app.py

import gradio as gr
from ultralytics import YOLOv10
import cv2
import spaces

# Load YOLOv10 model
model = YOLOv10.from_pretrained('jameslahm/yolov10x')

# Define object categories to classify activities
activity_categories = {
    "Working": ["laptop", "computer", "keyboard", "office chair"],
    "Meal Time": ["fork", "spoon", "plate", "food"],
    "Exercise": ["dumbbell", "bicycle", "yoga mat", "treadmill"],
    "Outdoors": ["car", "tree", "bicycle", "road"],
    # Add more categories and associated objects as needed
}

# Function to map detected objects to categorized activities
def categorize_activity(detected_objects):
    activity_summary = {}
    
    for activity, objects in activity_categories.items():
        if any(obj in detected_objects for obj in objects):
            if activity not in activity_summary:
                activity_summary[activity] = 0
            activity_summary[activity] += 1  # Increase count for that activity
    
    return activity_summary

# Function to process the video and generate the journal
@spaces.GPU
def generate_journal(video):
    cap = cv2.VideoCapture(video)
    frame_rate = cap.get(cv2.CAP_PROP_FPS)
    journal_entries = {}
    
    while cap.isOpened():
        ret, frame = cap.read()
        if not ret:
            break
        
        # Make predictions using YOLOv10
        results = model.predict(source=frame)
        detected_objects = [res.name for res in results]
        
        # Get current timestamp in the video
        timestamp = cap.get(cv2.CAP_PROP_POS_MSEC) / 1000  # Convert ms to seconds
        
        # Categorize the detected objects into activities
        activity_summary = categorize_activity(detected_objects)
        
        # Store the activities with their timestamp
        for activity, count in activity_summary.items():
            if activity not in journal_entries:
                journal_entries[activity] = []
            journal_entries[activity].append(f"At {timestamp:.2f} seconds: {count} objects related to {activity}")
    
    cap.release()
    
    # Create a formatted journal
    formatted_journal = []
    for activity, entries in journal_entries.items():
        formatted_journal.append(f"**{activity}:**")
        formatted_journal.extend(entries)
    
    return "\n".join(formatted_journal)

# Gradio interface for uploading video and generating journal
iface = gr.Interface(
    fn=generate_journal,
    inputs=gr.Video(label="Upload Video"),
    outputs=gr.Textbox(label="Generated Daily Journal"),
    title="AI-Powered Daily Journal"
)

iface.launch()