Summary of Towards Infusing Auxiliary Knowledge For Distracted Driver Detection, by Ishwar B Balappanawar et al.
Towards Infusing Auxiliary Knowledge for Distracted Driver Detection
by Ishwar B Balappanawar, Ashmit Chamoli, Ruwan Wickramarachchi, Aditya Mishra, Ponnurangam Kumaraguru, Amit P. Sheth
First submitted to arxiv on: 29 Aug 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
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 proposed method, KiD3, aims to detect and classify distracted driving behaviors from in-vehicle camera feeds to improve road safety. This is a challenging task due to the need for robust models that can generalize to diverse driver behaviors without requiring extensive annotated datasets. The approach infuses auxiliary knowledge about semantic relations between entities in a scene and the structural configuration of the driver’s pose, integrating scene graphs, driver pose information, and visual cues to create a holistic representation of the driver’s behavior. Experimental results show that KiD3 achieves a 13.64% accuracy improvement over the vision-only baseline by incorporating auxiliary knowledge with visual information. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary KiD3 is a new way to detect distracted driving using camera feeds from cars. This helps make roads safer. The problem is tricky because drivers do lots of different things while driving, and we need a computer program that can recognize all these behaviors without needing huge amounts of labeled data. KiD3 works by combining information about the scene, what the driver is doing, and visual clues in the video to get a complete picture of the driver’s behavior. It did better than other methods by adding this extra information. |
