Sync object-detection from metro-analytics-catalog

README.md

@@ -220,7 +220,9 @@ from gstgva import VideoFrame
 
 Gst.init(None)
 
-# For GPU: change device=CPU to device=GPU and add vapostproc after decodebin.
+# For GPU: change device=CPU to device=GPU, add vapostproc !
+# video/x-raw(memory:VASurface) after jpegdec, and set
+# pre-process-backend=vaapi-surface-sharing on gvadetect.
 # For NPU: change device=CPU to device=NPU (batch-size=1 recommended).
 pipeline_str = (
     "filesrc location=test.jpg ! jpegdec ! videoconvert ! "
@@ -258,7 +260,7 @@ pipeline.set_state(Gst.State.NULL)
 **Device targets:**
 
 - `device=CPU` -- default in the sample code.
-- `device=GPU` -- add `vapostproc` after `decodebin` for zero-copy color conversion.
+- `device=GPU` -- add `vapostproc ! video/x-raw(memory:VASurface)` after `jpegdec` and set `pre-process-backend=vaapi-surface-sharing` on `gvadetect`.
 - `device=NPU` -- use `batch-size=1` and `nireq=4` for best NPU utilization.
 
 ---