diff --git a/docs/hardware-bringup.md b/docs/hardware-bringup.md
new file mode 100644
index 0000000..ce0d3a5
--- /dev/null
+++ b/docs/hardware-bringup.md
@@ -0,0 +1,141 @@
+# Hardware Bring-up & Benchmark Procedure (Raspberry Pi 5 + Hailo-8L)
+
+This document describes the validation procedure for the edge detection core on actual hardware (Pi 5 + Hailo accelerator). Development PC testing is covered in the main test suite; this procedure applies to the Pi deployment phase.
+
+## 1. PCIe Gen3 Activation
+
+Enable PCIe Gen3 for Hailo-8L optimal throughput:
+
+1. SSH to Pi 5 and edit `/boot/firmware/config.txt`:
+   ```bash
+   sudo nano /boot/firmware/config.txt
+   ```
+
+2. Add or update the line:
+   ```
+   dtparam=pciex1_gen=3
+   ```
+
+3. Reboot:
+   ```bash
+   sudo reboot
+   ```
+
+4. Verify PCIe Gen3 negotiation:
+   ```bash
+   lspci -vv | grep -i speed
+   ```
+   Expected output: `LnkSta: Speed 8GT/s` (Gen3) or higher, not 2.5GT/s (Gen1).
+
+---
+
+## 2. HEF Benchmark: Single, 2-Stream, 4-Stream
+
+Benchmark `yolov8s_pose.hef` (fall detection backbone) under different load scenarios:
+
+1. **Single-stream baseline:**
+   - Load HEF via HailoRT VDevice, run 1 stream continuously (640×640 RGB input).
+   - Measure: FPS, CPU usage, Hailo die temperature.
+   - Target: ≥ 20 FPS @ <60°C (baseline headroom).
+
+2. **2-stream round-robin:**
+   - Process 2 video streams (CSI + USB UVC) round-robin into Hailo.
+   - Measure: Combined FPS per stream, CPU, temperature.
+   - Target: ≥ 10 FPS per stream (full fall detection at 2 streams).
+
+3. **4-stream round-robin (stress test):**
+   - Process 4 USB UVC streams into Hailo round-robin.
+   - Measure: FPS per stream, CPU, temperature, memory.
+   - Target: ≥ 7–8 FPS per stream (performance envelope; may require USB controller separation).
+
+**Benchmark tooling:**
+- Use `hailo-benchmark` or custom Python loop with HailoRT + OpenCV frame capture.
+- Log FPS, CPU (top/mpstat), temperature (vcgencmd measure_temp).
+- Store results in `docs/benchmarks/YYYY-MM-DD-pi5-hef-results.txt`.
+
+---
+
+## 3. FPS 3-Tier Validation
+
+Measure frame processing under three operational modes:
+
+| Tier | Mode | Description | Target FPS | Notes |
+|------|------|-------------|-----------|-------|
+| **T1: Full** | Detection on all frames | Hailo inference on every frame; maximum load. | ≥ 12 fps (crucial: fall detection responsiveness) | For 1–2 primary cameras (fall risk zones). Limits concurrent streams. |
+| **T2: Detection** | Inference every 2–3 frames | Trade-off: skip frames to reduce Hailo load. | ≥ 8 fps | For additional context cameras; acceptable for non-critical zones. |
+| **T3: Motion** | Hailo only on motion keyframes | Inference triggered by motion (v4l2 MJPEG keyframe or frame diff). | ≥ 5 fps avg | For background monitoring; many cameras, low overhead. |
+
+1. Configure edge detection core to support tier selection (via thresholds file or env var).
+2. Run each tier with realistic camera setup (e.g., T1 on main fall cam, T2/T3 on perimeter).
+3. Log FPS, E2E latency (frame capture → alert), CPU, Hailo temp for 30 min per tier.
+4. Confirm T1 ≥ 12 fps for the target scene (well-lit, medium activity).
+
+---
+
+## 4. Multi-Camera Stability (Long-run Test)
+
+Validate sustained operation and resource cleanup:
+
+1. **Setup:**
+   - 1 CSI camera (picamera2 via PiCameraSource) + 2–4 USB UVC cameras (UvcSource).
+   - Route USB cameras to 2 separate USB3 controllers (Pi 5 has 2 controllers; check with `lsusb -t`).
+
+2. **Test duration:** 4–8 hours continuous frame capture and optional Hailo inference.
+
+3. **Monitor:**
+   - FPS stability (no drift or sudden drops).
+   - Memory usage (RSS, no unbounded growth; confirm video buffer cleanup).
+   - CPU distribution (no single core maxed; picamera2 process isolation working).
+   - Hailo temperature (sustained < 75°C).
+   - Error logs (no hang or exception cascades).
+
+4. **Pass criterion:** No crashes, memory leaks, or FPS degradation after 4 hours.
+
+---
+
+## 5. Reflect Results in Thresholds & Camera Roles
+
+After benchmark completion, update configuration:
+
+1. **`edge/config.py` thresholds:**
+   - Adjust `motion.cooldown_ms`, `motion.min_duration_ms` based on measured T2/T3 FPS.
+   - Tune `fall.confidence_threshold` if fall recall vs. precision trade-off differs on real video.
+
+2. **`edge/config.py` camera roles:**
+   - Assign `role="fall_primary"` to high-fps T1 cam (≥ 12 fps).
+   - Assign `role="context"` to T2 cameras (8–10 fps).
+   - Assign `role="perimeter"` to T3 motion-only cameras.
+
+3. **Benchmark report:**
+   - Document actual Pi hardware, kernel version, HailoRT version, Hailo FW version.
+   - Archive FPS/latency/temp results.
+   - Flag any anomalies (thermal throttling, USB contention, CPU saturation).
+
+---
+
+## Troubleshooting
+
+**PCIe speed not Gen3:**
+- Confirm cable seating and power to Hailo.
+- Check firmware update: `sudo rpi-update` (experimental; use with caution).
+
+**HEF FPS < target:**
+- Verify HailoRT version matches Hailo FW.
+- Check for CPU threads contention (picamera2 process + Python inference + OS).
+- Monitor Hailo die temperature; throttle if > 85°C.
+
+**Memory leak in USB capture:**
+- Ensure OpenCV's `VideoCapture.release()` is called on cleanup.
+- Check `v4l2-ctl -D` for buffer count and memory mapping.
+
+**USB controller contention:**
+- Separate high-bandwidth cameras (USB3 MJPEG) across 2 controllers.
+- Use `lsusb -t` and `/sys/bus/usb/devices/` to map.
+
+---
+
+## References
+
+- [hailo-rpi5-examples](https://github.com/hailo-ai/hailo-rpi5-examples) — Hailo + Pi 5 reference (MIT).
+- [picamera2 docs](https://datasheets.raspberrypi.com/camera/picamera2-manual.pdf).
+- [Raspberry Pi 5 datasheet](https://datasheets.raspberrypi.com/rpi5/raspberry-pi-5-datasheet.pdf).
diff --git a/edge/adapters/__init__.py b/edge/adapters/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/edge/adapters/hailo_pose.py b/edge/adapters/hailo_pose.py
new file mode 100644
index 0000000..31144bb
--- /dev/null
+++ b/edge/adapters/hailo_pose.py
@@ -0,0 +1,16 @@
+"""Hailo yolov8s_pose HEF 어댑터 (실장비). PosePort 구현.
+개발 PC에선 인스턴스화 불가(hailort 부재). Pi에서 HailoRT로 실제 추론 배선."""
+
+from edge.models import Person, BBox, Keypoint
+
+
+class HailoPoseAdapter:
+    def __init__(self, hef_path: str):
+        self.hef_path = hef_path
+        # 실장비 배선 지점: HailoRT VDevice/InferModel 로드, yolov8s_pose 후처리.
+        # 참고: hailo-rpi5-examples pose 파이프라인 (MIT).
+        raise NotImplementedError("실장비 전용: HailoRT 배선 필요")
+
+    def infer(self, frame) -> list:
+        # frame(640x640 RGB) -> yolov8s_pose -> list[Person(bbox, 17 keypoints)]
+        raise NotImplementedError
diff --git a/edge/adapters/picamera_source.py b/edge/adapters/picamera_source.py
new file mode 100644
index 0000000..2fa7c8e
--- /dev/null
+++ b/edge/adapters/picamera_source.py
@@ -0,0 +1,10 @@
+"""CSI 카메라 소스 (실장비). 카메라당 별 프로세스로 picamera2 구동."""
+
+
+class PiCameraSource:
+    def __init__(self, index: int = 0):
+        self.index = index
+        raise NotImplementedError("실장비 전용: picamera2 배선 필요")
+
+    def read(self):
+        raise NotImplementedError
diff --git a/edge/adapters/uvc_source.py b/edge/adapters/uvc_source.py
new file mode 100644
index 0000000..56836ea
--- /dev/null
+++ b/edge/adapters/uvc_source.py
@@ -0,0 +1,13 @@
+"""USB UVC 소스 (실장비). v4l2 MJPEG. cv2.VideoCapture, 2개 USB3 컨트롤러 분산."""
+
+import cv2
+
+
+class UvcSource:
+    def __init__(self, dev, mjpeg: bool = True):
+        self.cap = cv2.VideoCapture(dev)
+        if mjpeg:
+            self.cap.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter_fourcc(*"MJPG"))
+
+    def read(self):
+        return self.cap.read()