diff --git a/backend/app/tasks/vision.py b/backend/app/tasks/vision.py
index f40f574..796f48b 100644
--- a/backend/app/tasks/vision.py
+++ b/backend/app/tasks/vision.py
@@ -134,8 +134,66 @@ async def _ocr_photo_async(photo_id: str):
 
 @shared_task(name='detect_objects', queue='vision')
 def detect_objects(photo_id: str):
-    """Detect objects in a photo — implemented in PR6."""
-    return {'status': 'not_implemented'}
+    """Detect objects in a photo, create Tag(kind=object) rows, and
+    link via photo_tags with confidence/bbox/source."""
+    if not settings.vision.enabled or not settings.vision.detector.enabled:
+        return {'status': 'skipped', 'reason': 'detection disabled'}
+    return asyncio.run(_detect_objects_async(photo_id))
+
+
+async def _detect_objects_async(photo_id: str):
+    image = _load_thumb(photo_id, "medium")  # 640px
+    if image is None:
+        return {'status': 'error', 'message': 'thumbnail not found'}
+
+    from app.services.vision.registry import registry
+    detector = registry.get_detector()
+    detections = detector.detect(image)
+
+    if not detections:
+        logger.info("No objects detected for photo %s", photo_id)
+        return {'status': 'success', 'photo_id': photo_id, 'objects': 0}
+
+    from app.models.tags import Tag, photo_tags
+
+    source_name = "vision:yolov8n"
+
+    async with AsyncSessionLocal() as session:
+        # Wipe previous detection results for this photo from this model
+        await session.execute(
+            delete(photo_tags).where(
+                photo_tags.c.photo_id == photo_id,
+                photo_tags.c.source == source_name,
+            )
+        )
+
+        for det in detections:
+            # Find or create the object tag
+            result = await session.execute(
+                select(Tag).where(Tag.name == det.label, Tag.kind == 'object')
+            )
+            tag = result.scalar_one_or_none()
+            if not tag:
+                tag = Tag(name=det.label, kind='object', source=source_name)
+                session.add(tag)
+                await session.flush()  # get tag.id
+
+            # Insert photo_tags association with ML metadata
+            await session.execute(
+                photo_tags.insert().values(
+                    photo_id=photo_id,
+                    tag_id=tag.id,
+                    confidence=det.confidence,
+                    bbox=det.bbox,
+                    source=source_name,
+                )
+            )
+
+        await session.commit()
+
+    labels = [d.label for d in detections]
+    logger.info("Detected %d objects in photo %s: %s", len(detections), photo_id, labels)
+    return {'status': 'success', 'photo_id': photo_id, 'objects': len(detections)}
 
 
 @shared_task(name='extract_faces', queue='vision')