Loading Now

Summary of Drivegazen: Event-based Driving Status Recognition Using Conventional Camera, by Xiaoyin Yang


DriveGazen: Event-Based Driving Status Recognition using Conventional Camera

by Xiaoyin Yang

First submitted to arxiv on: 16 Dec 2024

Categories

  • Main: Computer Vision and Pattern Recognition (cs.CV)
  • Secondary: Artificial Intelligence (cs.AI)

     Abstract of paper      PDF of paper


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 introduces a wearable device for recognizing driving status, along with an open-source dataset and a real-time method for identifying driving status from eye observations. The method uses event frames generated from conventional intensity frames and an Attention Driving State Network (ADSN) to recognize driving status. Compared to event cameras, conventional cameras offer richer spatial information but lack temporal information, posing challenges in recognizing driving status. To address this issue, the paper utilizes video frames to generate synthetic DVS events, adopts a spiking neural network to decode temporal information, and uses ADSN to extract spatial cues and guide attention during training and inference. The approach is validated on the Driving Status (DriveGaze) dataset and the Single-eye Event-based Emotion (SEE) dataset.
Low GrooveSquid.com (original content) Low Difficulty Summary
The paper introduces a new way to recognize when someone is driving or not using a camera that’s worn by the driver. They also created a big collection of data with labeled examples, which can be used to train machines to do this task accurately. The method uses special techniques like “event frames” and “Attention Driving State Network” (ADSN) to analyze the video feed from the camera and figure out if someone is driving or not.

Keywords

» Artificial intelligence  » Attention  » Inference  » Neural network