File size: 4,338 Bytes
875487a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 |
import streamlit as st
import cv2
import numpy as np
import pandas as pd
from PIL import Image
import torch
from torchvision.transforms import Compose, Resize, ToTensor, Normalize
from segment_anything import SamPredictor, sam_model_registry
# Set Streamlit configuration
st.set_page_config(page_title="Volume Estimator", layout="wide")
st.title("📦 Volume Estimation using SAM Segmentation + MiDaS Depth")
# Load SAM and MiDaS models
@st.cache_resource
def load_models():
sam_checkpoint = "C:/Users/Administrator/Desktop/streamlit_tl/models/sam_vit_h_4b8939.pth"
sam = sam_model_registry["vit_h"](checkpoint=sam_checkpoint).to("cuda" if torch.cuda.is_available() else "cpu")
predictor = SamPredictor(sam)
midas = torch.hub.load("intel-isl/MiDaS", "DPT_Large")
midas.eval()
midas_transform = Compose([
Resize(384),
ToTensor(),
Normalize(mean=[0.5]*3, std=[0.5]*3)
])
return predictor, midas, midas_transform
predictor, midas_model, midas_transform = load_models()
# Input source selection
source_option = st.radio("Select input source", ("Upload Image", "Use Webcam"))
uploaded_file = None
image_pil = None
if source_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 source_option == "Use Webcam":
run_camera = st.checkbox("Start Camera")
if run_camera:
cap = cv2.VideoCapture(0)
stframe = st.empty()
capture = False
while run_camera and cap.isOpened():
ret, frame = cap.read()
if not ret:
break
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
stframe.image(frame_rgb, caption="Live Camera Feed", channels="RGB")
if st.button("📸 Capture Frame"):
image_pil = Image.fromarray(frame_rgb)
run_camera = False
cap.release()
break
# Continue processing if we have an image
if image_pil:
image_np = np.array(image_pil)
img_h, img_w = image_np.shape[:2]
st.image(image_pil, caption="Selected Image", use_container_width=True)
# Real-world reference dimensions
real_image_width_cm = 100
real_image_height_cm = 75
assumed_max_depth_cm = 100
pixel_to_cm_x = real_image_width_cm / img_w
pixel_to_cm_y = real_image_height_cm / img_h
# SAM Segmentation
predictor.set_image(image_np)
masks, _, _ = predictor.predict(multimask_output=False)
# MiDaS Depth Estimation
input_tensor = midas_transform(image_pil).unsqueeze(0)
with torch.no_grad():
depth_prediction = midas_model(input_tensor).squeeze().cpu().numpy()
depth_resized = cv2.resize(depth_prediction, (img_w, img_h))
# Object volume computation
volume_data = []
for i, mask in enumerate(masks):
mask_np = mask
x, y, w, h = cv2.boundingRect(mask_np.astype(np.uint8))
width_px = w
height_px = h
width_cm = width_px * pixel_to_cm_x
height_cm = height_px * pixel_to_cm_y
depth_masked = depth_resized[mask_np > 0.5]
if depth_masked.size == 0:
continue
normalized_depth = (depth_masked - np.min(depth_resized)) / (np.max(depth_resized) - np.min(depth_resized) + 1e-6)
depth_cm = np.mean(normalized_depth) * assumed_max_depth_cm
volume_cm3 = round(depth_cm * width_cm * height_cm, 2)
volume_data.append({
"Object": f"Object #{i+1}",
"Length (Depth)": f"{round(depth_cm, 2)} cm",
"Breadth (Width)": f"{round(width_cm, 2)} cm",
"Height": f"{round(height_cm, 2)} cm",
"Volume": f"{volume_cm3} cm³"
})
# Display volume table
if volume_data:
df = pd.DataFrame(volume_data)
st.markdown("### 📊 Object Dimensions and Volume")
st.dataframe(df)
csv = df.to_csv(index=False).encode('utf-8')
st.download_button("📂 Download Volume Table as CSV", csv, "object_volumes_with_units.csv", "text/csv")
else:
st.warning("🚫 No objects were segmented.")
|