Sync face-matching from metro-analytics-catalog

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+expected_output_dlstreamer.gif filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) Intel Corporation.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE

README.md

@@ -0,0 +1,378 @@
+---
+license: mit
+license_link: LICENSE
+library_name: openvino
+pipeline_tag: image-classification
+tags:
+  - openvino
+  - intel
+  - face-detection
+  - face-matching
+  - face-reidentification
+  - edge-ai
+  - metro
+  - dlstreamer
+language:
+  - en
+---
+
+# Face Matching
+
+| Property | Value |
+|---|---|
+| **Category** | Face Detection + One-to-One Verification |
+| **Base Model** | [face-detection-adas-0001](https://docs.openvino.ai/2024/omz_models_model_face_detection_adas_0001.html) + [face-reidentification-retail-0095](https://docs.openvino.ai/2024/omz_models_model_face_reidentification_retail_0095.html) (Open Model Zoo) |
+| **Source Framework** | Caffe / PyTorch (Open Model Zoo) |
+| **Supported Precisions** | FP32, FP16 |
+| **Inference Engine** | OpenVINO |
+| **Hardware** | CPU, GPU, NPU |
+| **Detected Class(es)** | Human faces (detection) + 256-d face embeddings (matching) |
+
+---
+
+## Overview
+
+Face Matching is a Metro Analytics use case that verifies a specific identity:
+given a reference face image, it locates that person inside a scene that may
+contain several people and highlights only the matching face. Each detected
+face is compared to the reference by cosine similarity of its embedding vector.
+
+It uses the same two-stage pipeline as [facial-recognition](../facial-recognition/):
+
+- **face-detection-adas-0001** -- detects every face in the scene.
+- **face-reidentification-retail-0095** -- computes a 256-d embedding per face.
+
+The difference from full facial recognition is scope: face matching verifies a
+single reference identity and highlights only that person, without maintaining a
+gallery database.
+
+Typical Metro deployments include:
+
+- **Badge Verification** -- compare a live face to a badge photo at entry gates.
+- **Document Verification** -- match a passport or ID photo to the holder.
+- **Duplicate Detection** -- check if two records belong to the same person.
+- **Re-identification Confirmation** -- confirm a person flagged by the search system.
+
+> **Privacy Note:** Face matching involves biometric data.
+> Ensure your deployment complies with applicable privacy regulations
+> (GDPR, BIPA, etc.) and has proper consent mechanisms in place.
+
+---
+
+## Prerequisites
+
+- Python 3.11+
+- [Install OpenVINO](https://docs.openvino.ai/2026/get-started/install-openvino.html) (latest version)
+- [Install Intel DLStreamer](https://docs.openedgeplatform.intel.com/2026.0/edge-ai-libraries/dlstreamer/get_started/install/install_guide_ubuntu.html) (latest version)
+
+Create and activate a Python virtual environment before running the scripts:
+
+```bash
+python3 -m venv .venv --system-site-packages
+source .venv/bin/activate
+```
+
+> **Note:** The `--system-site-packages` flag is required so the virtual
+> environment can access the system-installed OpenVINO and DLStreamer Python
+> packages.
+
+---
+
+## Getting Started
+
+### Download Models
+
+Run the provided script to download the face detection and re-identification
+models from the Open Model Zoo:
+
+```bash
+chmod +x export_and_quantize.sh
+./export_and_quantize.sh
+```
+
+The script downloads `face-detection-adas-0001` and
+`face-reidentification-retail-0095` in FP16, downloads the sample video, and
+captures a reference face image (`face_a.jpg`) of the left subject from it.
+
+### OpenVINO Sample
+
+The sample below verifies identity inside a scene: it loads the captured
+reference image of the subject (`face_a.jpg`, the woman who pauses on the left of
+the sample video), computes its embedding, then reads a frame from the video that
+contains several people. It detects every face in the frame, embeds each one, and
+draws a green box only on the face whose similarity to the reference is highest
+and above the match threshold. Change the `device` string to run on CPU, GPU, or NPU.
+
+```python
+import cv2
+import numpy as np
+import openvino as ov
+
+DETECTION_MODEL = "intel/face-detection-adas-0001/FP16/face-detection-adas-0001.xml"
+REID_MODEL = "intel/face-reidentification-retail-0095/FP16/face-reidentification-retail-0095.xml"
+REFERENCE_IMAGE = "face_a.jpg"  # reference: left subject captured from the video
+SCENE_VIDEO = "test_video.mp4"  # scene containing the reference subject plus others
+SCENE_FRAME = 480               # frame index of the two-person scene (~40s)
+CONF_THRESHOLD = 0.5
+MATCH_THRESHOLD = 0.5
+
+core = ov.Core()
+
+# Change device to "GPU" or "NPU" to run on integrated GPU or NPU.
+det_compiled = core.compile_model(core.read_model(DETECTION_MODEL), "CPU")
+reid_compiled = core.compile_model(core.read_model(REID_MODEL), "CPU")
+
+det_input = det_compiled.input(0)
+det_h, det_w = det_input.shape[2], det_input.shape[3]
+reid_input = reid_compiled.input(0)
+reid_h, reid_w = reid_input.shape[2], reid_input.shape[3]
+
+
+def detect_faces(img):
+    h0, w0 = img.shape[:2]
+    blob = cv2.resize(img, (det_w, det_h))
+    blob = blob.transpose(2, 0, 1)[np.newaxis, ...].astype(np.float32)
+    dets = det_compiled([blob])[det_compiled.output(0)][0][0]
+    faces = []
+    for d in dets:
+        if float(d[2]) < CONF_THRESHOLD:
+            continue
+        x1 = max(0, int(d[3] * w0))
+        y1 = max(0, int(d[4] * h0))
+        x2 = min(w0, int(d[5] * w0))
+        y2 = min(h0, int(d[6] * h0))
+        if x2 > x1 and y2 > y1:
+            faces.append((x1, y1, x2, y2))
+    return faces
+
+
+def get_embedding(img, bbox):
+    x1, y1, x2, y2 = bbox
+    crop = img[y1:y2, x1:x2]
+    blob = cv2.resize(crop, (reid_w, reid_h))
+    blob = blob.transpose(2, 0, 1)[np.newaxis, ...].astype(np.float32)
+    emb = reid_compiled([blob])[reid_compiled.output(0)].flatten()
+    return emb / np.linalg.norm(emb)
+
+
+# 1. Embed the reference face.
+reference = cv2.imread(REFERENCE_IMAGE)
+ref_faces = detect_faces(reference)
+if not ref_faces:
+    raise SystemExit("No face detected in the reference image")
+ref_bbox = max(ref_faces, key=lambda b: (b[2] - b[0]) * (b[3] - b[1]))
+ref_emb = get_embedding(reference, ref_bbox)
+
+# 2. Read a scene frame that contains several people.
+cap = cv2.VideoCapture(SCENE_VIDEO)
+cap.set(cv2.CAP_PROP_POS_FRAMES, SCENE_FRAME)
+ok, frame = cap.read()
+cap.release()
+if not ok:
+    raise SystemExit(f"Could not read frame {SCENE_FRAME} from {SCENE_VIDEO}")
+
+# 3. Compare every face in the scene to the reference; keep the best match.
+best_bbox = None
+best_sim = 0.0
+for bbox in detect_faces(frame):
+    sim = float(np.dot(get_embedding(frame, bbox), ref_emb))
+    if sim > best_sim:
+        best_sim = sim
+        best_bbox = bbox
+
+if best_bbox is not None and best_sim >= MATCH_THRESHOLD:
+    x1, y1, x2, y2 = best_bbox
+    cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+    cv2.putText(frame, f"MATCH {best_sim:.2f}", (x1, max(15, y1 - 8)),
+                cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
+    print(f"Matched reference identity, similarity {best_sim:.4f}")
+else:
+    print(f"No matching face found (best similarity {best_sim:.4f})")
+
+cv2.imwrite("output_openvino.jpg", frame)
+print("Saved: output_openvino.jpg")
+```
+
+**Device targets:**
+
+- `"CPU"` -- default, works on all Intel platforms.
+- `"GPU"` -- Intel integrated or discrete GPU.
+- `"NPU"` -- Intel NPU; face-detection-adas-0001 FP16 is NPU-compatible.
+
+#### Expected Output
+
+![OpenVINO expected output](expected_output_openvino.jpg)
+
+### DLStreamer Sample
+
+The pipeline below runs the face detector via `gvadetect` and the
+re-identification model via `gvaclassify` on the video. Frames are pulled through
+an `appsink`, where each detected face's embedding is compared to the reference
+embedding computed from `face_a.jpg`. Only faces that match the reference are
+boxed, so the annotated `output_dlstreamer.mp4` highlights just the reference
+subject even when other people are present.
+
+> **Notes on running this sample:**
+>
+> - Export `PYTHONPATH` so the DLStreamer Python modules (`gi`, `gstgva`) are
+>   importable:
+>
+>   ```bash
+>   source /opt/intel/openvino_2026/setupvars.sh
+>   source /opt/intel/dlstreamer/scripts/setup_dls_env.sh
+>   export PYTHONPATH=/opt/intel/dlstreamer/python:\
+>   /opt/intel/dlstreamer/gstreamer/lib/python3/dist-packages:${PYTHONPATH:-}
+>   ```
+>
+> - The re-identification embedding is attached as a tensor on each face's
+>   region-of-interest metadata. Convert the stream to `BGR` **before**
+>   `gvadetect`/`gvaclassify` so a downstream format conversion does not strip
+>   those tensors before the `appsink` reads them.
+
+```python
+import gi
+
+gi.require_version("Gst", "1.0")
+from gi.repository import Gst
+
+Gst.init([])
+
+import numpy as np
+import cv2
+from gstgva import VideoFrame
+
+INPUT_VIDEO = "test_video.mp4"
+REFERENCE_IMAGE = "face_a.jpg"
+OUTPUT_VIDEO = "output_dlstreamer.mp4"
+DETECTION_MODEL = "intel/face-detection-adas-0001/FP16/face-detection-adas-0001.xml"
+REID_MODEL = "intel/face-reidentification-retail-0095/FP16/face-reidentification-retail-0095.xml"
+# For CPU: change "GPU" to "CPU". For NPU: change "GPU" to "NPU".
+DEVICE = "GPU"
+DET_THRESHOLD = 0.6
+MATCH_THRESHOLD = 0.4
+
+
+def face_embeddings(video_frame):
+    """Yield ((x, y, w, h), normalized_embedding) for each classified face."""
+    for region in video_frame.regions():
+        rect = region.rect()
+        emb = None
+        for tensor in region.tensors():
+            if tensor.is_detection():
+                continue
+            data = np.array(tensor.data(), dtype=np.float32)
+            if data.size >= 256:
+                emb = data[:256]
+        if emb is None:
+            continue
+        emb = emb / (np.linalg.norm(emb) + 1e-9)
+        yield (int(rect.x), int(rect.y), int(rect.w), int(rect.h)), emb
+
+
+def run_pipeline(source_desc, on_frame):
+    # Convert to BGR before inference so gvaclassify's embedding tensors survive
+    # to the appsink (a later format-changing videoconvert would strip them).
+    pipeline = Gst.parse_launch(
+        f"{source_desc} ! videoconvert ! video/x-raw,format=BGR ! "
+        f"gvadetect model={DETECTION_MODEL} device={DEVICE} "
+        f"threshold={DET_THRESHOLD} ! queue ! "
+        f"gvaclassify model={REID_MODEL} device={DEVICE} ! queue ! "
+        "appsink name=sink emit-signals=true sync=false max-buffers=4 drop=false"
+    )
+    sink = pipeline.get_by_name("sink")
+    sink.connect("new-sample", on_frame)
+    pipeline.set_state(Gst.State.PLAYING)
+    pipeline.get_bus().timed_pop_filtered(
+        Gst.CLOCK_TIME_NONE, Gst.MessageType.EOS | Gst.MessageType.ERROR)
+    pipeline.set_state(Gst.State.NULL)
+
+
+# 1. Compute the reference embedding from the reference image.
+ref = {"emb": None, "area": 0}
+
+
+def on_reference(sink):
+    sample = sink.emit("pull-sample")
+    if sample is None:
+        return Gst.FlowReturn.OK
+    vf = VideoFrame(sample.get_buffer(), caps=sample.get_caps())
+    for (x, y, w, h), emb in face_embeddings(vf):
+        if w * h > ref["area"]:
+            ref["area"] = w * h
+            ref["emb"] = emb
+    return Gst.FlowReturn.OK
+
+
+run_pipeline(f"filesrc location={REFERENCE_IMAGE} ! jpegdec", on_reference)
+if ref["emb"] is None:
+    raise SystemExit("No face detected in the reference image")
+ref_emb = ref["emb"]
+
+# 2. Process the video, boxing only faces that match the reference identity.
+writer = {"w": None}
+match_frames = 0
+
+
+def on_video(sink):
+    global match_frames
+    sample = sink.emit("pull-sample")
+    if sample is None:
+        return Gst.FlowReturn.OK
+    vf = VideoFrame(sample.get_buffer(), caps=sample.get_caps())
+    matches = []
+    for (x, y, w, h), emb in face_embeddings(vf):
+        similarity = float(np.dot(emb, ref_emb))
+        if similarity >= MATCH_THRESHOLD:
+            matches.append((x, y, w, h, similarity))
+
+    with vf.data() as mat:
+        frame = mat.copy()
+
+    if writer["w"] is None:
+        frame_h, frame_w = frame.shape[:2]
+        structure = sample.get_caps().get_structure(0)
+        ok_fr, fps_n, fps_d = structure.get_fraction("framerate")
+        fps = fps_n / fps_d if ok_fr and fps_d else 12
+        writer["w"] = cv2.VideoWriter(
+            OUTPUT_VIDEO, cv2.VideoWriter_fourcc(*"mp4v"), fps, (frame_w, frame_h))
+
+    for x, y, w, h, similarity in matches:
+        cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
+        cv2.putText(frame, f"MATCH {similarity:.2f}", (x, max(15, y - 8)),
+                    cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
+    if matches:
+        match_frames += 1
+    writer["w"].write(frame)
+    return Gst.FlowReturn.OK
+
+
+run_pipeline(f"filesrc location={INPUT_VIDEO} ! decodebin3", on_video)
+if writer["w"] is not None:
+    writer["w"].release()
+print(f"Frames with a matched face: {match_frames}", flush=True)
+print(f"Saved: {OUTPUT_VIDEO}", flush=True)
+```
+
+**Device targets:**
+
+- `DEVICE = "GPU"` -- default in the sample code.
+- `DEVICE = "CPU"` -- change `"GPU"` to `"CPU"`.
+- `DEVICE = "NPU"` -- change `"GPU"` to `"NPU"`; use `batch-size=1` and `nireq=4` for best NPU utilization.
+
+#### Expected Output
+
+![DLStreamer expected output](expected_output_dlstreamer.gif)
+
+---
+
+## License
+
+Licensed under the MIT License. See [LICENSE](LICENSE) for details.
+
+## References
+
+- [face-detection-adas-0001](https://docs.openvino.ai/2024/omz_models_model_face_detection_adas_0001.html)
+- [face-reidentification-retail-0095](https://docs.openvino.ai/2024/omz_models_model_face_reidentification_retail_0095.html)
+- [Open Model Zoo](https://github.com/openvinotoolkit/open_model_zoo)
+- [OpenVINO Documentation](https://docs.openvino.ai/)
+- [Intel DLStreamer](https://docs.openedgeplatform.intel.com/2026.0/edge-ai-libraries/dlstreamer/index.html)

export_and_quantize.sh

@@ -0,0 +1,113 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: MIT
+# Copyright (C) Intel Corporation
+#
+# Download face detection and re-identification models from Open Model Zoo
+# for the face-matching use case.
+# Usage: ./export_and_quantize.sh
+
+set -euo pipefail
+
+# Official Open Model Zoo public model storage (versioned, immutable).
+OMZ_BASE="https://storage.openvinotoolkit.org/repositories/open_model_zoo/2023.0/models_bin/1"
+
+echo "--- Installing dependencies ---"
+pip install -qU openvino opencv-python numpy
+
+# Download both the IR topology (.xml) and weights (.bin) for an OMZ model
+# from the official storage into intel/<model>/<precision>/.
+download_omz_model() {
+    local model="$1"
+    local precision="$2"
+    local dest="intel/${model}/${precision}"
+    mkdir -p "${dest}"
+    local ext
+    for ext in xml bin; do
+        if [[ ! -f "${dest}/${model}.${ext}" ]]; then
+            wget -q -O "${dest}/${model}.${ext}" \
+                "${OMZ_BASE}/${model}/${precision}/${model}.${ext}"
+        fi
+    done
+}
+
+# Ask for approval before downloading models and sample files
+echo ""
+echo "This script will download:"
+echo "  - Model weights and/or sample files"
+echo ""
+read -p "Continue with downloads? (yes/no): " APPROVAL
+if [[ "${APPROVAL}" != "yes" ]]; then
+    echo "Download cancelled by user."
+    exit 0
+fi
+echo ""
+
+echo "--- Downloading face-detection-adas-0001 (FP16) ---"
+download_omz_model face-detection-adas-0001 FP16
+echo "Ready: face-detection-adas-0001"
+
+echo "--- Downloading face-reidentification-retail-0095 (FP16) ---"
+download_omz_model face-reidentification-retail-0095 FP16
+echo "Ready: face-reidentification-retail-0095"
+
+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/face-demographics-walking-and-pause.mp4"
+    echo "Downloaded: test_video.mp4"
+else
+    echo "Already present: test_video.mp4"
+fi
+
+echo "--- Capturing the reference face of the left subject from the video ---"
+if [[ ! -f face_a.jpg ]]; then
+    python3 - <<'PY'
+import cv2
+import numpy as np
+import openvino as ov
+
+DET = "intel/face-detection-adas-0001/FP16/face-detection-adas-0001.xml"
+core = ov.Core()
+det = core.compile_model(core.read_model(DET), "CPU")
+inp = det.input(0)
+det_h, det_w = inp.shape[2], inp.shape[3]
+
+
+def left_face_portrait(frame, thr=0.6):
+    """Return a head-and-shoulders crop of the left-most detected face."""
+    h, w = frame.shape[:2]
+    blob = cv2.resize(frame, (det_w, det_h))
+    blob = blob.transpose(2, 0, 1)[np.newaxis, ...].astype(np.float32)
+    out = det([blob])[det.output(0)][0][0]
+    boxes = [(int(d[3] * w), int(d[4] * h), int(d[5] * w), int(d[6] * h))
+             for d in out if float(d[2]) >= thr]
+    if not boxes:
+        return None
+    x1, y1, x2, y2 = min(boxes, key=lambda b: (b[0] + b[2]) / 2)  # left-most
+    bw, bh = x2 - x1, y2 - y1
+    cx1, cx2 = max(0, int(x1 - 0.6 * bw)), min(w, int(x2 + 0.6 * bw))
+    cy1, cy2 = max(0, int(y1 - 0.7 * bh)), min(h, int(y2 + 1.6 * bh))
+    return frame[cy1:cy2, cx1:cx2]
+
+
+# During the 37-42s segment a woman pauses on the left of the frame; capture
+# a head-and-shoulders portrait of her as the reference face to search for.
+cap = cv2.VideoCapture("test_video.mp4")
+cap.set(cv2.CAP_PROP_POS_FRAMES, 468)
+ok, frame = cap.read()
+crop = left_face_portrait(frame) if ok else None
+if crop is None or crop.size == 0:
+    raise SystemExit("Could not capture a reference face at frame 468")
+cv2.imwrite("face_a.jpg", crop)
+print("Captured face_a.jpg from frame 468")
+cap.release()
+PY
+else
+    echo "Already present: face_a.jpg"
+fi
+
+echo "--- Done ---"
+echo "Detector  : intel/face-detection-adas-0001/FP16/face-detection-adas-0001.xml"
+echo "ReID      : intel/face-reidentification-retail-0095/FP16/face-reidentification-retail-0095.xml"
+echo "Reference : face_a.jpg (left subject captured from the sample video)"
+echo "Scene     : test_video.mp4 (contains the reference subject plus others)"