Upload 3 files

best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:203342ef59cb5b4ae59f20d8b2e0f1024415cfe6ce4dac7693dd96ce6aa31a1c
+size 5477139

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+ultralytics
+opencv-python
+numpy
+pandas

trafic_cong.py

@@ -0,0 +1,139 @@
+# -*- coding: utf-8 -*-
+"""Untitled7.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1jQG-GmOOby02SciEngcsoZq6ySP7gQDJ
+"""
+
+import streamlit as st
+import cv2
+import tempfile
+import os
+import time
+import numpy as np
+import pandas as pd
+from collections import defaultdict
+from ultralytics import YOLO
+
+# --- FONCTIONS UTILES ---
+
+def get_color_for_id(track_id):
+    np.random.seed(track_id)
+    return tuple(np.random.randint(0, 255, size=3).tolist())
+
+def draw_text_with_background(image, text, position, font=cv2.FONT_HERSHEY_SIMPLEX,
+                              font_scale=1, font_thickness=2, text_color=(255, 255, 255), bg_color=(0, 0, 0), padding=5):
+
+    text_size = cv2.getTextSize(text, font, font_scale, font_thickness)[0]
+    text_width, text_height = text_size
+
+    x, y = position
+    top_left = (x, y - text_height - padding)
+    bottom_right = (x + text_width + padding * 2, y + padding)
+
+    cv2.rectangle(image, top_left, bottom_right, bg_color, -1)
+    cv2.putText(image, text, (x + padding, y), font, font_scale, text_color, font_thickness, cv2.LINE_AA)
+
+class YOLOVideoProcessor:
+    def __init__(self, model_path, video_path, output_path, poly1, poly2, tracker_method="bot"):
+        self.model = YOLO(model_path, task="detect")
+        self.tracker_method = tracker_method
+        self.video_path = video_path
+        self.output_path = output_path
+
+        self.unique_region1_ids = set()
+        self.unique_region2_ids = set()
+        self.poly1 = poly1
+        self.poly2 = poly2
+
+    def is_in_region(self, center, poly):
+        poly_np = np.array(poly, dtype=np.int32)
+        return cv2.pointPolygonTest(poly_np, center, False) >= 0
+
+    def process_video(self):
+        cap = cv2.VideoCapture(self.video_path)
+        frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+        frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+
+        fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+        out = cv2.VideoWriter(self.output_path, fourcc, 30, (frame_width, frame_height))
+
+        while cap.isOpened():
+            success, frame = cap.read()
+            if not success:
+                break
+
+            tracker = "botsort.yaml" if self.tracker_method.lower() == "bot" else "bytetrack.yaml"
+            results = self.model.track(frame, persist=True, tracker=tracker, conf=0.25)
+
+            track_ids = []
+            if len(results[0].boxes) > 0:
+                try:
+                    track_ids = results[0].boxes.id.int().cpu().tolist()
+                except AttributeError:
+                    track_ids = [i for i in range(len(results[0].boxes.xywh.cpu().numpy()))]
+
+            # Dessiner les polygones
+            cv2.polylines(frame, [np.array(self.poly1, np.int32)], isClosed=True, color=(0, 255, 0), thickness=2)
+            cv2.polylines(frame, [np.array(self.poly2, np.int32)], isClosed=True, color=(255, 0, 0), thickness=2)
+
+            for box, track_id in zip(results[0].boxes.xywh.cpu().numpy(), track_ids):
+                x, y, w, h = box
+                center_point = (int(x), int(y))
+
+                if self.is_in_region(center_point, self.poly1):
+                    self.unique_region1_ids.add(track_id)
+                if self.is_in_region(center_point, self.poly2):
+                    self.unique_region2_ids.add(track_id)
+
+            draw_text_with_background(frame, f'Total Sens 1: {len(self.unique_region1_ids)}', (10, frame_height - 50))
+            draw_text_with_background(frame, f'Total Sens 2: {len(self.unique_region2_ids)}', (880, frame_height - 50))
+
+            out.write(frame)
+
+        cap.release()
+        out.release()
+        cv2.destroyAllWindows()
+
+# --- INTERFACE STREAMLIT ---
+st.title("🚗 Détection de Véhicules avec Polygones")
+
+uploaded_file = st.file_uploader("📂 Upload une vidéo", type=["mp4", "avi", "mov"])
+
+# Entrée utilisateur pour les polygones
+st.sidebar.header("🔹 Saisie des polygones")
+
+st.sidebar.subheader("📍 Polygone 1 (vert)")
+poly1_input = st.sidebar.text_area("Entrez 4 points (x,y) séparés par des espaces", "465,350 609,350 520,630 3,630")
+
+st.sidebar.subheader("📍 Polygone 2 (rouge)")
+poly2_input = st.sidebar.text_area("Entrez 4 points (x,y) séparés par des espaces", "678,350 815,350 1203,630 743,630")
+
+def parse_polygon(input_text):
+    try:
+        return [tuple(map(int, point.split(','))) for point in input_text.split()]
+    except:
+        return []
+
+poly1 = parse_polygon(poly1_input)
+poly2 = parse_polygon(poly2_input)
+
+if uploaded_file is not None:
+    tfile = tempfile.NamedTemporaryFile(delete=False, suffix='.mp4')
+    tfile.write(uploaded_file.read())
+
+    st.video(tfile.name)
+
+    model_path = "best.pt"  # Mettre le bon chemin du modèle
+    output_path = "output_video.mp4"
+
+    if st.button("▶️ Lancer l'analyse"):
+        if len(poly1) == 4 and len(poly2) == 4:
+            processor = YOLOVideoProcessor(model_path, tfile.name, output_path, poly1, poly2)
+            processor.process_video()
+            st.success("✅ Traitement terminé !")
+            st.video(output_path)
+        else:
+            st.error("❌ Les coordonnées des polygones doivent contenir **exactement 4 points**.")