https://github.com/cdjellen/lc-14
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.6%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: CDJellen
- Language: Jupyter Notebook
- Default Branch: main
- Size: 65 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 2
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Aircraft Identification
Satellite imagery provides an invaluable source of near-real-time data on the movement and positioning of assets across the globe. The past two decades have witnessed a dramatic surge in both image resolution and the sheer number of satellite imaging systems. However, this abundance of data has also created a challenge: the volume of imagery far surpasses the capacity for manual review by specialists.
By automating the analysis of satellite imagery, we can extract critical insights, such as the quantity and location of mobile assets like aircraft, which are essential for maintaining situational awareness and information dominance.
In this project, you will develop a model which can identify commercial and non-commercial aircraft in satellite images.
This capstone project challenges you to develop this model using a two-phased approach:
Commercial Aircraft Detection
The first phase focuses on building a robust model capable of accurately locating commercial aircraft within satellite images of airports. Your model will be rigorously validated using a diverse set of similar airport images, ensuring its accuracy and generalization capabilities.
Non-Commercial Aircraft Counting
In the second phase, the focus shifts to non-commercial aircraft. You'll be provided with a limited dataset of satellite images featuring non-commercial aircraft, along with their corresponding labels. Leveraging the model developed in phase one and employing transfer learning techniques, you'll fine-tune your model to accurately count the number of non-commercial aircraft present in a collection of similar airfield images.
The Customer
Imagine the "customer" as a national security agency tasked with monitoring airfields and assessing potential threats. You will develop a model capable of accurately detecting and counting aircraft, contributing to enhanced national security through automated aerial surveillance.
Owner
- Name: Chris Jellen
- Login: CDJellen
- Kind: user
- Location: Seattle, WA
- Company: @Microsoft
- Website: cdjellen.com
- Repositories: 5
- Profile: https://github.com/CDJellen
Cloud software engineering at Microsoft. Cross-team data solutions focused on observability, reliability, strategic planning, and automation.
GitHub Events
Total
- Push event: 18
- Public event: 1
- Pull request event: 15
- Fork event: 2
- Create event: 7
Last Year
- Push event: 18
- Public event: 1
- Pull request event: 15
- Fork event: 2
- Create event: 7
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 1
- Total pull requests: 6
- Average time to close issues: 2 minutes
- Average time to close pull requests: 1 minute
- Total issue authors: 1
- Total pull request authors: 1
- Average comments per issue: 0.0
- Average comments per pull request: 0.0
- Merged pull requests: 6
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 1
- Pull requests: 6
- Average time to close issues: 2 minutes
- Average time to close pull requests: 1 minute
- Issue authors: 1
- Pull request authors: 1
- Average comments per issue: 0.0
- Average comments per pull request: 0.0
- Merged pull requests: 6
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
- CDJellen (6)
Top Labels
Issue Labels
Pull Request Labels
Dependencies
- Pillow *
- albumentations *
- boto3 *
- matplotlib *
- mlflow *
- opencv-python *
- scikit-learn *
- shapely *
- torch *
- torchvision *
- tqdm *