Fixes (#18220)

* Add option to not trim clip

* Improve API

* Update snapshot for new best objects

* Fix missing strings

* Convert to separate key

* Always include bounding box on snapshots

* improve autotracking relative zooming time calculation

* update proxy docs to note the need for comma separated header roles

* Add count translation

* tracked object lifecycle i18n fix

* update speed estimation docs

* clarity

* Re-initialize onvif information when toggling camera on live view

* Move time ago to card info and add face area

* Clarify face recognition docs

* Increase minimum face recognition area

* use clipFrom to in vod module endpoint to start at the correct time

* Cleanup media api

* Don't change duration

* Use search detail dialog for face library

* Move to segment based

* Cleanup

* Add back duration modification

* clean up docs

---------

Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>

frigate/api/media.py

@@ -593,10 +593,12 @@ def recording_clip(
         clip: Recordings
         for clip in recordings:
             file.write(f"file '{clip.path}'\n")
+
             # if this is the starting clip, add an inpoint
             if clip.start_time < start_ts:
                 file.write(f"inpoint {int(start_ts - clip.start_time)}\n")
-            # if this is the ending clip, add an outpoint
+
+            # if this is the ending clip and end trim is enabled, add an outpoint
             if clip.end_time > end_ts:
                 file.write(f"outpoint {int(end_ts - clip.start_time)}\n")
 
@@ -641,7 +643,12 @@ def recording_clip(
 @router.get("/vod/{camera_name}/start/{start_ts}/end/{end_ts}")
 def vod_ts(camera_name: str, start_ts: float, end_ts: float):
     recordings = (
-        Recordings.select(Recordings.path, Recordings.duration, Recordings.end_time)
+        Recordings.select(
+            Recordings.path,
+            Recordings.duration,
+            Recordings.end_time,
+            Recordings.start_time,
+        )
         .where(
             Recordings.start_time.between(start_ts, end_ts)
             | Recordings.end_time.between(start_ts, end_ts)
@@ -661,14 +668,19 @@ def vod_ts(camera_name: str, start_ts: float, end_ts: float):
         clip = {"type": "source", "path": recording.path}
         duration = int(recording.duration * 1000)
 
-        # Determine if we need to end the last clip early
+        # adjust start offset if start_ts is after recording.start_time
+        if start_ts > recording.start_time:
+            inpoint = int((start_ts - recording.start_time) * 1000)
+            clip["clipFrom"] = inpoint
+            duration -= inpoint
+
+        # adjust end if recording.end_time is after end_ts
         if recording.end_time > end_ts:
             duration -= int((recording.end_time - end_ts) * 1000)
 
-            if duration == 0:
-                # this means the segment starts right at the end of the requested time range
-                # and it does not need to be included
-                continue
+        if duration <= 0:
+            # skip if the clip has no valid duration
+            continue
 
         if 0 < duration < max_duration_ms:
             clip["keyFrameDurations"] = [duration]

frigate/camera/state.py

@@ -282,9 +282,13 @@ class CameraState:
             }
             new_obj.thumbnail_data = thumbnail_data
             tracked_objects[id].thumbnail_data = thumbnail_data
-            self.best_objects[new_obj.obj_data["label"]] = new_obj
+            object_type = new_obj.obj_data["label"]
+            self.best_objects[object_type] = new_obj
 
             # call event handlers
+            for c in self.callbacks["snapshot"]:
+                c(self.name, self.best_objects[object_type], frame_name)
+
             for c in self.callbacks["start"]:
                 c(self.name, new_obj, frame_name)
 

frigate/config/classification.py

@@ -78,7 +78,7 @@ class FaceRecognitionConfig(FrigateBaseModel):
         le=1.0,
     )
     min_area: int = Field(
-        default=500, title="Min area of face box to consider running face recognition."
+        default=750, title="Min area of face box to consider running face recognition."
     )
     save_attempts: int = Field(
         default=100, ge=0, title="Number of face attempts to save in the train tab."
@@ -91,7 +91,7 @@ class FaceRecognitionConfig(FrigateBaseModel):
 class CameraFaceRecognitionConfig(FrigateBaseModel):
     enabled: bool = Field(default=False, title="Enable face recognition.")
     min_area: int = Field(
-        default=500, title="Min area of face box to consider running face recognition."
+        default=750, title="Min area of face box to consider running face recognition."
     )
 
     model_config = ConfigDict(extra="forbid", protected_namespaces=())

frigate/ptz/autotrack.py

@@ -1171,7 +1171,20 @@ class PtzAutoTracker:
             zoom_predicted_movement_time = 0
 
             if np.any(average_velocity):
-                zoom_predicted_movement_time = abs(zoom) * self.zoom_time[camera]
+                # Calculate the intended change in zoom level
+                zoom_change = (1 - abs(zoom)) * (1 if zoom >= 0 else -1)
+
+                # Calculate new zoom level and clamp to [0, 1]
+                new_zoom = max(
+                    0, min(1, self.ptz_metrics[camera].zoom_level.value + zoom_change)
+                )
+
+                # Calculate the actual zoom distance
+                zoom_distance = abs(
+                    new_zoom - self.ptz_metrics[camera].zoom_level.value
+                )
+
+                zoom_predicted_movement_time = zoom_distance * self.zoom_time[camera]
 
                 zoom_predicted_box = (
                     predicted_box
@@ -1188,7 +1201,7 @@ class PtzAutoTracker:
                 tilt = (0.5 - (centroid_y / camera_height)) * 2
 
             logger.debug(
-                f"{camera}: Zoom amount: {zoom}, zoom predicted time: {zoom_predicted_movement_time}, zoom predicted box: {tuple(zoom_predicted_box)}"
+                f"{camera}: Zoom amount: {zoom}, zoom distance: {zoom_distance}, zoom predicted time: {zoom_predicted_movement_time}, zoom predicted box: {tuple(zoom_predicted_box)}"
             )
 
         self._enqueue_move(camera, obj.obj_data["frame_time"], pan, tilt, zoom)