Summary of P-yolov8: Efficient and Accurate Real-time Detection Of Distracted Driving, by Mohamed R. Elshamy et al.
P-YOLOv8: Efficient and Accurate Real-Time Detection of Distracted Driving
by Mohamed R. Elshamy, Heba M. Emara, Mohamed R. Shoaib, Abdel-Hameed A. Badawy
First submitted to arxiv on: 21 Oct 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
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 A machine learning-based approach to detect distracted driving behaviors is presented in this study. The authors optimize the Pretrained YOLOv8 (P-YOLOv8) model, a real-time object detection system, for both speed and accuracy. This approach addresses computational constraints and latency limitations associated with conventional detection models. The study demonstrates P-YOLOv8’s versatility in object detection and image classification tasks using the Distracted Driver Detection dataset from State Farm. Compared to deep learning models like VGG16, VGG19, and ResNet, P-YOLOv8 achieves competitive accuracy while reducing computational costs and improving detection speeds. The lightweight model (2.84 MB) with 1,451,098 parameters offers high accuracy (99.46%) making it a cost-effective solution for real-time deployment using Tiny Machine Learning (TinyML). This study provides an in-depth analysis of P-YOLOv8’s architecture, training, and performance benchmarks, highlighting its potential for real-time use in detecting distracted driving. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study is about developing a new way to detect when people are distracted while driving. The researchers used a special kind of artificial intelligence called machine learning to create a model that can quickly and accurately identify distracted driving behaviors. They tested their model using a large dataset of images from State Farm and compared it to other models like VGG16, VGG19, and ResNet. The new model is fast, accurate, and small enough to be used on inexpensive devices, making it a promising solution for detecting distracted driving in real-time. |
Keywords
» Artificial intelligence » Deep learning » Image classification » Machine learning » Object detection » Resnet
