perf(axelera): greedy NMS via cv2.dnn.NMSBoxes

Replace the pure-Python O(n^2) _nms_xyxy loop with the framework's own
C++ NMS (xyxy -> xywh first, same as frigate.util.model). Same contract:
kept indices in descending score order; empty-safe. Removes a per-frame
CPU hot spot on dense daytime frames without changing decode results.

frigate/detectors/plugins/axelera.py

@@ -174,28 +174,39 @@ def _find_model_json(where: str) -> str:
     )
 
 
-def _nms_xyxy(boxes, scores, iou_threshold: float) -> list:
-    """Classic greedy NMS on xyxy boxes. Returns kept indices (desc score)."""
+def _nms_xyxy(boxes, scores, iou_threshold: float) -> np.ndarray:
+    """Greedy NMS on xyxy boxes via cv2.dnn.NMSBoxes (C++, GIL-free).
+
+    Returns kept indices in descending score order, same contract as the
+    previous pure-Python loop but without the O(n^2) worst case on dense
+    frames (daytime, multiple motion regions at 48 fps offered).
+    """
     if len(boxes) == 0:
-        return []
-    x1, y1, x2, y2 = boxes[:, 0], boxes[:, 1], boxes[:, 2], boxes[:, 3]
-    areas = np.maximum(0, x2 - x1) * np.maximum(0, y2 - y1)
-    order = scores.argsort()[::-1]
-    keep = []
-    while order.size > 0:
-        i = order[0]
-        keep.append(int(i))
-        if order.size == 1:
-            break
-        xx1 = np.maximum(x1[i], x1[order[1:]])
-        yy1 = np.maximum(y1[i], y1[order[1:]])
-        xx2 = np.minimum(x2[i], x2[order[1:]])
-        yy2 = np.minimum(y2[i], y2[order[1:]])
-        inter = np.maximum(0, xx2 - xx1) * np.maximum(0, yy2 - yy1)
-        union = areas[i] + areas[order[1:]] - inter
-        ovr = np.where(union > 0, inter / np.maximum(union, 1e-9), 0)
-        order = order[1:][ovr <= iou_threshold]
-    return keep
+        return np.array([], dtype=np.int64)
+    x1 = boxes[:, 0]
+    y1 = boxes[:, 1]
+    xywh = np.stack(
+        [
+            x1,
+            y1,
+            np.maximum(0, boxes[:, 2] - x1),
+            np.maximum(0, boxes[:, 3] - y1),
+        ],
+        axis=1,
+    )
+    indices = cv2.dnn.NMSBoxes(
+        xywh.tolist(),
+        [float(s) for s in scores],
+        # inputs are already filtered above CONF_THRESHOLD by the caller
+        score_threshold=0.0,
+        nms_threshold=float(iou_threshold),
+    )
+    if len(indices) == 0:
+        return np.array([], dtype=np.int64)
+    if isinstance(indices, np.ndarray):
+        return indices.reshape(-1).astype(np.int64)
+    # OpenCV versions that return a (N, 1) list of nested lists
+    return np.asarray(indices, dtype=np.int64).reshape(-1)
 
 
 def _read_model_manifest(model_dir: str) -> dict: