File size: 3,156 Bytes
4d18315 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
import cv2
import gradio as gr
import numpy as np
import tempfile
import os
from ultralytics import YOLO
from deep_sort_realtime.deepsort_tracker import DeepSort
from collections import defaultdict
# Dictionnaire pour compter les objets détectés
class_counts = defaultdict(set)
# Charger modèle YOLOv8
model = YOLO("best.pt") # Assure-toi que ce fichier est bien dans le même dossier
# Initialiser DeepSORT
tracker = DeepSort(max_age=30)
# 📸 Détection image
def detect_on_image(image):
results = model(image)[0]
for box in results.boxes:
cls_id = int(box.cls[0])
conf = float(box.conf[0])
x1, y1, x2, y2 = map(int, box.xyxy[0])
if conf > 0.4:
label = f"{model.names[cls_id]} {conf:.2f}"
cv2.rectangle(image, (x1, y1), (x2, y2), (255, 0, 0), 2)
cv2.putText(image, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255, 0, 0), 2)
return image
# 🎥 Détection vidéo
def detect_and_track_video(video_path):
if not os.path.exists(video_path):
return None
cap = cv2.VideoCapture(video_path)
width = int(cap.get(3))
height = int(cap.get(4))
fps = cap.get(cv2.CAP_PROP_FPS)
temp_output = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
out = cv2.VideoWriter(temp_output.name, cv2.VideoWriter_fourcc(*'mp4v'), fps, (width, height))
class_counts.clear()
while cap.isOpened():
ret, frame = cap.read()
if not ret:
break
results = model(frame)[0]
detections = []
for box in results.boxes:
cls_id = int(box.cls[0])
conf = float(box.conf[0])
x1, y1, x2, y2 = map(int, box.xyxy[0])
if conf > 0.4:
detections.append(([x1, y1, x2 - x1, y2 - y1], conf, model.names[cls_id]))
tracks = tracker.update_tracks(detections, frame=frame)
for track in tracks:
if not track.is_confirmed():
continue
track_id = track.track_id
l, t, r, b = map(int, track.to_ltrb())
label = track.get_det_class()
cv2.rectangle(frame, (l, t), (r, b), (0, 255, 0), 2)
cv2.putText(frame, f'{label} ID {track_id}', (l, t - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
class_counts[label].add(track_id)
out.write(frame)
cap.release()
out.release()
return temp_output.name
# Interfaces Gradio
image_interface = gr.Interface(
fn=detect_on_image,
inputs=gr.Image(type="numpy", label="Image de surveillance"),
outputs=gr.Image(type="numpy", label="Image annotée"),
title="📸 Détection sur Image",
description="Détection de bagages et objets avec YOLOv8."
)
video_interface = gr.Interface(
fn=detect_and_track_video,
inputs=gr.Video(label="Vidéo de surveillance"),
outputs=gr.Video(label="Vidéo annotée avec suivi"),
title="🎥 Suivi sur Vidéo",
description="Suivi multi-objets avec DeepSORT + YOLOv8."
)
# Interface finale
gr.TabbedInterface(
[image_interface, video_interface],
tab_names=["📷 Image", "🎥 Vidéo"]
).launch() |