initial

.gitattributes

@@ -1,35 +1,13 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.pdf filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,22 @@
----
-title: Area Approx
-emoji: 🏢
-colorFrom: gray
-colorTo: yellow
-sdk: streamlit
-sdk_version: 1.41.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Classroom Dimension Estimator
+
+This Streamlit application estimates classroom dimensions from images using computer vision techniques. It can detect room boundaries and use a person in the image as a reference for more accurate measurements.
+
+## Features
+- Upload classroom images
+- Automatic dimension estimation
+- Person detection for better scaling
+- Visual results with confidence levels
+
+## Usage
+1. Upload an image of your classroom
+2. If possible, include a person in the image for better accuracy
+3. View the processed image and estimated dimensions
+4. Check the confidence level of the measurements
+
+## Technologies Used
+- Streamlit
+- OpenCV
+- MediaPipe
+- NumPy
+- PIL

app.py

@@ -0,0 +1,234 @@
+import streamlit as st
+import cv2
+import numpy as np
+import mediapipe as mp
+from PIL import Image
+import math
+
+# Set page config
+st.set_page_config(
+    page_title="Classroom Dimension Estimator",
+    page_icon="📏",
+    layout="wide"
+)
+
+# Custom CSS
+st.markdown("""
+    <style>
+    .main {
+        padding: 2rem;
+    }
+    .stAlert {
+        margin-top: 1rem;
+    }
+    .result-box {
+        background-color: #f0f2f6;
+        padding: 1.5rem;
+        border-radius: 10px;
+        margin: 1rem 0;
+    }
+    </style>
+""", unsafe_allow_html=True)
+
+# Initialize MediaPipe
+mp_drawing = mp.solutions.drawing_utils
+mp_pose = mp.solutions.pose
+
+def calculate_distance(point1, point2, pixel_to_meter_ratio=0.01):
+    """Calculate distance between two points in meters"""
+    return math.sqrt((point2[0] - point1[0])**2 + (point2[1] - point1[1])**2) * pixel_to_meter_ratio
+
+def estimate_room_dimensions(image):
+    """Estimate room dimensions using image processing"""
+    height, width = image.shape[:2]
+    
+    # Convert to grayscale
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    
+    # Edge detection
+    edges = cv2.Canny(gray, 50, 150)
+    
+    # Line detection
+    lines = cv2.HoughLinesP(edges, 1, np.pi/180, threshold=100, minLineLength=100, maxLineGap=10)
+    
+    if lines is None:
+        return None, None, image
+    
+    # Initialize variables for dimensions
+    max_width = 0
+    max_height = 0
+    
+    # Draw lines and calculate dimensions
+    result_image = image.copy()
+    for line in lines:
+        x1, y1, x2, y2 = line[0]
+        cv2.line(result_image, (x1, y1), (x2, y2), (0, 255, 0), 2)
+        
+        # Calculate length of line
+        length = math.sqrt((x2-x1)**2 + (y2-y1)**2)
+        
+        # Determine if line is more horizontal or vertical
+        angle = abs(math.degrees(math.atan2(y2-y1, x2-x1)))
+        if angle < 45 or angle > 135:
+            max_width = max(max_width, length)
+        else:
+            max_height = max(max_height, length)
+    
+    # Convert pixels to meters (approximate conversion)
+    pixel_to_meter = 0.01  # This value should be calibrated based on known references
+    width_meters = max_width * pixel_to_meter
+    height_meters = max_height * pixel_to_meter
+    
+    return width_meters, height_meters, result_image
+
+def estimate_with_person_reference(image):
+    """Estimate dimensions using a person as reference"""
+    with mp_pose.Pose(static_image_mode=True, min_detection_confidence=0.5) as pose:
+        results = pose.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
+        
+        if results.pose_landmarks:
+            # Get person height in pixels
+            landmarks = results.pose_landmarks.landmark
+            image_height, image_width = image.shape[:2]
+            
+            # Calculate person height (from head to ankle)
+            head = (int(landmarks[mp_pose.PoseLandmark.NOSE].x * image_width),
+                   int(landmarks[mp_pose.PoseLandmark.NOSE].y * image_height))
+            ankle = (int(landmarks[mp_pose.PoseLandmark.LEFT_ANKLE].x * image_width),
+                    int(landmarks[mp_pose.PoseLandmark.LEFT_ANKLE].y * image_height))
+            
+            person_height_pixels = calculate_distance(head, ankle)
+            
+            # Assume average person height is 1.7 meters
+            pixel_to_meter_ratio = 1.7 / person_height_pixels
+            
+            # Draw pose landmarks on image
+            annotated_image = image.copy()
+            mp_drawing.draw_landmarks(
+                annotated_image,
+                results.pose_landmarks,
+                mp_pose.POSE_CONNECTIONS
+            )
+            
+            return pixel_to_meter_ratio, annotated_image
+    
+    return None, image
+
+def main():
+    # Header section
+    col1, col2, col3 = st.columns([1,2,1])
+    with col2:
+        st.title("📏 Classroom Dimension Estimator")
+    
+    st.markdown("""
+        <div style='text-align: center'>
+            <p>Upload an image of your classroom to estimate its dimensions. 
+            For best results, include a person in the image for scale reference.</p>
+        </div>
+    """, unsafe_allow_html=True)
+    
+    # File upload section with better styling
+    uploaded_file = st.file_uploader(
+        "Choose an image...", 
+        type=["jpg", "jpeg", "png"],
+        help="Upload a clear image of your classroom. Supported formats: JPG, JPEG, PNG"
+    )
+    
+    if uploaded_file is not None:
+        # Create a spinner while processing
+        with st.spinner('Processing image...'):
+            # Read image
+            image = Image.open(uploaded_file)
+            image_np = np.array(image)
+            
+            # Create tabs for different views
+            tab1, tab2 = st.tabs(["📸 Image Analysis", "📊 Results"])
+            
+            with tab1:
+                col1, col2 = st.columns(2)
+                
+                with col1:
+                    st.markdown("### Original Image")
+                    st.image(image, use_column_width=True)
+                
+                # Try to detect person first for better calibration
+                pixel_to_meter_ratio, person_detected_image = estimate_with_person_reference(image_np)
+                
+                if pixel_to_meter_ratio:
+                    st.success("✅ Person detected! Using human height as reference for better estimation.")
+                    
+                    # Estimate dimensions with calibrated ratio
+                    width_meters, height_meters, processed_image = estimate_room_dimensions(image_np)
+                    
+                    with col2:
+                        st.markdown("### Processed Image")
+                        st.image(processed_image, use_column_width=True)
+                        
+                    with tab2:
+                        if width_meters is not None and height_meters is not None:
+                            # Adjust measurements using the calibrated ratio
+                            width_meters = (width_meters * pixel_to_meter_ratio) + 1.1
+                            height_meters = (height_meters * pixel_to_meter_ratio) + 1.1
+                            
+                            # Display results in a nice format
+                            st.markdown("### 📐 Estimated Dimensions")
+                            
+                            metrics_col1, metrics_col2, metrics_col3 = st.columns(3)
+                            with metrics_col1:
+                                st.metric("Width", f"{width_meters:.2f} m")
+                            with metrics_col2:
+                                st.metric("Height", f"{height_meters:.2f} m")
+                            with metrics_col3:
+                                st.metric("Area", f"{(width_meters * height_meters):.2f} m²")
+                            
+                            # Add confidence indicator
+                            st.progress(0.9)
+                            st.caption("Confidence level: High (Person detected for scale)")
+                        else:
+                            st.error("❌ Could not detect room boundaries clearly. Please try with a different image.")
+                else:
+                    # Fallback to basic estimation
+                    width_meters, height_meters, processed_image = estimate_room_dimensions(image_np)
+                    
+                    with col2:
+                        st.markdown("### Processed Image")
+                        st.image(processed_image, use_column_width=True)
+                    
+                    with tab2:
+                        if width_meters is not None and height_meters is not None:
+                            # Add 1.1 meters to both dimensions
+                            width_meters += 1.1
+                            height_meters += 1.1
+                            
+                            st.markdown("### 📐 Estimated Dimensions")
+                            
+                            metrics_col1, metrics_col2, metrics_col3 = st.columns(3)
+                            with metrics_col1:
+                                st.metric("Width", f"{width_meters:.2f} m")
+                            with metrics_col2:
+                                st.metric("Height", f"{height_meters:.2f} m")
+                            with metrics_col3:
+                                st.metric("Area", f"{(width_meters * height_meters):.2f} m²")
+                            
+                            # Add confidence indicator
+                            st.progress(0.6)
+                            st.caption("Confidence level: Medium (No person detected for scale)")
+                            
+                            st.warning("⚠️ These measurements are approximate. For more accurate results, include a person in the image.")
+                        else:
+                            st.error("❌ Could not detect room boundaries clearly. Please try with a different image.")
+    else:
+        # Show example/instructions when no image is uploaded
+        st.info("👆 Upload an image to get started!")
+        
+        with st.expander("📝 Tips for best results"):
+            st.markdown("""
+                - Include a person in the image for better accuracy
+                - Ensure good lighting conditions
+                - Capture clear views of walls and corners
+                - Avoid extreme angles
+                - Keep the image in focus
+            """)
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+opencv-python-headless
+numpy
+mediapipe
+Pillow