Sync vehicle-detection from metro-analytics-catalog

README.md

@@ -202,10 +202,10 @@ Detected vehicles: 1
 ### DLStreamer Sample
 
 The pipeline below runs the FP16 YOLO26 detector on the sample video via
-`gvadetect`, filters detections to vehicle classes in a buffer probe using
-the DLStreamer Python bindings (`gstgva.VideoFrame`), overlays bounding boxes,
-saves the annotated result to `output_dlstreamer.mp4`, and prints the vehicle count per
-frame.
+`gvadetect`, filters detections to vehicle classes using the DLStreamer
+Python bindings (`gstgva.VideoFrame`), draws only vehicle bounding boxes
+with OpenCV, saves the annotated result to `output_dlstreamer.mp4`, and
+prints the vehicle count per frame.
 
 > **Notes on running this sample:**
 >
@@ -222,10 +222,13 @@ frame.
 >   ```
 
 ```python
+import subprocess
+
+import cv2
+import numpy as np
 import gi
 
 gi.require_version("Gst", "1.0")
-gi.require_version("GstVideo", "1.0")
 from gi.repository import Gst
 from gstgva import VideoFrame
 
@@ -233,6 +236,10 @@ Gst.init(None)
 
 INPUT_VIDEO = "test_video.mp4"
 VEHICLE_LABELS = {"car", "motorcycle", "bus", "truck"}
+COLORS = {
+    "car": (0, 255, 0), "motorcycle": (255, 128, 0),
+    "bus": (0, 128, 255), "truck": (128, 0, 255),
+}
 
 # For CPU: change device=GPU to device=CPU.
 # For NPU: change device=GPU to device=NPU (batch-size=1, nireq=4 recommended).
@@ -242,36 +249,73 @@ pipeline_str = (
     "gvadetect model=yolo26n_openvino_model/yolo26n.xml "
     "device=GPU "
     "threshold=0.4 ! queue ! "
-    "gvawatermark ! videoconvert ! video/x-raw,format=I420 ! "
-    "openh264enc ! h264parse ! "
-    "mp4mux ! filesink name=sink location=output_dlstreamer.mp4"
+    "videoconvert ! video/x-raw,format=BGR ! "
+    "appsink name=sink emit-signals=false sync=false"
 )
 pipeline = Gst.parse_launch(pipeline_str)
+appsink = pipeline.get_by_name("sink")
 
+pipeline.set_state(Gst.State.PLAYING)
 
-def on_buffer(pad, info):
-    buf = info.get_buffer()
-    caps = pad.get_current_caps()
+proc = None
+
+while True:
+    sample = appsink.emit("pull-sample")
+    if sample is None:
+        break
+
+    buf = sample.get_buffer()
+    caps = sample.get_caps()
+    struct = caps.get_structure(0)
+    width = struct.get_value("width")
+    height = struct.get_value("height")
+
+    # Start ffmpeg encoder on the first frame.
+    if proc is None:
+        ok, fps_num, fps_den = struct.get_fraction("framerate")
+        fps = fps_num / fps_den if ok and fps_den > 0 else 30.0
+        proc = subprocess.Popen(
+            ["ffmpeg", "-y", "-f", "rawvideo", "-pix_fmt", "bgr24",
+             "-s", f"{width}x{height}", "-r", str(fps),
+             "-i", "pipe:0", "-c:v", "libx264", "-pix_fmt", "yuv420p",
+             "-movflags", "+faststart", "output_dlstreamer.mp4"],
+            stdin=subprocess.PIPE, stderr=subprocess.DEVNULL,
+        )
+
+    # Read detection metadata and filter to vehicle classes.
     frame = VideoFrame(buf, caps=caps)
-    vehicles = [r for r in frame.regions() if r.label() in VEHICLE_LABELS]
+    vehicles = [(r.label(), r.rect()) for r in frame.regions()
+                if r.label() in VEHICLE_LABELS]
+
+    # Map buffer read-only and copy pixels to a writable numpy array.
+    success, map_info = buf.map(Gst.MapFlags.READ)
+    if not success:
+        continue
+    arr = np.ndarray((height, width, 3), dtype=np.uint8,
+                     buffer=map_info.data).copy()
+    buf.unmap(map_info)
+
+    # Draw vehicle bounding boxes only.
+    for label, rect in vehicles:
+        x1, y1 = int(rect.x), int(rect.y)
+        x2, y2 = int(rect.x + rect.w), int(rect.y + rect.h)
+        color = COLORS.get(label, (0, 255, 0))
+        cv2.rectangle(arr, (x1, y1), (x2, y2), color, 2)
+        cv2.putText(arr, label, (x1, max(y1 - 6, 0)),
+                    cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
+
     if vehicles:
         print(f"Vehicle count: {len(vehicles)}", flush=True)
-        for v in vehicles:
-            print(f"  {v.label()} at ({v.rect().x},{v.rect().y})", flush=True)
-    return Gst.PadProbeReturn.OK
-
+        for label, rect in vehicles:
+            print(f"  {label} at ({int(rect.x)},{int(rect.y)})", flush=True)
 
-sink = pipeline.get_by_name("sink")
-sink_pad = sink.get_static_pad("sink")
-sink_pad.add_probe(Gst.PadProbeType.BUFFER, on_buffer)
+    proc.stdin.write(arr.tobytes())
 
-pipeline.set_state(Gst.State.PLAYING)
-bus = pipeline.get_bus()
-bus.timed_pop_filtered(
-    Gst.CLOCK_TIME_NONE,
-    Gst.MessageType.EOS | Gst.MessageType.ERROR,
-)
 pipeline.set_state(Gst.State.NULL)
+if proc:
+    proc.stdin.close()
+    proc.wait()
+print("Wrote output_dlstreamer.mp4", flush=True)
 ```
 
 #### Expected Output

export_and_quantize.sh

@@ -47,7 +47,7 @@ fi
 echo "--- Downloading sample test video ---"
 if [[ ! -f test_video.mp4 ]]; then
     wget -q -O test_video.mp4 \
-        https://github.com/intel-iot-devkit/sample-videos/raw/master/car-detection.mp4
+        "https://www.pexels.com/download/video/34505889?fps=29.97&h=360&w=640"
     echo "Downloaded: test_video.mp4"
 else
     echo "Already present: test_video.mp4"