mm with 6 parts on 7 nets, routed with 5 tracks and 0 vias.

It belongs with the sensors and measurement boards of this library.

README

README.md

Early-fire-detection-classifier

Description

This repository aims to detect fires at an early stage and classify the type of fire using sensor-fusion techniques and machine learning. The project is from the University of Texas at Austin's engineering senior design group Spring 2026.

Things that are Good to Know

GIT

Git on the jetson is setup using the SSH key route. Any git actions will not prompt a log in due to the stored SSH deploy key. Pushes will be recorded as have been made by the deploy key. Whoever is registered on the jetson's git config global user.email will show up as the user responsible of a commit at the time of commit.

To change the git config global user:

git config --global user.email [git email here]

When you want to do a COMMIT, change the git config global user email to your git email or sign your first name at the end of your commit message (For example add file -firstname).

Once you attempt to PUSH your changes, you will then be prompted with the following message to provide a passphrase for security (this passphrase is shared among the team members):

Enter passphrase for key '/home/firedistinguisher/.ssh/id_ed25519':

AFTER you finish pushing your changes and making edits, consider running the following command to clear the user.email environment variable so the next developer will be automatically reminded to provide their email when making their commits, thanks!

git config --global --unset user.email


SSH

To log onto the jetson from the ECE-LRC servers:

ssh firedistinguisher@localhost -p 2000

To log onto the jetson from the ECE-LRC servers with video forwarding:

ssh firedistinguisher@localhost -p 2000 -Y

To log onto the jetson from your laptop through the ECE-LRC servers to support web-streaming from local host on the jeston to your local browser:

ssh ssh -J eid@mario.ece.utexas.edu -p 2000 firedistinguisher@localhost -L [port]:localhost:[port]

  • Replace [port] with the port number the web stream is hosted on or streaming to

CONDA Virtual Environment Manager

Available CONDA environments:

  • base
  • app
  • appgui
  • cameragui
  • recording
  • telemetry

Please do not modify the base environment.


Repository Structure

I2C-testing

This folder contains code to test accessing read-write functionality on the I2C bus using python smbus2 module for various connected devices including the ADC and HDC. Use i2cdetect -r to scan I2C busses for connected devices.

  • basic-I2C.py sends read and write commands on the i2c bus
  • ads1115-i2c.py is a class that reads values from the ads1115 modules
  • hdc3022.py is a class that reads values from the hdc3022 temp and humidity sensor

Requires recording conda env.


audio-testing

This folder contains code for testing the MAX98357A Audio Amp for producing audio from the jetson using the I2S protocol.

  • play-tone.py plays a sine wave for a specified duration and frequency
  • play-wav.py plays a wav file

Requires recording conda env.


camera-gui

This folder contains original python gui that was developed to play prerecorded mp4 files. A pyside 6 gui application is used to display the videos and interactive buttons.

  • camera_gui.ipynb is the original python notebook that was used to develop the initial gui
  • camera_gui.py is the python version of the ipynb notebook
  • test.txt is a test file

Requires cameragui conda env.


camera-testing

This folder contains tools to view the raw camera streams for RGB and IR cameras. In particular, it contains code for the tc001. The raw camera streams open native openCV windows or host a web stream. NOTE: The tc001 code came from another repo leswright pythermalcam and contains some erroneous temperature decoding code. (That is fixed in the data recording camera module)

  • readme: This folder comes with its own readme. See readme for more details
  • web-stream-camera.py is the web stream version of stream-camera.py. Note: to use the web-stream, the ssh port forwarding needs to be used. (See web stream ssh command above).

Requires cameragui conda env.


data-recording

This is the main data recording software folder. Multi-modal data is recorded and streamed using either a pyside6 gui application, console only mode, or web stream application (recommended). Data is recorded at a default 25 FPS.

Recordings are saved to saved_recordings [dir] and test_recordings [dir] hold recordings that were taken just for testing and are kept for historical purposes.

  • readme.txt: This folder comes with its own readme. See readme for more details
  • record.py is the main data recording script```
  • utilities [dir] holds utility modules such as writers, web stream host server, html, javascript, etc. and other helpful utility code
  • peripherals [dir] holds modules containing classes to read info and interact with connected external devices such as cameras and adcs.
  • saved_recordings [dir] holds saved recordings
  • test_recordings [dir] holds test recordings
  • clear_Saved_to_test.py is a helper script to move all recordings in saved_recordings to test_recordings
  • gstreamer_test.py is a helper script to test using gstreamer to run nvidia hardware optimized camera frames
  • verify-frame-count.py is a helper script to count the number of frames in every mp4 file in a specified directory (does not search child directories)

Requires recording conda env.


downloads

The purpose of this folder is to store files in transit (Files that needed to be copied over into or exported out of the jeston).


stream-camera-gui

This folder contains files to stream both RGB and IR camera feeds simultaneously with a more custom gui in a pyside6 application

  • readme.txt: This folder comes with its own readme. See readme for more details. This readme has details for the rest of the components in the folder and therefore the other contents in the folder won't be listed again here.

Requires appgui conda env.


telemetry-display

This folder contains files to stream data to a ST7735 LCD display.

Requires telemetry conda env.


test-files

This folder contains miscellaneous test files.


Additional Notes

Thanks, add anything other considerations here if need be.

Michael

Parts

6
QtyValueFootprintReferences
4~ECE445L:MountingHole_4_40H3, H4, H5, H6
1Barrel_Jack_SwitchConnector_BarrelJack:BarrelJack_Wuerth_6941xx301002J1
1Conn_01x02Connector_PinHeader_2.54mm:PinHeader_1x02_P2.54mm_VerticalJ24

More from CaptainOrangeSparrow/early-fire-detection-classifier

6
  • 2 layers251.3 × 143.9 mmFD PCB, the printed circuit board in 3D

    FD PCB

    CaptainOrangeSparrow/early-fire-detection-classifier

    This repository aims to detect fires at an early stage and classify the type of fire using sensor-fusion techniques and machine learning.

    183 parts1
  • 2 layers246.2 × 120.3 mmFD PCB, the printed circuit board in 3D

    FD PCB

    CaptainOrangeSparrow/early-fire-detection-classifier

    This repository aims to detect fires at an early stage and classify the type of fire using sensor-fusion techniques and machine learning.

    150 parts1
  • 2 layers113.7 × 71.6 mmFD PCB, the printed circuit board in 3D

    FD PCB

    CaptainOrangeSparrow/early-fire-detection-classifier

    This repository aims to detect fires at an early stage and classify the type of fire using sensor-fusion techniques and machine learning.

    113 parts1
  • 2 layers116.5 × 79 mmFD PCB, the printed circuit board in 3D

    FD PCB

    CaptainOrangeSparrow/early-fire-detection-classifier

    This repository aims to detect fires at an early stage and classify the type of fire using sensor-fusion techniques and machine learning.

    29 parts1
  • 2 layers73.7 × 61 mmFD PCB, the printed circuit board in 3D

    FD PCB

    CaptainOrangeSparrow/early-fire-detection-classifier

    This repository aims to detect fires at an early stage and classify the type of fire using sensor-fusion techniques and machine learning.

    28 parts1
  • 2 layers44.3 × 15.2 mmFD PCB, the printed circuit board in 3D

    FD PCB

    CaptainOrangeSparrow/early-fire-detection-classifier

    This repository aims to detect fires at an early stage and classify the type of fire using sensor-fusion techniques and machine learning.

    7 parts1

Similar boards

  • 2 layers18.5 × 11.1 mmSwitch, the printed circuit board in 3D

    Switch

    byrantech/laptop

    anyon_e, a highly integrated, high end, open source laptop. Attempt the impossible.

    6 parts4.3kMIT
  • 2 layers14.6 × 33 mmBrain board SD Card 1, the printed circuit board in 3D

    Brain board SD Card 1

    rusefi/rusefi

    rusefi - GPL internal combustion engine control unit

    6 parts1.2k
  • 2 layers9 × 9 mmDpoint, the printed circuit board in 3D

    Dpoint

    Jcparkyn/dpoint

    Open-source digital stylus using camera tracking and inertial measurements

    6 parts1.1kMIT
  • 2 layers51.5 × 16.6 mmMicroswitchXY Endstop, the printed circuit board in 3D

    MicroswitchXY Endstop

    VoronDesign/Voron-Hardware

    Cool Hardware designed by the Voron Design group

    6 parts1.1kGPL-3.0
  • 2 layers21.9 × 76.7 mmAmiga External, the printed circuit board in 3D

    Amiga External

    hoglet67/RGBtoHDMI

    Bare-metal Raspberry Pi project that provides pixel-perfect sampling of Retro Computer RGB/YUV video and conversion to HDMI

    6 parts1kGPL-3.0
  • 2 layers88.9 × 50.8 mmBusinesscard, the printed circuit board in 3D

    Businesscard

    hackclub/OnBoard

    💡 Join 1,000 teenagers and make your first PCB with a $100 grant!

    6 parts915
  • 2 layers20.3 × 15.2 mmL0 RGB led, the printed circuit board in 3D

    L0 RGB led

    Luos-io/luos_engine

    Open-source and real-time orchestrator for cyber-physical-systems, to easily design, test and deploy embedded applications and digital twins.

    6 parts546MIT
  • 2 layers9 × 3.6 mmOpticalEncoder, the printed circuit board in 3D

    OpticalEncoder

    adamb314/ServoProject

    Getting the most out of your hobby servo

    6 parts545

Questions

How big is the FD PCB PCB?

It measures 23 × 24.2 mm and has 2 copper layers, 1.6 mm thick.

What parts does the FD PCB use?

6 parts. The full list of its parts is on this page, with links to each part's symbol and footprint where PCBKit's library has them.

Where can I download the FD PCB KiCad files?

From the CaptainOrangeSparrow/early-fire-detection-classifier repository on GitHub, at the commit this page was made from: the board is hw/KiCAD/FD_PCB_Final_BarrelJackBreakout_Board/FD_PCB.kicad_pcb and its schematic hw/KiCAD/FD_PCB/FD_PCB.kicad_sch. PCBKit opens the board in the browser, with nothing to install.

Can I use the FD PCB design in my own project?

Its repository states no licence, so its author keeps all rights: ask CaptainOrangeSparrow before reusing the design.