Category Archives: Uncategorized

R&D – Prototyping & Exploring Options

The first step in our project will be to explore multiple solutions to the problem of tracking, identifying, and utilizing hand signals/gestures. These options will be tiered in nature such that they allow us to progress towards a final prototype before designing and making the final product for the project.

The 4 solutions or Options are laid out below:

  • Option 1 – “Proof of Concept”
    • use a desktop PC & webcam along with pre-trained neural networks or detection software to prove the concept and idea of this project
    • this will help us identify how best to turn the signal detection into actually control signals to a monitor
  • Option 2 – PAJ7620U2 3D gesture recognition Sensor
    • this is a pre-programmed sensor which can detect basic hand gestures
    • the challenge here is to integrate the component into a breadboard setup with something like an Arduino as a controller to take and convert outputs to a monitor for control
  • Option 3 – Ultrasonic Sensors
    • we plan to use 4 ultrasonic sensors as a means of testing how little info is needed to detect hand signals in an effort to increase detection time and processing lag
    • this also presents a cheaper option to using cameras
  • Option 4 – Raspberry Pi w/ camera
    • this option is aimed at moving us towards out ultimate end goal for the project. It would allow us to use all of our new knowledge to enable fast, accurate, and customizable hand signal input to a greater extent than the option options and provides a great starting point for a final prototype

Project Objective

Create a low-cost embedded product with camera that is able to learn and recognize a custom and reconfigurable set of 5-10 basic hand signals. For example, this could be used as an alternative method to control digital devices from a far. A mobile application should allow users to 1) configure the device to connect to WiFi/Bluetooth, 2) perform real-time machine learning and training for new hand signals, 3) recognize and effectively identify signals when present. The real constraint of this project is the embedded hardware cost and size, meaning that most computation will need to be forwarded to a cloud server for processing.

CONSTRAINTS
< $5/unit
< 6 months for development and testing
Prediction Accuracy > 75%
False Alarm Rate < 5%
Prediction Speed < 1 second