Detections, events and observations
These three words appear all over the app and they mean different things. Mixing them up is the most common reason two numbers do not match.
Detection
One box around one animal, in one file. A photo with three deer has three detections.
Each detection has a species label and a confidence score. A detection is the smallest unit. It is what you correct on the Labels page.
Event
Files from the same camera, taken close together in time. AddaxAI groups them for you.
The gap that starts a new event is the independence interval. It is 30 minutes by default. So if a deer walks past and the camera fires 12 times in one minute, that is one event, not 12.
Events only exist in projects. A folder run does not group anything.
Observation
One species inside one event, with a count.
If an event holds 8 photos of deer and 2 of a fox, that is one event with two observations: deer and fox.
How the count is worked out
The count for an observation is the highest number of that species visible in any single photo of the event. This is often called MaxN.
An example. A deer walks past and the camera takes 5 photos:
| Photo | Deer visible |
|---|---|
| 1 | 1 |
| 2 | 2 |
| 3 | 2 |
| 4 | 1 |
| 5 | 0 |
The count is 2, not 6. Two deer were there. Counting every photo would count the same animal again and again.
If you confirm a different number yourself, your number is used instead. See confidence and verification.
Why this matters
Say one deer triggers your camera 40 times in an afternoon:
- 40 detections
- 1 event
- 1 observation, count 1
If you report detections you will say you saw 40 deer. You saw one. For almost all ecological work, use observations.
Where each number appears
| Number | Where you see it |
|---|---|
| Detections | Labels page, detections export |
| Events | Counts page, dashboard tile |
| Observations | Dashboard, map, charts, observations export |
The dashboard and the map use observations. The Labels page works on detections, because that is what you correct.