Summary of Enhancing Robustness Of Human Detection Algorithms in Maritime Sar Through Augmented Aerial Images to Simulate Weather Conditions, by Miguel Tjia et al.
Enhancing Robustness of Human Detection Algorithms in Maritime SAR through Augmented Aerial Images to Simulate Weather Conditions
by Miguel Tjia, Artem Kim, Elaine Wynette Wijaya, Hanna Tefara, Kevin Zhu
First submitted to arxiv on: 25 Aug 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 research paper presents a study on improving the accuracy of human detection in maritime Search and Rescue (SAR) operations using YOLO (You Only Look Once) and convolutional neural networks (CNNs). The authors utilize an augmented dataset to train their model, which allows for simulating different weather conditions and lighting scenarios. This approach enables the model to learn to differentiate between various objects, potentially enhancing the efficiency of SAR operations by improving detection accuracy. The study evaluates a robust dataset containing diverse elevations and geological locations, as well as data augmentation, which outperformed non-augmented models in terms of human recall scores (0.891-0.911) with an improvement rate of 3.4% on the YOLOv5l model. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The study aims to improve the accuracy of human detection in maritime SAR operations by training a YOLO model using an augmented dataset and evaluating its performance against a robust set of elevations and geological locations. The results show that models trained on this dataset outperform those without augmentation, with human recall scores ranging from 0.891 to 0.911. |
Keywords
» Artificial intelligence » Data augmentation » Recall » Yolo
