Notes from the watch floor
Blog
How to tell a scheduled drill from a real activity surgeWhy one VHR pass can't separate a routine exercise cycle from a genuine surge, and what a recurring-pattern baseline shows that a single look can't.
What is denial and deception in satellite imagery analysis?What denial and deception mean in satellite imagery analysis, and why the real D&D indicators show up across repeat passes, not a single frame.
Change detection vs. anomaly detection for imagery analystsChange detection and anomaly detection solve different problems in imagery review. A breakdown of when to use each, and why baselines matter.
- How many days of imagery before a site baseline is reliable
How many days of VHR imagery it takes before a site baseline stops moving and starts catching real deviations.
How to set alert thresholds for site change detectionA working method for tuning anomaly alerts against a real site baseline, so fewer false positives clog the imagery review queue.
- Seasonal change vs. real anomaly: a field guide for analysts
A field guide for imagery analysts on separating seasonal drift and shadow artifacts from genuine site anomalies, using a multi-pass baseline.