brand banner

AirBoard

AirBoard is a portable digital whiteboard system engineered to allow teachers to make handwritten annotations on any flat surface using infrared diodes (~940nm), optical sensors, Computer Vision, and perspective transform.

Updated · 1 min read · #project · #computer-vision · #hardware

AirBoard

AirBoard is a portable digital whiteboard system engineered to allow teachers to make handwritten annotations on any flat surface using infrared diodes (~940nm), optical sensors, Computer Vision, and perspective transform.

AirBoard is a portable digital whiteboard system engineered to allow teachers to make handwritten annotations on computer and projector screens (or on any flat surface). Utilizing Computer Vision and Artificial Intelligence techniques, AirBoard is built with cutting-edge technology that can bring any classroom into the digital age.


Demo

Implementation

AirBoard implementation poster

Involvements

Carsome Mobility Lab

11 November 2021 — Prof. Elizabeth Lee (CEO, Sunway Education Group) and Mr. Eric Cheng (CEO, Carsome) signed a Memorandum of Understanding with AirBoard.

AirBoard and Carsome Mobility Lab poster

Articles

Hackathon Events

AirBoard has won at least 4 international hackathons. This success is thanks to the dedication of the AirBoard team and it’s dedicated determination. AirBoard’s innovative ingenuity is easily appreciated by judges and participants alike.

AirBoard hackathon events poster

Launching Ceremonies

AirBoard’s initial MVP prototype was constructed at SMK Seafield High School’s Robotics Lab. Upon completion, the prototype was field-tested by the Deputy Selangor District Ministor of Education, the School Principal, and the President of the Parent-Teacher Association during morning assembly.

AirBoard launch at SMK Seafield High School

  • DriveSafe AI (31%) — Driver risk assessment from dashcam footage, using a ResNet50 + LSTM model to classify driving as safe, collision, tailgating, or weaving.
  • Handwired: Programs as Neural Networks (30%) — How Handwired replaces control flow with numeric data flow, and what that does—and does not—make possible.
  • Superliminal in Three.js (29%) — Recreation of the 'Superliminal' game's 'Forced Perspective' effect using Three.js. Used Raycaster, Quaternion Rotations, Bounding Boxes, and Linear Transformations.
  • DriveSafe: Video Classification Notes (28%) — Early DriveSafe notes on driving behavior classification, training data, model evaluation, and ways to incorporate temporal information from video.
  • Data Augmentation for Bias Term (22%) — Adding a constant feature folds the intercept into linear regression’s weight vector without conflating it with statistical bias.
  • Raycasting to the Entire Surface of an Object in Three.js. (21%) — 3 best approaches to efficiently raycast from the camera and cover the entire surface of an object in Three.js.
  • Linear Algebra LaTeX (21%) — Some basic LaTeX snippets common used in Linear Algebra.
  • yang-ts-parser (21%) — CLI tool to automagically parse and compile YANG models into Typescript types with respect to Nokia SDN extended RESTCONF implementation. Lexer/parser grammar based on ANTLRv4.

© 2026 James Yap

Personal Website and Knowledge Base