How jesika-23/hackcult_aquashield works
AquaShield is a Streamlit prototype for AI-assisted underwater and sonar-style image review. Users upload an image, configure a confidence threshold, and receive YOLO detections with visual annotations and supporting quality, shadow, anomaly, and priority analysis. The app also supports optional preprocessing, reports, manually entered location visualization, session history, and human feedback logging. The graph reflects documented capabilities; unsampled app wiring is linked only where the README or source index supports it. Priority and shadow analysis are prototype heuristics, not validated risk or sonar-physics models.
Main entry points: app.py Streamlit application · inference.py YOLO detection · feedback.py Feedback logging · preprocess.py Image preprocessing
Components 14
Review interface
- Streamlit application
app.py
Image analysis
- Image preprocessing
utils/preprocess.py - YOLO detection
utils/inference.py - YOLO weights
model/best.pt - Image quality
utils/quality.py - Shadow heuristics
utils/shadow.py - Visual anomalies
utils/inference.py
Review results
- Priority scoring
utils/priority.py - Analysis report
utils/report.py - Location map
utils/map_view.py
History and feedback
- Session history
utils/history.py - Feedback logging
utils/feedback.py - Feedback CSV
feedback_log.csv
Other components
- Human reviewer
Connections 13
- Human reviewer → Streamlit application: uploads and reviews
README.md - Streamlit application → Image preprocessing: optionally enhances
README.md - Streamlit application → YOLO detection: runs detection
README.md - YOLO detection → YOLO weights: uses weights
utils/inference.py - Streamlit application → Image quality: assesses quality
README.md - Streamlit application → Shadow heuristics: analyzes shadows
README.md - Streamlit application → Visual anomalies: checks image differences
utils/inference.py - Streamlit application → Priority scoring: scores detections
app.py - Streamlit application → Analysis report: generates report
README.md - Streamlit application → Location map: shows locations
README.md - Streamlit application → Session history: records session history
README.md - Streamlit application → Feedback logging: saves reviewer feedback
app.py - Feedback logging → Feedback CSV: appends rows
utils/feedback.py