Upload 2 files

app.py

@@ -0,0 +1,129 @@
+import streamlit as st
+st.set_page_config(page_title="Object Volume Estimator", layout="wide")
+
+import cv2
+import torch
+import numpy as np
+from PIL import Image
+import pandas as pd
+from ultralytics import YOLO
+from torchvision.transforms import Compose, Resize, ToTensor, Normalize
+
+# Load models
+@st.cache_resource
+def load_models():
+    yolo = YOLO("yolov8n.pt")
+    midas = torch.hub.load("intel-isl/MiDaS", "DPT_Large")
+    midas.eval()
+    transform = Compose([
+        Resize(384),
+        ToTensor(),
+        Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
+    ])
+    return yolo, midas, transform
+
+yolo_model, midas_model, midas_transform = load_models()
+
+# --- Streamlit App ---
+st.title("Object Dimension & Volume Estimator")
+
+# 📸 Image Source Selection
+option = st.radio("Choose Image Source:", ("📤 Upload Image", "📸 Use Camera"))
+
+# Mode Selection
+mode = st.selectbox("Select Image Type:", ["2D RGB Image", "RGB + Depth Image"])
+
+image_pil = None
+
+if option == "📤 Upload Image":
+    uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
+    if uploaded_file:
+        image_pil = Image.open(uploaded_file).convert("RGB")
+
+elif option == "📸 Use Camera":
+    camera_input = st.camera_input("Take a picture")
+    if camera_input:
+        image_pil = Image.open(camera_input).convert("RGB")
+
+# Upload depth image if RGB + Depth selected
+depth_map = None
+if mode == "RGB + Depth Image" and image_pil is not None:
+    depth_file = st.file_uploader("Upload corresponding Depth Map (grayscale image)", type=["png", "jpg", "jpeg", "tiff"])
+    if depth_file:
+        depth_map = np.array(Image.open(depth_file).convert("L"))
+
+# Proceed if we have an image
+if image_pil is not None:
+    # Convert to OpenCV format
+    image_cv = np.array(image_pil)
+    image_cv = cv2.cvtColor(image_cv, cv2.COLOR_RGB2BGR)
+    img_h, img_w = image_cv.shape[:2]
+    st.image(image_pil, caption="Input Image", use_container_width=True)
+
+    # Store detected object data
+    object_data = []
+
+    # 🔍 YOLO Object Detection
+    results = yolo_model(image_cv)
+
+    # 📏 Depth Estimation
+    if mode == "2D RGB Image":
+        input_tensor = midas_transform(image_pil).unsqueeze(0)
+        with torch.no_grad():
+            estimated_depth = midas_model(input_tensor).squeeze().cpu().numpy()
+        depth_map_resized = cv2.resize(estimated_depth, (img_w, img_h))
+    else:
+        if depth_map is not None:
+            depth_map_resized = cv2.resize(depth_map, (img_w, img_h))
+        else:
+            st.error("Please upload a corresponding depth map for 3D images.")
+            st.stop()
+
+    # 🎯 Process each detection
+    for r in results:
+        for box in r.boxes:
+            x1, y1, x2, y2 = map(int, box.xyxy[0])
+            width = x2 - x1
+            height = y2 - y1
+            region = depth_map_resized[y1:y2, x1:x2]
+            if region.size == 0:
+                continue
+            depth = np.mean(region)
+            volume = round(depth * width * height, 2)
+
+            # Draw bounding box & label
+            cv2.rectangle(image_cv, (x1, y1), (x2, y2), (0, 255, 0), 2)
+            label = f"L×B×H: {depth:.2f}×{width}×{height} | V: {volume}"
+            cv2.putText(image_cv, label, (x1, y1 - 10),
+                        cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 0), 2)
+
+            # Store data for CSV
+            object_data.append({
+                "Length": round(depth, 2),
+                "Breadth": int(width),
+                "Height": int(height),
+                "Volume": volume
+            })
+
+            # Show object details
+            st.markdown(f"**🧠 Object Detected:**")
+            st.write(f"📏 Length × Breadth × Height: {depth:.2f} × {width} × {height}")
+            st.write(f"📦 Estimated Volume: {volume} (relative units³)")
+
+    # Show annotated image
+    result_img = cv2.cvtColor(image_cv, cv2.COLOR_BGR2RGB)
+    st.image(result_img, caption="Detected Dimensions", use_container_width=True)
+
+    # Show table & CSV download if data exists
+    if object_data:
+        df = pd.DataFrame(object_data)
+        st.markdown("### 📋 Detected Objects Table")
+        st.dataframe(df)
+
+        csv = df.to_csv(index=False).encode('utf-8')
+        st.download_button(
+            label="📥 Download Results as CSV",
+            data=csv,
+            file_name='object_dimensions_volume.csv',
+            mime='text/csv',
+        )

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+torch
+torchvision
+ultralytics
+opencv-python
+timm