vision-processing

PhotonVision is the free, fast, and easy-to-use computer vision solution for the FIRST Robotics Competition.

Generating Video Description using Sequence-to-sequence Model with Temporal Attention

Dynamic vision processing system for FRC coprocessors

FRC Rapid React Vision Processing

Self Driving Robot – A Python and OpenCV-based self-driving robot built with Raspberry Pi and Arduino. It can follow lanes, detect AprilTags and crosswalks, and navigate safely through intersections. Designed for educational purposes, prototyping, and robotics competitions, it also supports real-time vision processing and optional live streaming.

Vision Processing - 2021

Astrolabe is a vision processing software for FRC teams. It is capable of object detection and apriltag detection, along with calculating a bunch of stuff about the object's location. It is designed to be the easiest vision processing system to use for FRC teams.

Number Plate Reader Using Image Processing In MATLAB

Cascade Classifiers and Image Dataset for the FRC Rapid React Season

Integrating GPT-4 with Vision into a reinforcement learning framework using Pygame and TensorFlow, this project enables an agent to navigate and interact within a simulated environment using advanced visual and textual input processing.

Home of the team's vision code!

Number Plate Detector Using Image Processing In MATLAB

A high-performance computer vision processing engine with an intuitive interpreter for building vision pipelines. support for real-time image processing, video I/O, deep learning, feature detection, optical flow, background subtraction, and more.

Handwritten Digit Recognition Using Machine Learning

Trained HAAR Cascade model for FRC 2020-2021 Infinite Recharge

The aim of this project is to decode the colour bands of a resistor by image processing and display the value of the resistance.

A collection of plugins for the ForgeSyte platform

This repository composes the modules available for an attentional system based on the selection model for perception proposed by Colombini (2016). The modules were implemented with CST.

EdgeOSA-Underwater-Vision-Enhancement is a lightweight deep learning framework for underwater image enhancement designed for high restoration quality and real time deployment. The proposed EdgeOSAEnhancer architecture integrates OSA aggregation, depthwise separable convolutions, channel shuffle, shift operations, and attention mechanisms.

detects notes and sends the data to the rio over udp