Summary of Real-time Pedestrian Detection on Iot Edge Devices: a Lightweight Deep Learning Approach, by Muhammad Dany Alfikri et al.
Real-Time Pedestrian Detection on IoT Edge Devices: A Lightweight Deep Learning Approach
by Muhammad Dany Alfikri, Rafael Kaliski
First submitted to arxiv on: 24 Sep 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computer Vision and Pattern Recognition (cs.CV); Networking and Internet Architecture (cs.NI)
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 a novel approach to improving computer vision-based pedestrian detection in intelligent transportation systems. It highlights the importance of addressing latency and data transfer speed limitations in real-time applications, particularly when life-loss is at stake. The authors propose leveraging edge servers, which offer localized computing and storage resources, as a potential solution. To overcome processing power limitations, they employ lightweight deep learning techniques, utilizing compressed deep neural network (DNN) models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper explores how to make computer vision work better in traffic systems. It shows that current systems can’t handle lots of data quickly enough, which is a big problem when safety is at stake. The solution involves using special computers called edge servers that are closer to where the data comes from. These edge servers need smart ways to process information, so the paper suggests using lightweight versions of deep learning models. |
Keywords
» Artificial intelligence » Deep learning » Neural network
