#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ car_measure.py -------------- 1. 读取显著性图 -> 阈值化生成纯白掩模 2. 形态学闭运算 -> 去噪 & 填孔 3. 计算 + 绘制外接矩形 (显示宽、高像素) 4. 霍夫圆检测 -> 仅画圆心 & 连线 + 距离标注 所有可视化与结果文件统一写到 out_dir """ import os import cv2 import numpy as np import matplotlib.pyplot as plt from PIL import Image, ImageDraw, ImageFont from u2net_saliency import generate_saliency_map # ---------------------------------------------------------------------- # -------------- 辅助：显著性图增强 & 调试可视化(可选) ------------------- # ---------------------------------------------------------------------- def enhance_saliency_map(saliency_map): """对显著性图做对比度增强、CLAHE、双边滤波——调参用，可删""" saliency_map = cv2.normalize(saliency_map, None, 0, 255, cv2.NORM_MINMAX) clahe = cv2.createCLAHE(clipLimit=3.0, tileGridSize=(8, 8)) saliency_map = clahe.apply(saliency_map) saliency_map = cv2.bilateralFilter(saliency_map, 9, 75, 75) return saliency_map # ---------------------------------------------------------------------- # ------------------------- 圆心检测 & 距离标注 ------------------------- # ---------------------------------------------------------------------- import os import cv2 import numpy as np def detect_and_draw_circles(salient_path, original_path, output_dir): """ 霍夫圆检测： - 在原图上：画圆心、连线、标注距离 - 在显著图上：画完整圆 和 圆心 —— 输出两张图： - detected_centers_salient.png - detected_centers_original.png """ salient_img = cv2.imread(salient_path, cv2.IMREAD_GRAYSCALE) original_img = cv2.imread(original_path) if salient_img is None or original_img is None: raise FileNotFoundError("Salient 或 original 图片路径有误") # 模糊+圆检测 blurred = cv2.GaussianBlur(salient_img, (9, 9), 2) circles = cv2.HoughCircles( blurred, cv2.HOUGH_GRADIENT, dp=1.2, minDist=290, param1=50, param2=17, minRadius=85, maxRadius=95 ) output_salient = cv2.cvtColor(salient_img, cv2.COLOR_GRAY2BGR) output_original = original_img.copy() if circles is not None: circles = np.uint16(np.around(circles)) centers = sorted([(c[0], c[1], c[2]) for c in circles[0]], key=lambda p: p[1], reverse=True)[:2] # 显著图上：画完整圆 + 圆心 for (x, y, r) in centers: cv2.circle(output_salient, (x, y), r, (0, 255, 0), 2) # 画圆边 cv2.circle(output_salient, (x, y), 3, (0, 0, 255), -1) # 画圆心 # 原图上：画圆心 + 连线 + 距离 if len(centers) >= 2: (x1, y1, _), (x2, y2, _) = centers cv2.circle(output_original, (x1, y1), 3, (0, 255, 0), -1) cv2.circle(output_original, (x2, y2), 3, (0, 255, 0), -1) cv2.line(output_original, (x1, y1), (x2, y2), (0, 0, 255), 2) dist = np.hypot(x1 - x2, y1 - y2) mid_pt = (int((x1 + x2) / 2), int((y1 + y2) / 2) - 10) cv2.putText(output_original, f"{dist:.1f}px", mid_pt, cv2.FONT_HERSHEY_SIMPLEX, 0.6, (255, 0, 0), 2) print(f"[Circle] 两圆心距离：{dist:.2f} px") else: print("[Circle] 检测到的圆少于 2 个") else: print("[Circle] 未检测到圆") os.makedirs(output_dir, exist_ok=True) cv2.imwrite(os.path.join(output_dir, 'detected_centers_salient.png'), output_salient) cv2.imwrite(os.path.join(output_dir, 'detected_centers_original.png'), output_original) # ---------------------------------------------------------------------- # ----------------------- 外接矩形 & 像素尺寸 --------------------------- # ---------------------------------------------------------------------- def _get_font(size): """跨平台字体加载""" for path in ("/usr/share/fonts/truetype/ubuntu/Ubuntu-B.ttf", "arial.ttf"): try: return ImageFont.truetype(path, size) except IOError: continue return ImageFont.load_default() def calculate_and_draw_bbox(mask_path, output_mask_path, original_path=None, output_original_path=None, display_width=None, display_height=None): """ 仅画一条顶边宽度线、一条右边高度线，并标注像素尺寸 """ # ---------- 获取外接框 ---------- mask_img = Image.open(mask_path).convert("L") arr = np.array(mask_img) coords = np.argwhere(arr > 0) if coords.size == 0: raise RuntimeError("掩模为空，无法测量尺寸") ymin, xmin = coords.min(axis=0) ymax, xmax = coords.max(axis=0) w_px = xmax - xmin + 1 h_px = ymax - ymin + 1 show_w = w_px if display_width is None else display_width show_h = h_px if display_height is None else display_height font = _get_font(34) # ---------- 在掩模图上绘制 ---------- vis_mask = mask_img.convert("RGB") draw_m = ImageDraw.Draw(vis_mask) # 顶边水平线 draw_m.line([(xmin, ymin), (xmax, ymin)], fill="red", width=4) # 右边垂直线 draw_m.line([(xmax, ymin), (xmax, ymax)], fill="red", width=4) # 文本位置计算 # 宽度文字：顶边中点偏上 10px；若超出图片则放到线下方 10px tx_w = int((xmin + xmax) / 2) - 40 ty_w = ymin - 40 if ty_w < 0: ty_w = ymin + 10 w_text = f"W:{int(round(show_w))}px" draw_m.text((tx_w, ty_w), w_text, fill="yellow", font=font) # 高度文字：右边线中点偏右 10px tx_h = xmax + 10 ty_h = int((ymin + ymax) / 2) - 20 h_text = f"H:{int(round(show_h))}px" draw_m.text((tx_h, ty_h), h_text, fill="yellow", font=font) vis_mask.save(output_mask_path) print(f"[Size] 掩模可视化已保存: {output_mask_path}") # ---------- 同步绘制到原图 ---------- if original_path and output_original_path: orig = Image.open(original_path).convert("RGB") draw_o = ImageDraw.Draw(orig) draw_o.line([(xmin, ymin), (xmax, ymin)], fill="red", width=4) draw_o.line([(xmax, ymin), (xmax, ymax)], fill="red", width=4) draw_o.text((tx_w, ty_w), w_text, fill="yellow", font=font) draw_o.text((tx_h, ty_h), h_text, fill="yellow", font=font) orig.save(output_original_path) print(f"[Size] 原图可视化已保存: {output_original_path}") return w_px, h_px # ---------------------------------------------------------------------- # ------------------------------- 主程序 ------------------------------- # ---------------------------------------------------------------------- if __name__ == '__main__': # ======================= 路径配置 ======================= triplets = [ # (标签, 原图路径, 显著 / 掩模 路径) ('front', './image/front_2.jpg', './saliency/front_2.jpg'), # 正面 ('rear', './image/rear_2.jpg', './saliency/rear_2.jpg'), # 后面 ('side', './image/side_2.jpg', './saliency/side_2.jpg'), # 侧面（做圆检测） ] out_dir = './result2' thresh_dir = './thresh2' os.makedirs(out_dir, exist_ok=True) os.makedirs(thresh_dir, exist_ok=True) for tag, orig_path, mask_src in triplets: # # ======================= 生成显著性图 （可以注释掉，在u2net_saliency生成）======================= print(f"处理 {tag} 图像中...") generate_saliency_map(orig_path, mask_src) # # ========================================================================================== # #======================= 阈值化处理 ======================= print(f'\n===== 处理 {tag} =====') # ---------- 1) 阈值化掩模 ---------- gray = cv2.imread(mask_src, cv2.IMREAD_GRAYSCALE) if gray is None: raise FileNotFoundError(mask_src) # Otsu 自动阈值 + 可选偏移（偏移范围建议0~20之间） offset = -10 # 负值让阈值变更敏感，保留更多区域 otsu_val, _ = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU) final_thresh = max(0, min(255, otsu_val + offset)) _, mask_bin = cv2.threshold(gray, final_thresh, 255, cv2.THRESH_BINARY) print(f'[Mask-{tag}] Otsu阈值={otsu_val:.1f}, 最终阈值={final_thresh}') # 可选的轻度闭运算（平滑小孔，不破坏细节） kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3)) mask_bin = cv2.morphologyEx(mask_bin, cv2.MORPH_CLOSE, kernel, iterations=1) # 保存阈值化结果 mask_path = os.path.join(thresh_dir, f'{tag}_1_mask_thresh.png') cv2.imwrite(mask_path, mask_bin) print(f'[Mask-{tag}] 阈值化掩模已保存: {mask_path}') # ---------- 2) 画长/宽线并写像素尺寸 ---------- mask_vis_path = os.path.join(out_dir, f'{tag}_size_lines_mask.png') orig_vis_path = os.path.join(out_dir, f'{tag}_size_lines_orig.png') calculate_and_draw_bbox( mask_path, # 纯白掩模 mask_vis_path, # 绘制后的掩模输出 orig_path, # 原图 orig_vis_path # 绘制后的原图输出 ) # ---------- 3) 仅“side”做圆心检测 ---------- if tag == 'side': detect_and_draw_circles(mask_src, orig_path, out_dir)