You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
|`id`| string (UUID) | Persistent track identifier assigned by the controller |
192
-
|`type`| string | Object type label; same value as `category` (e.g. `"person"`) |
193
-
|`category`| string | Object class label (e.g. `"person"`) |
194
-
|`confidence`| number | Inference confidence of the most recent contributing detection |
195
-
|`translation`| array[3] of number | 3D world position (`x`, `y`, `z`) in metres |
196
-
|`size`| array[3] of number | 3D object dimensions (`x`, `y`, `z`) in metres |
197
-
|`velocity`| array[3] of number | Velocity vector (`x`, `y`, `z`) in metres per second |
198
-
|`rotation`| array[4] of number | Orientation quaternion |
199
-
|`visibility`| array of string | Camera IDs currently observing this object |
200
-
|`regions`| object | Map of region/sensor IDs to membership metadata. By default this is `{id: {entered: timestamp}}`. In region-scoped outputs, objects currently inside a region also include a live dwell time as `{id: {entered: timestamp, dwell: seconds}}`. |
201
-
|`sensors`| object | Map of sensor IDs to timestamped readings (`{id: [[timestamp, value], ...]}`) |
|`id`| string (UUID) | Persistent track identifier assigned by the controller |
192
+
|`type`| string | Object type label; same value as `category` (e.g. `"person"`) |
193
+
|`category`| string | Object class label (e.g. `"person"`) |
194
+
|`confidence`| number | Inference confidence of the most recent contributing detection |
195
+
|`translation`| array[3] of number | 3D world position (`x`, `y`, `z`) in metres |
196
+
|`size`| array[3] of number | 3D object dimensions (`x`, `y`, `z`) in metres |
197
+
|`velocity`| array[3] of number | Velocity vector (`x`, `y`, `z`) in metres per second |
198
+
|`rotation`| array[4] of number | Orientation quaternion |
199
+
|`visibility`| array of string | Camera IDs currently observing this object |
200
+
|`regions`| object | Map of region/sensor IDs to membership metadata. By default this is `{id: {entered: timestamp}}`. In region-scoped outputs, objects currently inside a region also include a live dwell time as `{id: {entered: timestamp, dwell: seconds}}`. |
201
+
|`sensors`| object | Map of sensor IDs to timestamped readings (`{id: [[timestamp, value], ...]}`) |
202
202
|`similarity`| number or null | Similarity/distance value to the matched ReID embedding in VDMS, carried from VDMS `_distance`; interpretation depends on configured `similarity_metric` (for `COSINE`, SceneScape uses VDMS `IP` with higher-is-better semantics; for `L2`-style metrics, lower is better). `null` when ReID is still collecting embeddings, when no database match was found, or when ReID is disabled. |
203
-
|`reid_state`| string | Re-ID processing state for the object. One of: `pending_collection`, `query_no_match`, `matched`, `reid_disabled`|
204
-
|`previous_ids_chain`| array or absent | History of UUID reassignments for this track. Each element is `{"id": "<uuid>", "timestamp": "<ISO 8601>", "similarity_score": <number or null>}`. Present only when the object has been re-identified at least once; omitted otherwise. |
205
-
|`first_seen`| string (ISO 8601) | Timestamp when the track was first created |
206
-
|`metadata`| object | Semantic attributes propagated from camera detections; present when visual analytics (e.g. age, gender, Re-ID) are configured. Same attribute structure as camera input. See note below. |
207
-
|`camera_bounds`| object | Per-camera pixel bounding boxes (`{camera_id: {x, y, width, height, projected}}`) where `projected=false` means detector-provided pixel bbox and `projected=true` means computed projection; may be empty (`{}`) when no camera currently observes the track |
203
+
|`reid_state`| string | Re-ID processing state for the object. One of: `pending_collection`, `query_no_match`, `matched`, `reid_disabled`|
204
+
|`previous_ids_chain`| array or absent | History of UUID reassignments for this track. Each element is `{"id": "<uuid>", "timestamp": "<ISO 8601>", "similarity_score": <number or null>}`. Present only when the object has been re-identified at least once; omitted otherwise. |
205
+
|`first_seen`| string (ISO 8601) | Timestamp when the track was first created |
206
+
|`metadata`| object | Semantic attributes propagated from camera detections; present when visual analytics (e.g. age, gender, Re-ID) are configured. Same attribute structure as camera input. See note below. |
207
+
|`camera_bounds`| object | Per-camera pixel bounding boxes (`{camera_id: {x, y, width, height, projected}}`) where `projected=false` means detector-provided pixel bbox and `projected=true` means computed projection; may be empty (`{}`) when no camera currently observes the track |
208
208
209
209
> **Note on `metadata` in track objects**: Each attribute follows the structure
210
210
> `{label, model_name, confidence?}` — identical to [Semantic Metadata Fields](#semantic-metadata-fields)
0 commit comments