Summary of Deep Pulse-signal Magnification For Remote Heart Rate Estimation in Compressed Videos, by Joaquim Comas et al.
Deep Pulse-Signal Magnification for remote Heart Rate Estimation in Compressed Videos
by Joaquim Comas, Adria Ruiz, Federico Sukno
First submitted to arxiv on: 4 May 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 The proposed novel approach in this paper addresses the impact of video compression on remote photoplethysmography (rPPG) estimation. By leveraging a pulse-signal magnification transformation, the model adapts compressed videos to an uncompressed data domain, effectively magnifying the rPPG signal. The approach is validated through exhaustive evaluations on two publicly available datasets, UCLA-rPPG and UBFC-rPPG, at several compression rates. Additionally, the robustness of the method is assessed on two highly compressed datasets, MAHNOB-HCI and COHFACE, demonstrating outstanding heart rate estimation results. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper solves a problem with using video to measure heart rates from a distance. When videos are compressed, it makes it harder to get accurate readings. The solution is a special way of changing the compressed video back into an uncompressed one, which makes it easier to read the heart rate signal. The method was tested on several datasets and showed great results. |
