import sqlite3 import datetime from Status import Status import numpy as np class…
- User
`import sqlite3 import datetime from Status import Status import numpy as np
class Database: """ A class to handle interactions with the SQLite database for object tracking.
Attributes: conn (sqlite3.Connection): The database connection. cursor (sqlite3.Cursor): The database cursor. """ def __init__(self, db_path='object_tracking.db'): """ Initializes the Database class with a connection to the specified SQLite database. Args: db_path (str): The path to the SQLite database file. """ self.conn = sqlite3.connect(db_path) self.cursor = self.conn.cursor() self.create_table() self.add_person_name_column() self.create_known_faces_table() def create_table(self): """ Creates the 'tracked_objects' table if it does not already exist. """ self.cursor.execute(''' CREATE TABLE IF NOT EXISTS tracked_objects ( id INTEGER PRIMARY KEY AUTOINCREMENT, class_name TEXT, x1 INTEGER, y1 INTEGER, width INTEGER, height INTEGER, last_seen DATETIME, status TEXT, detection_count INTEGER DEFAULT 0, person_name TEXT -- Added new field for person's name ) ''') self.conn.commit() def create_known_faces_table(self): """ Creates the 'known_faces' table if it does not already exist. """ self.cursor.execute(''' CREATE TABLE IF NOT EXISTS known_faces ( id INTEGER PRIMARY KEY AUTOINCREMENT, name TEXT NOT NULL, embedding BLOB NOT NULL ) ''') self.conn.commit() def fetch_objects(self, class_name=None): """ Fetches objects from the database, optionally filtered by class name. Args: class_name (str, optional): The class name to filter objects. Returns: list: A list of tuples representing the objects. """ if class_name: self.cursor.execute('SELECT * FROM tracked_objects WHERE class_name=?', (class_name,)) else: self.cursor.execute('SELECT * FROM tracked_objects') return self.cursor.fetchall() def fetch_all_objects(self): """ Fetches all objects from the database. Returns: list: A list of tuples representing all objects. """ self.cursor.execute('SELECT * FROM tracked_objects') return self.cursor.fetchall() def fetch_object_by_id(self, obj_id): """ Fetches a single object by its ID. Args: obj_id (int): The ID of the object. Returns: tuple: The object data as a tuple. """ self.cursor.execute('SELECT * FROM tracked_objects WHERE id=?', (obj_id,)) return self.cursor.fetchone() def update_object(self, obj_id, x1, y1, width, height): """ Updates the position and size of an existing object in the database, and increments detection_count. Args: obj_id (int): The ID of the object to update. x1 (int): The new x-coordinate of the object's top-left corner. y1 (int): The new y-coordinate of the object's top-left corner. width (int): The new width of the object. height (int): The new height of the object. Returns: int: The ID of the updated object. """ last_seen = datetime.datetime.now().isoformat() status = Status.IN_FRAME.value # Set status to 'In Frame' self.cursor.execute(''' UPDATE tracked_objects SET x1=?, y1=?, width=?, height=?, last_seen=?, status=?, detection_count=detection_count+1 WHERE id=? ''', (x1, y1, width, height, last_seen, status, obj_id)) self.conn.commit() return obj_id def insert_object(self, class_name, x1, y1, width, height, person_name=None): """ Inserts a new object into the database, and returns the new object's ID. Args: class_name (str): The class name of the object. x1 (int): The x-coordinate of the object's top-left corner. y1 (int): The y-coordinate of the object's top-left corner. width (int): The width of the object. height (int): The height of the object. person_name (str, optional): The name of the person associated with the object. Returns: int: The ID of the newly inserted object. """ last_seen = datetime.datetime.now().isoformat() status = Status.IN_FRAME.value detection_count = 1 self.cursor.execute(''' INSERT INTO tracked_objects (class_name, x1, y1, width, height, last_seen, status, detection_count, person_name) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?) ''', (class_name, x1, y1, width, height, last_seen, status, detection_count, person_name)) self.conn.commit() return self.cursor.lastrowid def update_status(self, obj_id, status): """ Updates the status of an object in the database. Args: obj_id (int): The ID of the object to update. status (Status): The new status of the object. """ self.cursor.execute(''' UPDATE tracked_objects SET status=? WHERE id=? ''', (status.value, obj_id)) self.conn.commit() def delete_object(self, obj_id): """ Deletes an object from the database. Args: obj_id (int): The ID of the object to delete. """ self.cursor.execute(''' DELETE FROM tracked_objects WHERE id=? ''', (obj_id,)) self.conn.commit() def add_person_name_column(self): """ Adds the 'person_name' column to 'tracked_objects' table if it doesn't exist. """ self.cursor.execute("PRAGMA table_info(tracked_objects)") columns = [column[1] for column in self.cursor.fetchall()] if 'person_name' not in columns: self.cursor.execute('ALTER TABLE tracked_objects ADD COLUMN person_name TEXT') self.conn.commit() def insert_known_face(self, name, embedding): """ Inserts a new known face into the database. Args: name (str): The name of the person. embedding (np.ndarray): The face embedding. """ embedding_blob = embedding.astype(np.float32).tobytes() self.cursor.execute(''' INSERT INTO known_faces (name, embedding) VALUES (?, ?) ''', (name, embedding_blob)) self.conn.commit() def fetch_known_faces(self): """ Fetches all known faces from the database. Returns: list: A list of tuples representing known faces. """ self.cursor.execute('SELECT * FROM known_faces') known_faces = [] for row in self.cursor.fetchall(): id = row[0] name = row[1] embedding_blob = row[2] embedding = np.frombuffer(embedding_blob, dtype=np.float32) known_faces.append((id, name, embedding)) return known_faces def get_known_face_by_name(self, name): """ Fetches a known face by name from the database. Args: name (str): The name of the person. Returns: tuple: A tuple representing the known face. """ self.cursor.execute('SELECT * FROM known_faces WHERE name=?', (name,)) row = self.cursor.fetchone() if row: id = row[0] name = row[1] embedding_blob = row[2] embedding = np.frombuffer(embedding_blob, dtype=np.float32) return (id, name, embedding) return None def update_person_name(self, obj_id, person_name): self.cursor.execute(''' UPDATE tracked_objects SET person_name=? WHERE id=? ''', (person_name, obj_id)) self.conn.commit()`, `import cv2import numpy as np
class FaceInterface: """ A class for interfacing with the face recognition module. """ def init(self, db) -> None: """ Initializes the FaceInterface with the given database.
Args: db (Database): The database instance. """ self.db = db`, `# Import necessary librariesfrom Database import Database from ObjectDetection import ObjectDetection from ObjectTracker import ObjectTracker from FaceInterface import FaceInterface import cv2 import argparse
def add_known_faces(file_path: str, face_interface: FaceInterface) -> None: """ Add known faces from the CSV file to the face recognition module.
Args: file_path (str): Path to the CSV file containing image paths and names. face_interface (FaceInterface): The face recognition interface. Raises: ValueError: If a known face could not be added. """ if file_path: with open(file_path, 'r') as file: for line in file: image_path, name = line.strip().split(',') if not face_interface.add_known_face(image_path, name): raise ValueError(f"Failed to add {name} from {image_path}")def main(): """ The main function to initialize object detection and tracking, and process the video stream from the webcam. """ # Set up argument parser parser = argparse.ArgumentParser(description="CSV file of image_path, name. For face recognition.") parser.add_argument('--csv', type=str, help='Path to the CSV file for face recognition.') parser.add_argument('--model', type=str, default='yolov8n.pt', help='The YOLO model weights name. Default is yolov8n.pt.') args = parser.parse_args()
# Initialize the database, detection model, and tracker db = Database() detection_model = ObjectDetection(model=args.model) tracker = ObjectTracker(db, detection_model) face_interface = FaceInterface(db) # Add known faces from the CSV file add_known_faces(args.csv, face_interface) # Set up video capture from the default webcam cap = cv2.VideoCapture(0) cap.set(3, 640) # Set width cap.set(4, 480) # Set height while True: success, img = cap.read() if not success: break # Perform object tracking on the current frame img = tracker.track_objects(img) # Display the resulting frame cv2.imshow('Webcam', img) # Exit if 'q' is pressed if cv2.waitKey(1) & 0xFF == ord('q'): break # Release resources cap.release() cv2.destroyAllWindows()if name == "main": main()
,from ultralytics import YOLO import osclass ObjectDetection: """ A class for object detection using a YOLO model.
Attributes: model (YOLO): The YOLO model used for detection. classNames (list): List of class names that the model can detect. allowed_classes (set): Set of class indices that are allowed for tracking. """ def __init__(self, model="yolov8n.pt"): """ Initializes the ObjectDetection class with the specified YOLO model. Args: model_path (str): The path to the YOLO model weights. """ try: self.model = YOLO(self.get_onnx_model(model), task='detect') except Exception as e: raise Exception(f"Error loading YOLO model: {e}") self.classNames = ["person", "bicycle", "car", "motorbike", "aeroplane", "bus", "train", "truck", "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow", "elephant", "bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee", "skis", "snowboard", "sports ball", "kite", "baseball bat", "baseball glove", "skateboard", "surfboard", "tennis racket", "bottle", "wine glass", "cup", "fork", "knife", "spoon", "bowl", "banana", "apple", "sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake", "chair", "sofa", "pottedplant", "bed", "diningtable", "toilet", "tvmonitor", "laptop", "mouse", "remote", "keyboard", "cell phone", "microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors", "teddy bear", "hair drier", "toothbrush"] # Only allow certain classes for tracking self.allowed_classes = {0, 24, 25, 26, 31, 36, 37, 39, 40, 41, 53, 63, 65, 67} def get_onnx_model(self, model: str) -> str: """ Converts the given YOLO model to ONNX format. Args: model (str): The name of the YOLO model file. Raises: ValueError: If the model conversion fails. Returns: str: The path to the converted ONNX model. """ onnx_model_path = model.split('.')[0] + '.onnx' if os.path.exists(onnx_model_path): return onnx_model_path try: model: YOLO = YOLO(model) return model.export(format='onnx') except Exception as e: raise ValueError(f"Failed to convert model to ONNX format: {e}") def detect_objects(self, img): """ Detects objects in the given image. Args: img (numpy.ndarray): The image in which to detect objects. Returns: list: A list of detections, each containing class name, bounding box coordinates, width, height, and confidence. """ results = self.model(img, stream=True) detections = [] for r in results: for box in r.boxes: # Get the confidence score confidence = box.conf[0].item() if confidence < 0.55: continue # Skip detections below confidence threshold # Get the class index cls = int(box.cls[0]) if cls not in self.allowed_classes: continue # Skip classes that are not allowed # Get bounding box coordinates x1, y1, x2, y2 = map(int, box.xyxy[0]) width, height = x2 - x1, y2 - y1 class_name = self.classNames[cls] detections.append((class_name, x1, y1, width, height, confidence)) return detections`, `import cv2from deep_sort_realtime.deepsort_tracker import DeepSort from datetime import datetime, timedelta from Status import Status from insightface.app import FaceAnalysis import numpy as np import concurrent.futures
class ObjectTracker: """ A class for tracking objects using Deep Sort and updating their status in the database.
Attributes: db (Database): The database instance for storing object data. detection_model (ObjectDetection): The object detection model. tracker (DeepSort): The Deep Sort tracker instance. object_positions (dict): Dictionary to store the positions of each object. """ def __init__(self, db, detection_model): """ Initializes the ObjectTracker class with the given database and detection model. Args: db (Database): The database instance. detection_model (ObjectDetection): The object detection model. """ self.db = db self.detection_model = detection_model self.tracker = DeepSort(max_age=10, n_init=3, nms_max_overlap=1.0, max_cosine_distance=0.4, nn_budget=None) self.object_positions = {} # To store positions of each object # Initialize ArcFace for face recognition self.face_recognizer = FaceAnalysis(allowed_modules=['detection', 'recognition']) self.face_recognizer.prepare(ctx_id=0, det_size=(320, 320)) self.face_recognition_cache = {} # Stores obj_id: (person_name, last_recognition_frame) self.face_recognition_interval = 10 # Number of frames to wait before re-running face recognition self.frame_count = 0 # Initialize frame counter self.executor = concurrent.futures.ThreadPoolExecutor(max_workers=2) def is_near(self, existing_obj, new_obj, threshold=30): """ Determines if a new object is near an existing object based on a threshold. Args: existing_obj (tuple): The existing object's coordinates and size (x, y, w, h). new_obj (tuple): The new object's coordinates and size (x, y, w, h). threshold (int, optional): The distance threshold to consider. Returns: bool: True if the objects are near each other, False otherwise. """ ex, ey, ew, eh = existing_obj nx, ny, nw, nh = new_obj # Check if bounding boxes are close enough return not (nx > ex + ew + threshold or nx + nw < ex - threshold or ny > ey + eh + threshold or ny + nh < ey - threshold) def is_within_frame(self, obj_id, frame_width, frame_height, border_threshold=20, size_threshold=60): """ Checks if an object is within the frame or near the borders. If the object is near a border and its size is small (less than size_threshold), it is considered out of bounds. Args: obj_id (int): The ID of the object. frame_width (int): The width of the frame. frame_height (int): The height of the frame. border_threshold (int, optional): The distance from borders to consider as 'near the border'. size_threshold (int, optional): The size threshold to consider the object as out of bounds if near border. Returns: bool: True if the object is within the frame, False if it's out of bounds. """ positions = self.object_positions.get(obj_id, []) if not positions: return False # No position data available x, y, w, h = positions[-1] # Get the most recent position # Check distances from borders distance_left = x distance_right = frame_width - (x + w) distance_top = y distance_bottom = frame_height - (y + h) # If object is near left border if distance_left <= border_threshold and w <= size_threshold: return False # Object is out of bounds # If object is near right border if distance_right <= border_threshold and w <= size_threshold: return False # If object is near top border if distance_top <= border_threshold and h <= size_threshold: return False # If object is near bottom border if distance_bottom <= border_threshold and h <= size_threshold: return False # If none of the above conditions met, object is within frame return True def check_for_false_positives(self, frame_width, frame_height): """ Checks the database for objects that haven't been seen for more than 500 ms. If an object hasn't been seen for more than 500 ms and is not within frame, updates its status to 'Left Frame'. If detection_count < 5, deletes it. Args: frame_width (int): The width of the frame. frame_height (int): The height of the frame. """ all_objects = self.db.fetch_all_objects() now = datetime.now() detection_timeout = now - timedelta(milliseconds=500) for obj in all_objects: obj_id = obj[0] class_name = obj[1] x1 = obj[2] y1 = obj[3] width = obj[4] height = obj[5] last_seen_str = obj[6] status = obj[7] detection_count = obj[8] last_seen = datetime.fromisoformat(last_seen_str) # If the object hasn't been seen for more than 500 ms if last_seen < detection_timeout: if detection_count < 6: # Delete the object from the database self.db.delete_object(obj_id) # Remove from position tracking if obj_id in self.object_positions: del self.object_positions[obj_id] else: # Check if the object is within the frame if not self.is_within_frame(obj_id, frame_width, frame_height): # Update the object's status to 'Left Frame' self.db.update_status(obj_id, Status.LEFT_FRAME) def track_objects(self, img): self.frame_count += 1 # Update frame count frame_height, frame_width = img.shape[:2] detections = self.detection_model.detect_objects(img) formatted_detections = [] # Fetch all existing objects once per frame existing_objs = self.db.fetch_all_objects() existing_objs_dict = {} # Map class_name to list of objects for obj in existing_objs: class_name = obj[1] if class_name not in existing_objs_dict: existing_objs_dict[class_name] = [] existing_objs_dict[class_name].append(obj) for class_name, x1, y1, width, height, confidence in detections: new_obj = (x1, y1, width, height) formatted_detections.append(([x1, y1, width, height], confidence, class_name)) cv2.rectangle(img, (x1, y1), (x1 + width, y1 + height), (255, 0, 255), 3) cv2.putText(img, f'{class_name} {confidence:.2f}', (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (255, 0, 0), 2) person_name = None # Initialize person_name if class_name == 'person': objs_in_class = existing_objs_dict.get(class_name, []) preexisting_obj = False obj_id = None for existing_obj in objs_in_class: db_x1 = existing_obj[2] db_y1 = existing_obj[3] db_width = existing_obj[4] db_height = existing_obj[5] last_seen = datetime.fromisoformat(existing_obj[6]) status = Status(existing_obj[7]) if self.is_near((db_x1, db_y1, db_width, db_height), new_obj): preexisting_obj = True obj_id = existing_obj[0] self.db.update_object(obj_id, x1, y1, width, height) self.object_positions[obj_id] = [(x1, y1, width, height)] break if not preexisting_obj: obj_id = self.db.insert_object(class_name, x1, y1, width, height) self.object_positions[obj_id] = [(x1, y1, width, height)] self.db.update_status(obj_id, Status.IN_FRAME) # Perform face recognition for new object self.executor.submit(self.async_face_recognition, obj_id, img, x1, y1, width, height) if person_name: self.db.update_person_name(obj_id, person_name) self.face_recognition_cache[obj_id] = (person_name, self.frame_count) else: last_recognition_frame = self.face_recognition_cache.get(obj_id, (None, -self.face_recognition_interval))[1] if self.frame_count - last_recognition_frame >= self.face_recognition_interval: person_name = self.perform_face_recognition(img, x1, y1, width, height) if person_name: self.db.update_person_name(obj_id, person_name) self.face_recognition_cache[obj_id] = (person_name, self.frame_count) else: # Use cached name person_name = self.face_recognition_cache.get(obj_id, (None, None))[0] if person_name and person_name != 'Unknown': cv2.putText(img, f'Name: {person_name}', (x1, y1 - 30), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2) existing_objs = self.db.fetch_objects(class_name) preexisting_obj = False obj_id = None for existing_obj in existing_objs: db_x1 = existing_obj[2] db_y1 = existing_obj[3] db_width = existing_obj[4] db_height = existing_obj[5] last_seen = datetime.fromisoformat(existing_obj[6]) status = Status(existing_obj[7]) if self.is_near((db_x1, db_y1, db_width, db_height), new_obj): preexisting_obj = True obj_id = existing_obj[0] self.db.update_object(obj_id, x1, y1, width, height) if class_name == 'person': self.db.update_person_name(obj_id, person_name) self.object_positions[obj_id] = [(x1, y1, width, height)] break if not preexisting_obj: obj_id = self.db.insert_object(class_name, x1, y1, width, height, person_name) self.object_positions[obj_id] = [(x1, y1, width, height)] else: self.object_positions[obj_id] = [(x1, y1, width, height)] self.db.update_status(obj_id, Status.IN_FRAME) tracks = self.tracker.update_tracks(formatted_detections, frame=img) self.check_for_false_positives(frame_width, frame_height) return img def perform_face_recognition(self, img, x1, y1, width, height): person_img = img[y1:y1+height, x1:x1+width] faces = self.face_recognizer.get(person_img) if faces: face = faces[0] face_embedding = face.embedding / np.linalg.norm(face.embedding) known_faces = self.db.fetch_known_faces() min_distance = float('inf') matched_name = None for known_face in known_faces: known_name = known_face[1] known_embedding = known_face[2] / np.linalg.norm(known_face[2]) distance = np.linalg.norm(face_embedding - known_embedding) if distance < min_distance: min_distance = distance matched_name = known_name threshold = 1.0 # Adjust based on your model and data if min_distance < threshold: return matched_name else: return 'Unknown' else: return 'No Face Detected' def async_face_recognition(self, obj_id, img, x1, y1, width, height): person_name = self.perform_face_recognition(img, x1, y1, width, height) if person_name: self.db.update_person_name(obj_id, person_name) self.face_recognition_cache[obj_id] = (person_name, self.frame_count)`, `from enum import Enumclass Status(str, Enum): """ An enumeration to represent the status of tracked objects. """ IN_FRAME = "In Frame" LEFT_FRAME = "Left Frame"`. For this code, add in FaceInterface an add_known_face function to add face and name pair to the face recognition.
- Assistant
Certainly! Here's how you can add the
add_known_facemethod to theFaceInterfaceclass:import cv2 import numpy as np from insightface.app import FaceAnalysis class FaceInterface: """ A class for interfacing with the face recognition module. """ def __init__(self, db) -> None: """ Initializes the FaceInterface with the given database. Args: db (Database): The database instance. """ self.db = db # Initialize FaceAnalysis for face recognition self.face_recognition = FaceAnalysis(allowed_modules=['detection', 'recognition']) self.face_recognition.prepare(ctx_id=0, det_size=(320, 320)) def add_known_face(self, image_path: str, name: str) -> bool: """ Adds a known face to the database. Args: image_path (str): Path to the image file containing the face. name (str): Name of the person. Returns: bool: True if the face was successfully added, False otherwise. """ # Read the image from the given path img = cv2.imread(image_path) if img is None: print(f"Failed to read image at {image_path}") return False # Detect faces and get embeddings faces = self.face_recognition.get(img) if not faces: print(f"No face detected in image {image_path}") return False # Use the first detected face face = faces[0] embedding = face.embedding if embedding is None: print(f"Failed to get embedding for face in image {image_path}") return False # Normalize the embedding embedding = embedding / np.linalg.norm(embedding) # Insert the name and embedding into the database self.db.insert_known_face(name, embedding) return TrueThis method performs the following steps:
- Reads the image from the provided
image_pathusing OpenCV. - Detects faces in the image using the
FaceAnalysismodule from theinsightfacelibrary. - Extracts the embedding of the first detected face.
- Normalizes the embedding to ensure consistent distance calculations during recognition.
- Inserts the face embedding and associated name into the database using the
insert_known_facemethod of theDatabaseclass. - Returns
Trueif the face was successfully added, orFalseotherwise.
Now, your
FaceInterfaceclass has theadd_known_facemethod, and you can use it to add known faces to your face recognition system. Here's how it integrates with youradd_known_facesfunction in your main script:def add_known_faces(file_path: str, face_interface: FaceInterface) -> None: """ Add known faces from the CSV file to the face recognition module. Args: file_path (str): Path to the CSV file containing image paths and names. face_interface (FaceInterface): The face recognition interface. Raises: ValueError: If a known face could not be added. """ if file_path: with open(file_path, 'r') as file: for line in file: image_path, name = line.strip().split(',') if not face_interface.add_known_face(image_path, name): raise ValueError(f"Failed to add {name} from {image_path}")With this setup, you can now populate your database with known faces, and your face recognition module will be able to recognize those faces during the tracking process.
- Reads the image from the provided