170 lines
5.9 KiB
Python
170 lines
5.9 KiB
Python
import cv2
|
||
import numpy as np
|
||
from pathlib import Path
|
||
from ultralytics import YOLO
|
||
|
||
# --------------------
|
||
# 配置参数
|
||
# --------------------
|
||
IMAGE_PATH = "/home/hx/yolo/yemian/test_image/1.png"
|
||
MODEL_PATH = "best.pt"
|
||
OUTPUT_PATH = "./output/single_result.jpg"
|
||
|
||
TARGET_SIZE = 640
|
||
|
||
# 新增：用于计算像素到实际尺寸换算比例的函数
|
||
def calculate_pixel_to_real_ratio(real_length_mm, pixel_length):
|
||
"""
|
||
计算像素到实际尺寸的换算比例。
|
||
参数:
|
||
- real_length_mm: 实际物理长度（例如：毫米）
|
||
- pixel_length: 对应的实际物理长度在图像中的像素数
|
||
返回:
|
||
- PIXEL_TO_REAL_RATIO: 每个像素代表的实际物理长度（单位：mm/像素）
|
||
"""
|
||
if pixel_length == 0:
|
||
raise ValueError("像素长度不能为0")
|
||
return real_length_mm / pixel_length
|
||
|
||
|
||
# 在主函数infer_single_image之前设置一个默认值
|
||
PIXEL_TO_REAL_RATIO = 1.0 # 默认值，之后会被真实计算的比例替换
|
||
|
||
# 假设我们知道某物体的真实长度是real_length_mm毫米，在图像中占pixel_length像素
|
||
real_length_mm = 100 # 物体的实际长度（单位：毫米）
|
||
pixel_length = 200 # 物体在图像中的像素长度
|
||
|
||
try:
|
||
PIXEL_TO_REAL_RATIO = calculate_pixel_to_real_ratio(real_length_mm, pixel_length)
|
||
print(f"换算比例已设定: {PIXEL_TO_REAL_RATIO:.4f} mm/像素")
|
||
except ValueError as e:
|
||
print(e)
|
||
|
||
# 全局 ROI 定义：(x, y, w, h)
|
||
ROIS = [
|
||
(859, 810, 696, 328),
|
||
]
|
||
|
||
# --------------------
|
||
# 辅助函数（保持不变）
|
||
# --------------------
|
||
def select_edge_corners(corners, w, left_ratio=0.2, right_ratio=0.2, y_var_thresh=5):
|
||
if corners is None:
|
||
return [], []
|
||
corners = np.int32(corners).reshape(-1, 2)
|
||
left_thresh = int(w * left_ratio)
|
||
right_thresh = w - int(w * right_ratio)
|
||
|
||
left_candidates = corners[corners[:, 0] <= left_thresh]
|
||
right_candidates = corners[corners[:, 0] >= right_thresh]
|
||
|
||
def filter_by_y_variation(pts):
|
||
if len(pts) < 2:
|
||
return pts
|
||
pts_sorted = pts[np.argsort(pts[:, 1])]
|
||
diffs = np.abs(np.diff(pts_sorted[:, 1]))
|
||
keep_idx = np.where(diffs > y_var_thresh)[0]
|
||
selected = [pts_sorted[i] for i in keep_idx] + [pts_sorted[i + 1] for i in keep_idx]
|
||
return np.array(selected) if len(selected) > 0 else pts_sorted
|
||
|
||
left_final = filter_by_y_variation(left_candidates)
|
||
right_final = filter_by_y_variation(right_candidates)
|
||
return left_final, right_final
|
||
|
||
|
||
def fit_line_with_outlier_removal(pts, dist_thresh=10):
|
||
if pts is None or len(pts) < 2:
|
||
return None, pts
|
||
pts = np.array(pts)
|
||
x, y = pts[:, 0], pts[:, 1]
|
||
m, b = np.polyfit(y, x, 1) # x = m*y + b
|
||
x_fit = m * y + b
|
||
dists = np.abs(x - x_fit)
|
||
mask = dists < dist_thresh
|
||
if mask.sum() < 2:
|
||
return (m, b), pts
|
||
m, b = np.polyfit(y[mask], x[mask], 1)
|
||
inliers = np.stack([x[mask], y[mask]], axis=1)
|
||
return (m, b), inliers
|
||
|
||
|
||
# --------------------
|
||
# 单图推理主函数
|
||
# --------------------
|
||
def infer_single_image(image_path, model_path, output_path):
|
||
orig_img = cv2.imread(str(image_path))
|
||
if orig_img is None:
|
||
print(f"❌ 无法读取图像: {image_path}")
|
||
return None
|
||
|
||
overlay_img = orig_img.copy()
|
||
x_diff_pixel = None # 像素单位的差值
|
||
|
||
model = YOLO(model_path)
|
||
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
|
||
|
||
for idx, (x, y, w, h) in enumerate(ROIS):
|
||
roi_img = orig_img[y:y+h, x:x+w]
|
||
resized_img = cv2.resize(roi_img, (TARGET_SIZE, TARGET_SIZE))
|
||
|
||
results = model(source=resized_img, imgsz=TARGET_SIZE, verbose=False)
|
||
result = results[0]
|
||
|
||
if result.masks is None or len(result.masks.data) == 0:
|
||
print("❌ 未检测到 mask")
|
||
continue
|
||
|
||
mask = result.masks.data[0].cpu().numpy()
|
||
mask_bin = (mask > 0.5).astype(np.uint8)
|
||
mask_bin = cv2.resize(mask_bin, (w, h), interpolation=cv2.INTER_NEAREST)
|
||
|
||
color_mask = np.zeros_like(roi_img, dtype=np.uint8)
|
||
color_mask[mask_bin == 1] = (0, 255, 0)
|
||
overlay_img[y:y+h, x:x+w] = cv2.addWeighted(roi_img, 0.7, color_mask, 0.3, 0)
|
||
|
||
mask_gray = (mask_bin * 255).astype(np.uint8)
|
||
corners = cv2.goodFeaturesToTrack(mask_gray, maxCorners=200, qualityLevel=0.01, minDistance=5)
|
||
|
||
left_pts, right_pts = select_edge_corners(corners, w)
|
||
left_line, _ = fit_line_with_outlier_removal(left_pts)
|
||
right_line, _ = fit_line_with_outlier_removal(right_pts)
|
||
|
||
if left_line and right_line:
|
||
y_ref = h * 0.6
|
||
m1, b1 = left_line
|
||
m2, b2 = right_line
|
||
x1 = m1 * y_ref + b1
|
||
x2 = m2 * y_ref + b2
|
||
x_diff_pixel = abs(x2 - x1)
|
||
|
||
# 绘制参考线和文字（仍用像素值显示）
|
||
cv2.line(overlay_img[y:y+h, x:x+w], (0, int(y_ref)), (w, int(y_ref)), (0, 255, 255), 2)
|
||
cv2.putText(overlay_img[y:y+h, x:x+w],
|
||
f"x_diff={x_diff_pixel:.1f}px",
|
||
(10, 30), cv2.FONT_HERSHEY_SIMPLEX,
|
||
1, (0, 255, 255), 2)
|
||
|
||
# 绘制左右拟合线
|
||
for (m, b), color in [(left_line, (0, 0, 255)), (right_line, (255, 0, 0))]:
|
||
y1, y2 = 0, h
|
||
x1_line, x2_line = int(m * y1 + b), int(m * y2 + b)
|
||
cv2.line(overlay_img[y:y+h, x:x+w], (x1_line, y1), (x2_line, y2), color, 3)
|
||
|
||
cv2.imwrite(output_path, overlay_img)
|
||
print(f"✅ 结果已保存至: {output_path}")
|
||
|
||
if x_diff_pixel is not None:
|
||
x_diff_real = x_diff_pixel * PIXEL_TO_REAL_RATIO
|
||
print(f"📊 x差值（像素） = {x_diff_pixel:.2f} px")
|
||
print(f"📏 x差值（实际） = {x_diff_real:.2f} mm") # 可改为 cm 或其他单位
|
||
else:
|
||
print("⚠️ 未能计算 x 差值")
|
||
|
||
return x_diff_pixel
|
||
|
||
|
||
# =====================
|
||
# 运行入口
|
||
# =====================
|
||
if __name__ == "__main__":
|
||
infer_single_image(IMAGE_PATH, MODEL_PATH, OUTPUT_PATH) |