Upload 4 files

app.py

@@ -0,0 +1,180 @@
+import os
+import cv2
+import numpy as np
+import gradio as gr
+from ultralytics import YOLO
+
+# ----------------------------
+# Config
+# ----------------------------
+MODEL_NAME = os.getenv("YOLO_MODEL", "yolov8n.pt")
+CLASS_OF_INTEREST = "person"
+
+# Danger zone: top-left, bottom-right (x, y)
+DANGER_ZONE = ((100, 100), (400, 400))
+
+# Inference config
+CONF_THRES = 0.35
+IMG_SIZE = 640
+
+# ----------------------------
+# Load model once (global)
+# ----------------------------
+model = YOLO(MODEL_NAME)
+
+# Build class-name -> id mapping once (YOLOv8 COCO)
+# For yolov8n.pt, names is dict {id: name}
+NAMES = model.names
+PERSON_CLASS_ID = None
+for k, v in NAMES.items():
+    if v == CLASS_OF_INTEREST:
+        PERSON_CLASS_ID = int(k)
+        break
+
+if PERSON_CLASS_ID is None:
+    raise RuntimeError("Could not find 'person' class in model.names")
+
+
+# ----------------------------
+# Helpers
+# ----------------------------
+def overlaps_zone(box_xyxy, zone):
+    """True if box overlaps danger zone (partial overlap)."""
+    x1, y1, x2, y2 = box_xyxy
+    (zx1, zy1), (zx2, zy2) = zone
+    overlap_x = (x1 < zx2) and (x2 > zx1)
+    overlap_y = (y1 < zy2) and (y2 > zy1)
+    return overlap_x and overlap_y
+
+
+def make_beep(sr=22050, freq=880, duration=0.25):
+    """Return a short beep waveform for browser playback."""
+    t = np.linspace(0, duration, int(sr * duration), endpoint=False)
+    wave = 0.2 * np.sin(2 * np.pi * freq * t)  # low volume
+    return (sr, wave.astype(np.float32))
+
+
+BEEP_AUDIO = make_beep()
+
+
+# ----------------------------
+# Frame processor
+# ----------------------------
+def process_frame(frame, zone_x1, zone_y1, zone_x2, zone_y2, conf_thres):
+    """
+    frame: numpy array RGB from gradio
+    returns:
+      - annotated RGB frame
+      - grayscale RGB frame
+      - infrared frame (RGB)
+      - beep audio tuple or None
+      - status text
+    """
+    if frame is None:
+        return None, None, None, None, "No frame"
+
+    # Gradio gives RGB; OpenCV prefers BGR for drawing
+    rgb = frame
+    bgr = cv2.cvtColor(rgb, cv2.COLOR_RGB2BGR)
+
+    zone = ((int(zone_x1), int(zone_y1)), (int(zone_x2), int(zone_y2)))
+
+    # Derived feeds
+    gray = cv2.cvtColor(bgr, cv2.COLOR_BGR2GRAY)
+    gray_bgr = cv2.cvtColor(gray, cv2.COLOR_GRAY2BGR)
+    infrared = cv2.applyColorMap(gray, cv2.COLORMAP_JET)
+
+    # Draw danger zone
+    for img in (bgr, gray_bgr, infrared):
+        cv2.rectangle(img, zone[0], zone[1], (0, 0, 255), 2)
+
+    # YOLO inference (stream=False for single image)
+    # verbose=False keeps logs clean
+    results = model.predict(
+        source=bgr,
+        imgsz=IMG_SIZE,
+        conf=float(conf_thres),
+        verbose=False
+    )
+
+    alert = False
+    det_count = 0
+
+    r = results[0]
+    if r.boxes is not None and len(r.boxes) > 0:
+        boxes = r.boxes.xyxy.cpu().numpy().astype(int)
+        cls_ids = r.boxes.cls.cpu().numpy().astype(int)
+        confs = r.boxes.conf.cpu().numpy()
+
+        for (x1, y1, x2, y2), cid, c in zip(boxes, cls_ids, confs):
+            if cid != PERSON_CLASS_ID:
+                continue
+
+            det_count += 1
+            label = f"person: {c:.2f}"
+
+            # draw bbox
+            for img in (bgr, gray_bgr, infrared):
+                cv2.rectangle(img, (x1, y1), (x2, y2), (255, 0, 0), 2)
+                cv2.putText(img, label, (x1, max(15, y1 - 8)),
+                            cv2.FONT_HERSHEY_SIMPLEX, 0.6, (255, 0, 0), 2)
+
+            if overlaps_zone((x1, y1, x2, y2), zone):
+                alert = True
+
+    if alert:
+        for img in (bgr, gray_bgr, infrared):
+            cv2.putText(img, "ALERT: Person in danger zone", (20, 45),
+                        cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 255), 3)
+        status = f"🚨 ALERT! persons detected: {det_count}"
+        beep = BEEP_AUDIO
+    else:
+        status = f"✅ OK (persons detected: {det_count})"
+        beep = None
+
+    # Convert back to RGB for gradio display
+    out_rgb = cv2.cvtColor(bgr, cv2.COLOR_BGR2RGB)
+    out_gray = cv2.cvtColor(gray_bgr, cv2.COLOR_BGR2RGB)
+    out_infra = cv2.cvtColor(infrared, cv2.COLOR_BGR2RGB)
+
+    return out_rgb, out_gray, out_infra, beep, status
+
+
+# ----------------------------
+# Gradio UI
+# ----------------------------
+with gr.Blocks(title="YOLOv8 Danger Zone Demo") as demo:
+    gr.Markdown(
+        """
+# YOLOv8 Danger Zone Detection (Demo)
+- Uses browser webcam input (works on Hugging Face Spaces)
+- Detects **person** and triggers **alert** if they overlap the danger zone
+"""
+    )
+
+    with gr.Row():
+        cam = gr.Image(source="webcam", streaming=True, type="numpy", label="Webcam (Input)")
+        with gr.Column():
+            zone_x1 = gr.Slider(0, 1280, value=DANGER_ZONE[0][0], step=1, label="Zone x1")
+            zone_y1 = gr.Slider(0, 720, value=DANGER_ZONE[0][1], step=1, label="Zone y1")
+            zone_x2 = gr.Slider(0, 1280, value=DANGER_ZONE[1][0], step=1, label="Zone x2")
+            zone_y2 = gr.Slider(0, 720, value=DANGER_ZONE[1][1], step=1, label="Zone y2")
+            conf = gr.Slider(0.05, 0.90, value=CONF_THRES, step=0.01, label="Confidence Threshold")
+
+    with gr.Row():
+        out1 = gr.Image(type="numpy", label="Color (Annotated)")
+        out2 = gr.Image(type="numpy", label="Grayscale (Annotated)")
+        out3 = gr.Image(type="numpy", label="Infrared (Annotated)")
+
+    with gr.Row():
+        alert_audio = gr.Audio(label="Alert Beep (plays when triggered)", autoplay=True)
+        status = gr.Textbox(label="Status", interactive=False)
+
+    cam.stream(
+        fn=process_frame,
+        inputs=[cam, zone_x1, zone_y1, zone_x2, zone_y2, conf],
+        outputs=[out1, out2, out3, alert_audio, status],
+        show_progress=False
+    )
+
+demo.queue(concurrency_count=1).launch()

requirements.txt

@@ -0,0 +1,8 @@
+ultralytics
+torch
+torchvision
+opencv-python
+numpy
+pandas
+matplotlib
+gradio

yolov8n.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59b3d833e2ff32e194b5bb8e08d211dc7c5bdf144b90d2c8412c47ccfc83b36
+size 6549796