Summary of Deep Transformer Network For Monocular Pose Estimation Of Ship-based Uav, by Maneesha Wickramasuriya et al.
Deep Transformer Network for Monocular Pose Estimation of Ship-Based UAV
by Maneesha Wickramasuriya, Taeyoung Lee, Murray Snyder
First submitted to arxiv on: 13 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Robotics (cs.RO); Image and Video Processing (eess.IV)
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 introduces a deep transformer network that estimates the relative 6D pose of an Unmanned Aerial Vehicle (UAV) with respect to a ship using monocular images. The model is trained on a synthetic dataset of ship images annotated with 2D keypoints of multiple ship parts, and then integrates these estimates using Bayesian fusion. Tested on both synthetic data and in-situ flight experiments, the method demonstrates robustness and accuracy across various lighting conditions. The position estimation error is approximately 0.8% for synthetic data and 1.0% for flight experiments. This method has potential applications for ship-based autonomous UAV landing and navigation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper uses a special kind of computer model to figure out where a drone (UAV) is in relation to a ship, based on what it can see from just one camera. They made up some fake pictures of ships with lots of details marked, trained the model on those, and then tested it with real-life videos. The results are really good! It’s like having a super accurate GPS for drones that can land and take off from ships. |
Keywords
» Artificial intelligence » Synthetic data » Transformer
