Sync facial-recognition from metro-analytics-catalog

.gitattributes

@@ -33,3 +33,5 @@ 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
+expected_output_openvino.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 +1,386 @@
+---
+license: mit
+license_link: LICENSE
+library_name: openvino
+pipeline_tag: image-classification
+tags:
+  - openvino
+  - intel
+  - face-detection
+  - face-reidentification
+  - edge-ai
+  - metro
+  - dlstreamer
+language:
+  - en
+---
+
+# Facial Recognition
+
+| Property | Value |
+|---|---|
+| **Category** | Face Detection + Re-Identification |
+| **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 (re-identification) |
+
+---
+
+## Overview
+
+Facial Recognition is a Metro Analytics use case that detects human faces in
+images and video and computes a 256-dimensional embedding vector for each face,
+enabling enrollment, search, and identification against a known gallery.
+
+The pipeline composes two Intel Open Model Zoo models:
+
+- **face-detection-adas-0001** -- an SSD-based face detector optimized for
+  automotive and surveillance cameras (FP16, 384x672 input).
+- **face-reidentification-retail-0095** -- a compact CNN that maps a cropped
+  face to a 256-d embedding; cosine similarity between embeddings determines
+  identity.
+
+These models are well-tested with OpenVINO Runtime and Intel DLStreamer's
+`gvadetect` + `gvaclassify` pipeline.
+
+Typical Metro deployments include:
+
+- **Access Control** -- match employees or authorized personnel against an enrollment gallery.
+- **VIP Identification** -- recognize known individuals in a crowd.
+- **Search and Forensics** -- find a person of interest across multiple camera feeds.
+- **Attendance Tracking** -- log when enrolled individuals enter or leave a facility.
+
+> **Privacy Note:** Facial recognition 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 performs the following steps:
+
+1. Installs `openvino`.
+2. Downloads `face-detection-adas-0001` (FP16) into `./intel/face-detection-adas-0001/FP16/`.
+3. Downloads `face-reidentification-retail-0095` (FP16) into `./intel/face-reidentification-retail-0095/FP16/`.
+4. Downloads a sample test video (`test_video.mp4`).
+
+### OpenVINO Sample
+
+The sample below runs recognition on the sample video. It detects every face,
+computes a 256-d embedding, and matches it against a gallery of previously seen
+people. Each new person is enrolled and assigned a numeric ID; when the same
+person is seen again, the gallery returns their existing ID. Every face is
+annotated with its `ID <n>`, and the result is saved to `output_openvino.mp4`.
+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"
+INPUT_VIDEO = "test_video.mp4"
+CONF_THRESHOLD = 0.6
+MATCH_THRESHOLD = 0.5
+
+core = ov.Core()
+
+# Change device to "GPU" or "NPU" to run on integrated GPU or NPU.
+det_model = core.compile_model(core.read_model(DETECTION_MODEL), "CPU")
+reid_model = core.compile_model(core.read_model(REID_MODEL), "CPU")
+
+det_input = det_model.input(0)
+det_h, det_w = det_input.shape[2], det_input.shape[3]
+reid_input = reid_model.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)
+    detections = det_model([blob])[det_model.output(0)][0][0]
+    boxes = []
+    for det in detections:
+        if float(det[2]) < CONF_THRESHOLD:
+            continue
+        x1 = max(0, int(det[3] * w0))
+        y1 = max(0, int(det[4] * h0))
+        x2 = min(w0, int(det[5] * w0))
+        y2 = min(h0, int(det[6] * h0))
+        if x2 > x1 and y2 > y1:
+            boxes.append((x1, y1, x2, y2))
+    return boxes
+
+
+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_model([blob])[reid_model.output(0)].flatten()
+    return emb / np.linalg.norm(emb)
+
+
+# Gallery of (numeric_id, embedding). recognize() returns an existing ID for a
+# known face or enrolls a new one, keeping each person's ID stable over time.
+gallery = []
+next_id = 1
+
+
+def recognize(embedding):
+    global next_id
+    best_index, best_sim = -1, 0.0
+    for index, (_, gallery_emb) in enumerate(gallery):
+        sim = float(np.dot(embedding, gallery_emb))
+        if sim > best_sim:
+            best_sim, best_index = sim, index
+    if best_sim >= MATCH_THRESHOLD:
+        person_id, gallery_emb = gallery[best_index]
+        # Blend the embedding into the gallery entry to stay robust to pose.
+        updated = 0.9 * gallery_emb + 0.1 * embedding
+        gallery[best_index] = (person_id, updated / np.linalg.norm(updated))
+        return person_id
+    person_id = next_id
+    next_id += 1
+    gallery.append((person_id, embedding))
+    print(f"Enrolled ID {person_id}")
+    return person_id
+
+
+cap = cv2.VideoCapture(INPUT_VIDEO)
+fps = cap.get(cv2.CAP_PROP_FPS) or 12
+frame_w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+frame_h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+writer = cv2.VideoWriter(
+    "output_openvino.mp4", cv2.VideoWriter_fourcc(*"mp4v"), fps, (frame_w, frame_h))
+
+while True:
+    ok, frame = cap.read()
+    if not ok:
+        break
+    for bbox in detect_faces(frame):
+        person_id = recognize(get_embedding(frame, bbox))
+        x1, y1, x2, y2 = bbox
+        cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+        cv2.putText(frame, f"ID {person_id}", (x1, max(15, y1 - 8)),
+                    cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
+    writer.write(frame)
+
+cap.release()
+writer.release()
+print(f"Total identities recognized: {len(gallery)}")
+print("Saved: output_openvino.mp4")
+```
+
+**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.gif)
+
+### 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 face's embedding is matched against a gallery to assign
+a stable numeric ID (new people are enrolled, returning people keep their ID).
+Every face is annotated with its `ID <n>` and the result is saved to
+`output_dlstreamer.mp4`.
+
+> **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"
+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 = 0.5
+
+# Gallery of (numeric_id, embedding). recognize() returns an existing ID for a
+# known face or enrolls a new one, keeping each person's ID stable over time.
+gallery = []
+next_id = 1
+
+
+def recognize(embedding):
+    global next_id
+    best_index, best_sim = -1, 0.0
+    for index, (_, gallery_emb) in enumerate(gallery):
+        sim = float(np.dot(embedding, gallery_emb))
+        if sim > best_sim:
+            best_sim, best_index = sim, index
+    if best_sim >= MATCH_THRESHOLD:
+        person_id, gallery_emb = gallery[best_index]
+        # Blend the embedding into the gallery entry to stay robust to pose.
+        updated = 0.9 * gallery_emb + 0.1 * embedding
+        gallery[best_index] = (person_id, updated / np.linalg.norm(updated))
+        return person_id
+    person_id = next_id
+    next_id += 1
+    gallery.append((person_id, embedding))
+    print(f"Enrolled ID {person_id}", flush=True)
+    return person_id
+
+
+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
+
+
+# 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"filesrc location={INPUT_VIDEO} ! decodebin3 ! "
+    "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")
+
+writer = {"w": None}
+
+
+def on_video(sink):
+    sample = sink.emit("pull-sample")
+    if sample is None:
+        return Gst.FlowReturn.OK
+    vf = VideoFrame(sample.get_buffer(), caps=sample.get_caps())
+    labeled = []
+    for (x, y, w, h), emb in face_embeddings(vf):
+        labeled.append((x, y, w, h, recognize(emb)))
+
+    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, person_id in labeled:
+        cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
+        cv2.putText(frame, f"ID {person_id}", (x, max(15, y - 8)),
+                    cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
+    writer["w"].write(frame)
+    return Gst.FlowReturn.OK
+
+
+sink.connect("new-sample", on_video)
+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)
+if writer["w"] is not None:
+    writer["w"].release()
+print(f"Total identities recognized: {len(gallery)}", 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 +1,65 @@
+#!/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 facial-recognition 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
+
+# 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 "--- 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 "Video    : test_video.mp4"