Summary of N-drivermotion: Driver Motion Learning and Prediction Using An Event-based Camera and Directly Trained Spiking Neural Networks on Loihi 2, by Hyo Jong Chung et al.
N-DriverMotion: Driver motion learning and prediction using an event-based camera and directly trained spiking neural networks on Loihi 2
by Hyo Jong Chung, Byungkon Kang, Yoonseok Yang
First submitted to arxiv on: 23 Aug 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 novel system is introduced for learning and predicting driver motions, comprising an event-based camera and spiking neural networks (SNNs). The system is effective in training and predicting gestures, with a proposed simplified four-layer convolutional SNN achieving comparable accuracy to recent gesture recognition systems. A high-resolution dataset, N-DriverMotion, is collected and used to train the SNNs, consisting of 13 driver motion categories classified by direction, illumination, and participant. The system’s efficiency in training and predicting driver motions enables real-time inference on high-resolution event-based streams, making it suitable for developing safer and more efficient driver monitoring systems for autonomous vehicles or edge devices. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper presents a new way to recognize driver movements using a special camera that captures events instead of regular images. This helps create a large dataset of driver motions, which is then used to train a neural network that can predict the driver’s actions. The system works well and is similar in accuracy to other methods already developed. The dataset and neural network can be used to make autonomous vehicles or devices safer and more efficient. |
Keywords
» Artificial intelligence » Gesture recognition » Inference » Neural network
