Expose more annotation params for Roboflow processors

Author: dangusev

plugins/roboflow/vision_agents/plugins/roboflow/roboflow_cloud_processor.py

@@ -70,12 +70,16 @@ async def on_detection_completed(event: roboflow.DetectionCompletedEvent):
             Example: ["person", "sports ball"]
             Verify that the classes a supported by the given model.
             Default - None (all classes are detected).
+        client: optional custom instance of `inference_sdk.InferenceHTTPClient`.
         annotate: if True, annotate the detected objects with boxes and labels.
             Default - True.
         dim_background_factor: how much to dim the background around detected objects from 0 to 1.0.
             Effective only when annotate=True.
             Default - 0.0 (no dimming).
-        client: optional custom instance of `inference_sdk.InferenceHTTPClient`.
+        annotate_text_scale: annontation text scale. Default - 0.75.
+        annotate_text_padding: annotation text padding. Default - 1.0.
+        annotate_box_thickness: annotation box thickness. Default - 2.
+        annotate_text_position: annotation text position. Default - `sv.Position.TOP_CENTER`.
 
     Examples:
         Example usage:
@@ -104,10 +108,14 @@ def __init__(
         api_url: Optional[str] = None,
         conf_threshold: float = 0.5,
         fps: int = 5,
-        annotate: bool = True,
         classes: Optional[list[str]] = None,
-        dim_background_factor: float = 0.0,
         client: Optional[InferenceHTTPClient] = None,
+        annotate: bool = True,
+        dim_background_factor: float = 0.0,
+        annotate_text_scale: float = 0.75,
+        annotate_text_padding: int = 1,
+        annotate_box_thickness: int = 2,
+        annotate_text_position: sv.Position = sv.Position.TOP_CENTER,
     ):
         super().__init__(interval=0, receive_audio=False, receive_video=True)
 
@@ -139,6 +147,10 @@ def __init__(
         self.fps = fps
         self.dim_background_factor = max(0.0, dim_background_factor)
         self.annotate = annotate
+        self._annotate_text_scale = annotate_text_scale
+        self._annotate_text_padding = annotate_text_padding
+        self._annotate_box_thickness = annotate_box_thickness
+        self._annotate_text_position = annotate_text_position
 
         self._events: Optional[EventManager] = None
         self._client.configure(
@@ -237,7 +249,14 @@ async def _process_frame(self, frame: av.VideoFrame):
         if self.annotate:
             # Annotate frame with detections
             annotated_image = annotate_image(
-                image, detections, classes, dim_factor=self.dim_background_factor
+                image,
+                detections,
+                classes,
+                dim_factor=self.dim_background_factor,
+                text_scale=self._annotate_text_scale,
+                text_position=self._annotate_text_position,
+                text_padding=self._annotate_text_padding,
+                box_thickness=self._annotate_box_thickness,
             )
 
             # Convert back to av.VideoFrame

plugins/roboflow/vision_agents/plugins/roboflow/roboflow_local_processor.py

@@ -89,13 +89,17 @@ async def on_detection_completed(event: roboflow.DetectionCompletedEvent):
             Example: ["person", "sports ball"]
             Verify that the classes a supported by the given model.
             Default - None (all classes are detected).
+        model: optional instance of `RFDETRModel` to be used for detections.
+            Use it provide a model of choosing with custom parameters.
         annotate: if True, annotate the detected objects with boxes and labels.
             Default - True.
         dim_background_factor: how much to dim the background around detected objects from 0 to 1.0.
             Effective only when annotate=True.
             Default - 0.0 (no dimming).
-        model: optional instance of `RFDETRModel` to be used for detections.
-            Use it provide a model of choosing with custom parameters.
+        annotate_text_scale: annontation text scale. Default - 0.75.
+        annotate_text_padding: annotation text padding. Default - 1.0.
+        annotate_box_thickness: annotation box thickness. Default - 2.
+        annotate_text_position: annotation text position. Default - `sv.Position.TOP_CENTER`.
     """
 
     name = "roboflow_local"
@@ -106,9 +110,13 @@ def __init__(
         conf_threshold: float = 0.5,
         fps: int = 10,
         classes: Optional[list[str]] = None,
+        model: Optional[RFDETR] = None,
         annotate: bool = True,
         dim_background_factor: float = 0.0,
-        model: Optional[RFDETR] = None,
+        annotate_text_scale: float = 0.75,
+        annotate_text_padding: int = 1,
+        annotate_box_thickness: int = 2,
+        annotate_text_position: sv.Position = sv.Position.TOP_CENTER,
     ):
         super().__init__(interval=0, receive_audio=False, receive_video=True)
 
@@ -153,6 +161,10 @@ def __init__(
             fps=self.fps,
             max_queue_size=self.fps,  # Buffer 1s of the video
         )
+        self._annotate_text_scale = annotate_text_scale
+        self._annotate_text_padding = annotate_text_padding
+        self._annotate_box_thickness = annotate_box_thickness
+        self._annotate_text_position = annotate_text_position
 
     async def process_video(
         self,
@@ -267,6 +279,10 @@ async def _process_frame(self, frame: av.VideoFrame) -> None:
                 detections,
                 classes=self._model.class_names,
                 dim_factor=self.dim_background_factor,
+                text_scale=self._annotate_text_scale,
+                text_position=self._annotate_text_position,
+                text_padding=self._annotate_text_padding,
+                box_thickness=self._annotate_box_thickness,
             )
             # Convert back to av.VideoFrame
             annotated_frame = av.VideoFrame.from_ndarray(annotated_image)

plugins/roboflow/vision_agents/plugins/roboflow/utils.py

@@ -10,6 +10,10 @@ def annotate_image(
     detections: sv.Detections,
     classes: dict[int, str],
     dim_factor: Optional[float] = None,
+    text_scale: float = 0.75,
+    text_padding: int = 1,
+    box_thickness: int = 2,
+    text_position: sv.Position = sv.Position.TOP_CENTER,
 ) -> np.ndarray:
     """
     Draw bounding boxes and labels on frame.
@@ -23,14 +27,16 @@ def annotate_image(
             cv2.rectangle(mask, (x1, y1), (x2, y2), 255, -1)
         image[mask == 0] = (image[mask == 0] * dim_factor).astype(np.uint8)
 
-    boxed_image = sv.BoxAnnotator(thickness=1).annotate(image.copy(), detections)
+    boxed_image = sv.BoxAnnotator(thickness=box_thickness).annotate(
+        image.copy(), detections
+    )
     detected_class_ids: Iterable[int] = (
         detections.class_id if detections.class_id is not None else []
     )
     labels = [classes[class_id] for class_id in detected_class_ids]
     labeled_image = sv.LabelAnnotator(
-        text_position=sv.Position.BOTTOM_CENTER,
-        text_scale=0.25,
-        text_padding=1,
+        text_position=text_position,
+        text_scale=text_scale,
+        text_padding=text_padding,
     ).annotate(boxed_image, detections, labels)
     return labeled_image