Summary of Noise Filtering Benchmark For Neuromorphic Satellites Observations, by Sami Arja et al.
Noise Filtering Benchmark for Neuromorphic Satellites Observations
by Sami Arja, Alexandre Marcireau, Nicholas Owen Ralph, Saeed Afshar, Gregory Cohen
First submitted to arxiv on: 18 Nov 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 The proposed event-driven noise-filtering algorithms are designed specifically for very sparse scenes, tackling the challenge of noise in event cameras. The paper categorizes algorithms into logical-based and learning-based approaches, benchmarking their performance against 11 state-of-the-art noise-filtering algorithms using signal retention and noise removal accuracy metrics. Additionally, a new high-resolution satellite dataset is introduced with ground truth from a real-world platform under various noise conditions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Event cameras capture brightness changes that offer high temporal resolution, dynamic range, and low power consumption. However, the output often includes background activity noise that can overwhelm signal detection in low-light conditions. Existing algorithms struggle to remove noise in these scenarios due to their design for denser scenes. The paper proposes new event-driven noise-filtering algorithms for very sparse scenes, including logical-based and learning-based approaches. These algorithms are benchmarked against 11 state-of-the-art methods using signal retention and noise removal accuracy metrics. |
