Summary of Smartphone-based Eye Tracking System Using Edge Intelligence and Model Optimisation, by Nishan Gunawardena et al.
Smartphone-based Eye Tracking System using Edge Intelligence and Model Optimisation
by Nishan Gunawardena, Gough Yumu Lui, Jeewani Anupama Ginige, Bahman Javadi
First submitted to arxiv on: 22 Aug 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Performance (cs.PF)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents two new smartphone-based eye-tracking techniques for video-type visual stimuli, addressing limitations of current algorithms trained on static images. The proposed methods combine Convolutional Neural Networks (CNN) with Recurrent Neural Networks (RNN), specifically Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). The CNN+LSTM and CNN+GRU models achieved average Root Mean Square Error of 0.955 cm and 1.091 cm, respectively. To overcome resource constraints on smartphones, the authors developed an edge intelligence architecture to enhance eye-tracking performance. Optimisation methods like quantization and pruning were applied to deep learning models for better energy, CPU, and memory usage. The model inference time was reduced by 21.72% and 19.50%, respectively, on edge devices. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about making it easier to track people’s eye movements using smartphones. Right now, the algorithms used aren’t very good at handling videos or moving images. To fix this, the researchers created new methods that combine two types of neural networks (CNN and RNN) to improve accuracy. They also came up with ways to make these methods work better on smartphones by reducing the amount of power they use. |
Keywords
» Artificial intelligence » Cnn » Deep learning » Inference » Lstm » Pruning » Quantization » Rnn » Tracking
