import cv2
from ultralytics import YOLO
from collections import deque
import os

# Allow duplicate loading of OpenMP runtime
os.environ["KMP_DUPLICATE_LIB_OK"] = "True"

# Define the official YAML configuration file path (adjust as needed)
yaml_path = "botsort.yaml"

# Camera index (default camera index, 1 indicates an external camera)
camera_index = 1

# Load the YOLO model
model = YOLO(r"D:\AIM\lemon\runs\detect\train4\weights\best.pt")  # Load custom model

# Define class labels
class_labels = {
    0: "Bruised",
    1: "DefectiveLemon",
    2: "GoodLemon",
    3: "NotRipeLemon",
    4: "Rotten"
}

# Apply smoothing to "DefectiveLemon", "GoodLemon", and "NotRipeLemon"
smoothing_labels = ["DefectiveLemon", "GoodLemon", "NotRipeLemon"]

# Smoothing parameters for sliding window
HISTORY_LENGTH = 20  # Number of recent frames
DEFECT_THRESHOLD = 0.3  # Threshold for "DefectiveLemon" proportion
GOOD_THRESHOLD = 0.7    # Threshold for "GoodLemon" and "NotRipeLemon" proportion

# State history for each target (used for smoothing), format: {ID: deque([...], maxlen=HISTORY_LENGTH)}
lemon_history = {}

# Set the display window to be resizable
cv2.namedWindow("Live Detection", cv2.WINDOW_NORMAL)

# Smoothing function:
# If the current detected label is not in smoothing_labels, clear the target's history and return the current label;
# Otherwise, add the current label to the history and return a smoothed label based on the proportion.
def get_smoothed_label(obj_id, current_label):
    if current_label not in smoothing_labels:
        if obj_id in lemon_history:
            lemon_history[obj_id].clear()
        return current_label

    if obj_id not in lemon_history:
        lemon_history[obj_id] = deque(maxlen=HISTORY_LENGTH)
    lemon_history[obj_id].append(current_label)

    history = lemon_history[obj_id]
    defect_count = history.count("DefectiveLemon")
    good_count = history.count("GoodLemon")
    notripe_count = history.count("NotRipeLemon")
    total = len(history)

    if total == 0:
        return current_label
    if defect_count / total >= DEFECT_THRESHOLD:
        return "DefectiveLemon"
    elif good_count / total >= GOOD_THRESHOLD:
        return "GoodLemon"
    elif notripe_count / total >= GOOD_THRESHOLD:
        return "NotRipeLemon"
    else:
        return history[-1]

# Use streaming tracking mode to maintain tracker state
results = model.track(
    source=camera_index,    # Get video stream directly from the camera
    conf=0.5,
    tracker=yaml_path,      # Use the YAML configuration file
    persist=True,           # Persist tracking (do not reset)
    stream=True,            # Stream processing, not frame-by-frame calling
    show=False
)

# Iterate over streaming tracking results
for result in results:
    frame = result.orig_img  # Current frame
    detections = result.boxes  # Detection box information

    for box in detections:
        x1, y1, x2, y2 = map(int, box.xyxy[0])  # Detection box coordinates
        obj_id = int(box.id) if box.id is not None else -1  # Tracking ID
        class_id = int(box.cls)  # Class ID
        score = box.conf  # Confidence
        label = class_labels.get(class_id, "Unknown")  # Get class name

        # If target ID is valid
        if obj_id != -1:
            # If the detected label requires smoothing, use the smoothing function
            if label in smoothing_labels:
                final_label = get_smoothed_label(obj_id, label)
                display_text = f"ID {obj_id} | {final_label}"
                # Only print for targets with smoothed labels (only care about these three classes)
                if final_label in smoothing_labels:
                    position = f"({x1}, {y1}, {x2}, {y2})"
                    print(f"ID: {obj_id}, Position: {position}, Label: {display_text}")
            else:
                # For other classes, display the current detection result directly and clear history (if exists)
                if obj_id in lemon_history:
                    lemon_history[obj_id].clear()
                display_text = label
        else:
            display_text = label

        # Draw detection box and label
        cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
        cv2.putText(frame, display_text, (x1, y1 - 10),
                    cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)

    # Display the processed frame
    cv2.imshow("Live Detection", frame)

    # Exit program when ESC key is pressed
    if cv2.waitKey(1) & 0xFF == 27:
        print("ESC key detected. Exiting the program.")
        break

cv2.destroyAllWindows()
print("Camera video processing complete. Program terminated.")