Summary of Impact Of Video Compression Artifacts on Fisheye Camera Visual Perception Tasks, by Madhumitha Sakthi et al.
Impact of Video Compression Artifacts on Fisheye Camera Visual Perception Tasks
by Madhumitha Sakthi, Louis Kerofsky, Varun Ravi Kumar, Senthil Yogamani
First submitted to arxiv on: 25 Mar 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 This paper explores the use of lossy video compression on wide FOV fisheye camera images, which are commonly used in autonomous driving systems. The goal is to determine if lossy compression artifacts impact the performance of perception algorithms, such as 3D object detection tasks. To address this, the authors propose a radial distortion-aware zonal metric for evaluating the quality of compressed images. Additionally, they present a novel method for estimating affine mode parameters of the latest VVC codec and identify areas for improvement in video codecs specifically designed for fisheye imagery. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using special cameras called fisheye cameras to help self-driving cars see better. Fisheye cameras take wide-angle pictures that are important for detecting objects. The problem is that these images need to be stored and transmitted, which requires a lot of data space. To solve this, the authors looked at how well video compression works on fisheye camera images. They tested different ways of compressing the images and found that it’s possible to do lossy compression without hurting the performance of the computer vision algorithms. |
Keywords
» Artificial intelligence » Object detection
