Cat Pereira

Cat Pereira

Full-stack engineer, CV applications

I bridge the gap between computer vision and the real world. My background in platform services and game development has given me the foundational knowledge needed to build user-friendly, intuitive, and powerful custom dashboards, and their required backend services for successful computer vision implementation.

My portfolio includes projects incorporating pose estimation and body tracking, work done to use CV to translate and teach ASL, and projects that use CV as part of a data ingestion pipeline. I am also the sole maintainer of explorable.cv, a site dedicated to explaining computer vision concepts with interactive demos.

If I'm AFK, I'm either re-caffeinating, watching Formula 1 at an absurd hour, or out bouldering with friends!

explorable.cv

๐Ÿงญexplorable.cv

The home for my computer vision explorables!

Computer VisionReactTypeScriptVite
F1Guessr

๐ŸŽ๏ธF1Guessr

Web game inspired by GeoGuessr for F1 fans to guess the year and grand prix from a photo of the race.

Computer VisionPyTorchPythonReact
Sorty

๐Ÿค–Sorty

Local data preparation tool for computer vision, built to curate datasets I feel fully confident in before training.

Computer VisionFastAPILLMsPyTorchPythonReact
Sign Cards

๐ŸŒŸSign Cards

Browser game for learning ASL fingerspelling, with themed levels and webcam flashcards.

Computer VisionReactTypeScriptVite
Yoga Mirror

๐ŸชทYoga Mirror

Hold a yoga pose in front of your webcam and the app classifies it live

Computer VisionPyTorchPythonReactTypeScriptVite
Otterwatch

๐ŸฆฆOtterwatch

Live status board that watches sea otter cams, detects when an otter is on screen, and notifies you when one appears.

Computer VisionPostgresPythonReactTypeScript
MH Nature Cam

๐ŸŒฒMH Nature Cam

Wildlife cam board that watches Morten Hilmer's 24/7 woodland livestream and records a clip around each animal sighting.

Computer VisionPython
detstream

๐Ÿ›ฐ๏ธdetstream

Modular object detection framework for live video feeds. The engine behind Otterwatch.

Computer VisionPython
airdraw

๐Ÿ–๏ธairdraw

Draw on screen by pinching your fingers in the air, tracked through your webcam.

Computer VisionReactTypeScriptVite
OpenHand

๐ŸคŸOpenHand

Web app that converts American Sign Language fingerspelling to text in real-time using a webcam.

Computer VisionPyTorchPythonReactTypeScriptVite
Captionaut

๐Ÿ‘ฉโ€๐Ÿš€Captionaut

Video captioning app with automated transcription, speaker diarization, and inline caption editing.

Audio MLFastAPIPythonReact
prompt2dataset

๐Ÿ’ฌprompt2dataset

CLI tool that generates labeled image datasets from plain-English descriptions.

Computer VisionLLMsPyTorchPython
cli-cards

โœ‰๏ธcli-cards

Renders the terminal-style usage cards shown across this site. Works as a CLI, an npm library, and a browser-based card editor.

ReactTypeScriptVite
stitchimg

๐Ÿงตstitchimg

Stacks images vertically into one PNG or JPEG, running entirely in the browser.

ReactTypeScriptVite
DarkScrolls

๐Ÿ“œDarkScrolls

Chrome extension that seals away distracting websites and counts the doomscrolls you dodged.

JavaScript
airship.top

๐Ÿš€airship.top

A website I hosted to track live player count statistics for the multiplayer game platform Airship using GCP Cloud Run, Cloud Scheduler, Firebase Hosting, and Neon.

Google Cloud PlatformNest.jsReactTypeScript
Airship

โœˆ๏ธAirship

Worked on platform micro services, fully designing and implementing features across our stack from the database structure (Postgres, Prisma), to API design (NestJS, REST), and our user interfaces (TypeScript, React, Svelte).

Google Cloud PlatformNest.jsPostgresReactTypeScript
dinnote

๐Ÿ™†dinnote

Package building off my existing work with the dinscribe package to add speech diarization into my audio pre-preprocessing pipeline.

Audio MLPython
dinscribe

๐ŸŽตdinscribe

Package streamlining multiple steps of applying audio pre-processing libraries to clean noisy audio and detect speech.

Audio MLPython
F1 Pit Wall

๐ŸŽงF1 Pit Wall

Website hosting transcriptions of all driver radio communications from the 2025 F1 season.

Audio MLLLMsPythonReact
Roblox BedWars

๐Ÿ›๏ธRoblox BedWars

Led technical and creative development of over 10 purchasable and playable in-game characters

LuaReactRoblox EngineTypeScript
Roblox Islands

๐Ÿ๏ธRoblox Islands

Contributed to a weekly content update schedule

LuaReactRoblox EngineTypeScript
CNN Playground

๐Ÿ–จ๏ธCNN Playground

Browser-based interactive tool for visualizing how convolutional operations transform images in real-time.

Computer VisionReactTypeScript
CNN Visualizer

๐Ÿ–ผ๏ธCNN Visualizer

Web app that visualizes what a trained CNN model perceives at each layer when processing CIFAR-10 images.

Computer VisionPyTorchPythonReactTypeScript
CNN Architecture Comparison

๐Ÿ•ฐ๏ธCNN Architecture Comparison

Interactive web app that compares six major CNN architectures (LeNet-5, AlexNet, VGG-11, Inception-mini, ResNet-20, DenseNet-BC) side-by-side on the same image.

Computer VisionPyTorchPythonReactTypeScript
CV Interpretability Explorer

๐Ÿ”ฌCV Interpretability Explorer

Compares three image classifiers (Custom CNN, ResNet-18, ViT-S) trained on ImageNette, showing what factors go into each one's output.

Computer VisionPyTorchPythonReactTypeScript
Object Detection Playground

๐Ÿ”Object Detection Playground

Interactive tour of the processing that makes up an object detection pipeline.

Computer VisionReactTypeScript
ViT Playground

๐Ÿ‘€ViT Playground

Visualizes how a Vision Transformer turns an image into a sequence of tokens, then runs ViT-tiny end to end in the browser.

Computer VisionPyTorchReactTypeScript