File size: 2,566 Bytes
b3652fb cd88622 02cc722 81def50 c74ea71 81def50 02cc722 bef39ed 81def50 02cc722 c74ea71 81def50 c74ea71 cd88622 b3652fb 81def50 b3652fb 81def50 c74ea71 81def50 cd88622 c74ea71 2d5e944 c74ea71 81def50 c74ea71 3412511 c74ea71 cd88622 903cef3 cd88622 b3652fb 81def50 b3652fb 81def50 b3652fb 81def50 b3652fb 81def50 f6e7520 81def50 |
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 |
import io
import time
import numpy as np
import cv2
import torch
from transformers import AutoImageProcessor, ZoeDepthForDepthEstimation
from fastapi import FastAPI, File, UploadFile
from PIL import Image
import uvicorn
app = FastAPI()
# 🟢 Tải mô hình ZoeDepth từ Hugging Face
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
image_processor = AutoImageProcessor.from_pretrained("Intel/zoedepth-nyu-kitti")
model = ZoeDepthForDepthEstimation.from_pretrained("Intel/zoedepth-nyu-kitti").to(device)
model.eval()
@app.post("/analyze_path/")
async def analyze_path(file: UploadFile = File(...)):
# 🟢 Đọc file ảnh từ ESP32
image_bytes = await file.read()
image = Image.open(io.BytesIO(image_bytes)).convert("RGB")
# 🟢 Chuẩn bị ảnh cho mô hình ZoeDepth
inputs = image_processor(images=image, return_tensors="pt").to(device)
# 🟢 Bắt đầu đo thời gian dự đoán Depth Map
start_time = time.time()
# 🟢 Dự đoán Depth Map với ZoeDepth
with torch.no_grad():
outputs = model(**inputs)
# 🟢 Xử lý ảnh sau khi dự đoán
post_processed_output = image_processor.post_process_depth_estimation(
outputs,
source_sizes=[(image.height, image.width)],
)
predicted_depth = post_processed_output[0]["predicted_depth"]
depth_map = predicted_depth * 255 / predicted_depth.max()
depth_map = depth_map.detach().cpu().numpy().astype("uint8")
end_time = time.time()
print(f"⏳ ZoeDepth xử lý trong {end_time - start_time:.4f} giây")
# 🟢 Đo thời gian xử lý đường đi
start_detect_time = time.time()
command = detect_path(depth_map)
end_detect_time = time.time()
print(f"⏳ detect_path() xử lý trong {end_detect_time - start_detect_time:.4f} giây")
return {"command": command}
def detect_path(depth_map):
"""Phân tích đường đi từ ảnh Depth Map"""
h, w = depth_map.shape
center_x = w // 2
scan_y = h - 20 # Quét dòng gần đáy ảnh
left_region = np.mean(depth_map[scan_y, :center_x])
right_region = np.mean(depth_map[scan_y, center_x:])
center_region = np.mean(depth_map[scan_y, center_x - 20:center_x + 20])
if center_region > 200:
return "forward"
elif left_region > right_region:
return "left"
elif right_region > left_region:
return "right"
else:
return "backward"
# 🟢 Chạy server FastAPI
if __name__ == "__main__":
uvicorn.run(app, host="0.0.0.0", port=7860)
|