Summary of Using Deep Neural Networks to Quantify Parking Dwell Time, by Marcelo Eduardo Marques Ribas (1) et al.
Using Deep Neural Networks to Quantify Parking Dwell Time
by Marcelo Eduardo Marques Ribas, Heloisa Benedet Mendes, Luiz Eduardo Soares de Oliveira, Luiz Antonio Zanlorensi, Paulo Ricardo Lisboa de Almeida
First submitted to arxiv on: 31 Oct 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: 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 This paper proposes a method to automatically determine individual car dwell times from images in smart cities. The approach combines two deep neural networks: one for classifying parking space status as occupied or empty, and another Siamese network that checks if the parked car is the same across consecutive images. The authors evaluate their system using an experimental protocol involving cross-dataset scenarios, achieving 75% perfect dwell time predictions when a perfect classifier is used. However, they note a significant drop in prediction quality (49%) when using a real-world classifier, highlighting the impact of classifier accuracy on the overall system’s performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine trying to figure out how long someone stayed parked in a spot in a smart city. That can be hard! But this research paper shows how we can use special computer networks to help us do just that. It uses two types of networks: one to say if the parking space is empty or full, and another to check if the same car is there from one picture to the next. The scientists tested their idea and found it works really well when they use perfect information, but not so much when they use real-world data. This means we need better ways to identify what’s going on in those parking spaces. |
Keywords
» Artificial intelligence » Siamese network
