Update app.py

app.py

@@ -2,12 +2,18 @@ import os
 import cv2
 import numpy as np
 import torch
+import logging
 from ultralytics import YOLO
 from sort import Sort
 import gradio as gr
 
+# Configure logging
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
+
 # Load YOLOv12x model
 MODEL_PATH = "yolov12x.pt"
+if not os.path.exists(MODEL_PATH):
+    raise FileNotFoundError(f"Model file '{MODEL_PATH}' not found.")
 model = YOLO(MODEL_PATH)
 
 # COCO dataset class ID for truck
@@ -17,7 +23,7 @@ TRUCK_CLASS_ID = 7  # "truck"
 tracker = Sort()
 
 # Minimum confidence threshold for detection
-CONFIDENCE_THRESHOLD = 0.4  # Lowered for better detection
+CONFIDENCE_THRESHOLD = 0.4  # Adjust based on performance
 
 # Distance threshold to avoid duplicate counts
 DISTANCE_THRESHOLD = 50
@@ -30,41 +36,39 @@ TIME_INTERVALS = {
 
 def determine_time_interval(video_filename):
     """ Determines frame skip interval based on keywords in the filename. """
-    print(f"Checking filename: {video_filename}")  # Debugging
+    logging.info(f"Checking filename: {video_filename}")
     for keyword, interval in TIME_INTERVALS.items():
         if keyword in video_filename:
-            print(f"Matched keyword: {keyword} -> Interval: {interval}")  # Debugging
+            logging.info(f"Matched keyword: {keyword} -> Interval: {interval}")
             return interval
-    print("No keyword match, using default interval: 5")  # Debugging
+    logging.info("No keyword match, using default interval: 5")
     return 5  # Default interval
 
 def count_unique_trucks(video_path):
     """ Counts unique trucks in a video using YOLOv12x and SORT tracking. """
+    if not os.path.exists(video_path):
+        return {"Error": "Video file not found."}
+    
     cap = cv2.VideoCapture(video_path)
     if not cap.isOpened():
         return {"Error": "Unable to open video file."}
 
     unique_truck_ids = set()
     truck_history = {}
-
-    # Get FPS of the video
-    fps = int(cap.get(cv2.CAP_PROP_FPS))
-
-    # Extract filename from the path and convert to lowercase
+    
+    # Get FPS and total frames
+    fps = int(cap.get(cv2.CAP_PROP_FPS)) or 30  # Default to 30 if retrieval fails
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT)) or 1
+    
+    # Extract filename and determine time interval
     video_filename = os.path.basename(video_path).lower()
-
-    # Determine the dynamic time interval based on filename keywords
     time_interval = determine_time_interval(video_filename)
 
-    # Get total frames in the video
-    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
-
     # Ensure frame_skip does not exceed total frames
-    frame_skip = min(fps * time_interval, total_frames // 2)  # Reduced skipping
-
+    frame_skip = min(fps * time_interval, max(1, total_frames // 2))
     frame_count = 0
 
-    while True:
+    while cap.isOpened():
         ret, frame = cap.read()
         if not ret:
             break  # End of video
@@ -79,46 +83,29 @@ def count_unique_trucks(video_path):
         detections = []
         for result in results:
             for box in result.boxes:
-                class_id = int(box.cls.item())  # Get class ID
-                confidence = float(box.conf.item())  # Get confidence score
+                class_id = int(box.cls.item())
+                confidence = float(box.conf.item())
 
-                # Track only trucks
                 if class_id == TRUCK_CLASS_ID and confidence > CONFIDENCE_THRESHOLD:
-                    x1, y1, x2, y2 = map(int, box.xyxy[0])  # Get bounding box
+                    x1, y1, x2, y2 = map(int, box.xyxy[0])
                     detections.append([x1, y1, x2, y2, confidence])
 
-        # Debugging: Check detections
-        print(f"Frame {frame_count}: Detections -> {detections}")
-
-        if len(detections) > 0:
-            detections = np.array(detections)
-            tracked_objects = tracker.update(detections)
+        if detections:
+            tracked_objects = tracker.update(np.array(detections))
         else:
-            tracked_objects = []  # Prevent tracker from resetting
-
-        # Debugging: Check tracked objects
-        print(f"Frame {frame_count}: Tracked Objects -> {tracked_objects}")
+            tracked_objects = []
 
         for obj in tracked_objects:
-            truck_id = int(obj[4])  # Unique ID assigned by SORT
-            x1, y1, x2, y2 = obj[:4]  # Get the bounding box coordinates
-
-            truck_center = (x1 + x2) / 2, (y1 + y2) / 2  # Calculate truck center
+            truck_id = int(obj[4])
+            truck_center = ((obj[0] + obj[2]) / 2, (obj[1] + obj[3]) / 2)
 
-            # If truck is already in history, check movement distance
             if truck_id in truck_history:
                 last_position = truck_history[truck_id]["position"]
                 distance = np.linalg.norm(np.array(truck_center) - np.array(last_position))
-
                 if distance > DISTANCE_THRESHOLD:
-                    unique_truck_ids.add(truck_id)  # Add only if moved significantly
-
+                    unique_truck_ids.add(truck_id)
             else:
-                # If truck is not in history, add it
-                truck_history[truck_id] = {
-                    "frame_count": frame_count,
-                    "position": truck_center
-                }
+                truck_history[truck_id] = {"position": truck_center}
                 unique_truck_ids.add(truck_id)
 
     cap.release()
@@ -126,6 +113,9 @@ def count_unique_trucks(video_path):
 
 # Gradio UI function
 def analyze_video(video_file):
+    if not video_file:
+        return "Error: No video file uploaded."
+    
     result = count_unique_trucks(video_file)
     return "\n".join([f"{key}: {value}" for key, value in result.items()])