Spaces:
Runtime error
Runtime error
File size: 3,373 Bytes
7500064 581a214 7500064 581a214 7500064 581a214 7500064 581a214 f48d218 7500064 581a214 7500064 581a214 7500064 581a214 7500064 581a214 7500064 581a214 7500064 581a214 7500064 581a214 7500064 581a214 7500064 |
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 |
import gradio as gr
import torch
import numpy as np
import cv2
from PIL import Image
import pandas as pd
from torchvision.transforms import Compose, Resize, ToTensor, Normalize
from segment_anything import SamPredictor, sam_model_registry
import os
# Load SAM and MiDaS models
def load_models():
sam_checkpoint = "sam_vit_b_01ec64.pth"
if not os.path.exists(sam_checkpoint):
raise FileNotFoundError("Please upload the SAM checkpoint file to the working directory.")
device = "cuda" if torch.cuda.is_available() else "cpu"
sam = sam_model_registry["vit_h"](checkpoint=sam_checkpoint).to(device)
predictor = SamPredictor(sam)
midas = torch.hub.load("intel-isl/MiDaS", "DPT_Large")
midas.eval().to(device)
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()
# Processing function
def process_image(image_pil):
image_np = np.array(image_pil)
img_h, img_w = image_np.shape[:2]
# Real-world reference dimensions (adjust as needed)
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).to(next(midas_model.parameters()).device)
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):
x, y, w, h = cv2.boundingRect(mask.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 > 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([
f"Object #{i+1}",
round(depth_cm, 2),
round(width_cm, 2),
round(height_cm, 2),
volume_cm3
])
if not volume_data:
return image_pil, "No objects segmented."
df = pd.DataFrame(volume_data, columns=["Object", "Length (Depth) cm", "Breadth (Width) cm", "Height cm", "Volume cm³"])
return image_pil, df
# Gradio Interface
with gr.Blocks() as demo:
gr.Markdown("# 📦 Volume Estimation using SAM + MiDaS")
with gr.Row():
image_input = gr.Image(type="pil", label="Upload Image")
run_btn = gr.Button("Estimate Volume")
with gr.Row():
output_image = gr.Image(label="Original Image")
volume_table = gr.Dataframe(headers=["Object", "Length (Depth) cm", "Breadth (Width) cm", "Height cm", "Volume cm³"])
run_btn.click(fn=process_image, inputs=image_input, outputs=[output_image, volume_table])
demo.launch()
|