import cv2 import numpy as np def detect_arrow_direction(image, observe=False, delay=500): """ 从图像中提取绿色箭头并判断其指向方向(左或右) 参数: image: 输入图像,可以是文件路径或者已加载的图像数组 observe: 是否输出中间状态信息和可视化结果,默认为False delay: 展示每个步骤的等待时间(毫秒),默认为500ms 返回: direction: 字符串,"left"表示左箭头,"right"表示右箭头,"unknown"表示无法确定 """ # 如果输入是字符串(文件路径),则加载图像 if isinstance(image, str): img = cv2.imread(image) else: img = image.copy() if img is None: print("无法加载图像") return "unknown" if observe: print("步骤1: 原始图像已加载") cv2.imshow("原始图像", img) cv2.waitKey(delay) # 转换到HSV颜色空间以便更容易提取绿色 hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV) if observe: print("步骤2: 转换到HSV颜色空间") cv2.imshow("HSV图像", hsv) cv2.waitKey(delay) # 绿色的HSV范围 # 调整这些值以匹配图像中绿色的具体色调·· lower_green = np.array([40, 50, 50]) upper_green = np.array([80, 255, 255]) # 创建绿色的掩码 mask = cv2.inRange(hsv, lower_green, upper_green) if observe: print("步骤3: 创建绿色掩码") cv2.imshow("绿色掩码", mask) cv2.waitKey(delay) # 应用掩码,只保留绿色部分 green_only = cv2.bitwise_and(img, img, mask=mask) if observe: print("步骤4: 提取绿色部分") cv2.imshow("只保留绿色", green_only) cv2.waitKey(delay) # 将掩码转为灰度图 gray = mask.copy() # 查找轮廓 contours, _ = cv2.findContours(gray, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) # 如果没有找到轮廓,返回未知 if not contours: if observe: print("未找到轮廓") return "unknown" if observe: print(f"步骤5: 找到 {len(contours)} 个轮廓") contour_img = img.copy() cv2.drawContours(contour_img, contours, -1, (0, 255, 0), 2) cv2.imshow("所有轮廓", contour_img) cv2.waitKey(delay) # 找到最大的轮廓(假设是箭头) max_contour = max(contours, key=cv2.contourArea) if observe: print("步骤6: 提取最大轮廓") max_contour_img = img.copy() cv2.drawContours(max_contour_img, [max_contour], -1, (0, 0, 255), 2) cv2.imshow("最大轮廓", max_contour_img) cv2.waitKey(delay) # 使用多边形近似轮廓 epsilon = 0.02 * cv2.arcLength(max_contour, True) approx = cv2.approxPolyDP(max_contour, epsilon, True) if observe: print(f"步骤7: 多边形近似,顶点数: {len(approx)}") approx_img = img.copy() cv2.drawContours(approx_img, [approx], -1, (255, 0, 0), 2) cv2.imshow("多边形近似", approx_img) cv2.waitKey(delay) # 计算凸包 hull = cv2.convexHull(max_contour) if observe: print("步骤8: 计算凸包") hull_img = img.copy() cv2.drawContours(hull_img, [hull], -1, (0, 255, 0), 2) cv2.imshow("凸包", hull_img) cv2.waitKey(delay) # 计算凸缺陷 if len(max_contour) > 3: defects = cv2.convexityDefects(max_contour, cv2.convexHull(max_contour, returnPoints=False)) else: if observe: print("轮廓点太少,无法准确判断") return "unknown" # 轮廓点太少,无法准确判断 if defects is None: if observe: print("未找到凸缺陷") return "unknown" if observe: print(f"步骤9: 计算凸缺陷,找到 {defects.shape[0]} 个缺陷点") defect_img = img.copy() for i in range(defects.shape[0]): s, e, f, d = defects[i, 0] start = tuple(max_contour[s][0]) end = tuple(max_contour[e][0]) far = tuple(max_contour[f][0]) cv2.circle(defect_img, far, 5, (0, 0, 255), -1) cv2.imshow("凸缺陷", defect_img) cv2.waitKey(delay) # 获取轮廓的最小外接矩形 rect = cv2.minAreaRect(max_contour) box = cv2.boxPoints(rect) box = np.int0(box) if observe: print("步骤10: 获取最小外接矩形") rect_img = img.copy() cv2.drawContours(rect_img, [box], 0, (255, 0, 0), 2) cv2.imshow("最小外接矩形", rect_img) cv2.waitKey(delay) # 获取中心点和角度 center = rect[0] angle = rect[2] if observe: print(f"矩形中心: {center}, 角度: {angle}") # 计算轮廓的矩,用于确定箭头方向 M = cv2.moments(max_contour) # 避免除以零 if M["m00"] != 0: cx = int(M["m10"] / M["m00"]) cy = int(M["m01"] / M["m00"]) else: cx, cy = int(center[0]), int(center[1]) if observe: print(f"步骤11: 计算质心 - 坐标: ({cx}, {cy})") center_img = img.copy() cv2.circle(center_img, (cx, cy), 5, (255, 0, 0), -1) cv2.imshow("质心", center_img) cv2.waitKey(delay) # 改进的箭头尖端检测算法 # 1. 找到所有凸缺陷点 defect_points = [] for i in range(defects.shape[0]): s, e, f, d = defects[i, 0] start = tuple(max_contour[s][0]) end = tuple(max_contour[e][0]) far = tuple(max_contour[f][0]) # 计算缺陷点到中心的距离 dist = np.sqrt((far[0] - cx) ** 2 + (far[1] - cy) ** 2) if observe: print(f"缺陷点 {i}: 位置 {far}, 到中心距离: {dist:.2f}") # 记录凸缺陷点及其距离 defect_points.append({ 'point': far, 'distance': dist, 'start': start, 'end': end }) # 没有缺陷点,使用矩形判断 if not defect_points: # 判断逻辑将在后面处理 arrow_tip = None else: # 2. 按距离对缺陷点排序 defect_points.sort(key=lambda x: x['distance'], reverse=True) # 3. 获取最远的几个缺陷点(可能的尖端候选) top_n = min(3, len(defect_points)) candidates = defect_points[:top_n] # 4. 分析这些点的位置分布 left_candidates = [p for p in candidates if p['point'][0] < cx] right_candidates = [p for p in candidates if p['point'][0] >= cx] # 5. 根据候选点的分布判断箭头朝向 if len(left_candidates) > len(right_candidates): # 左侧候选点更多,箭头可能指向左边 arrow_tip = max(left_candidates, key=lambda x: x['distance'])['point'] arrow_direction = "left" elif len(right_candidates) > len(left_candidates): # 右侧候选点更多,箭头可能指向右边 arrow_tip = max(right_candidates, key=lambda x: x['distance'])['point'] arrow_direction = "right" else: # 候选点分布均衡,使用最远的点 arrow_tip = candidates[0]['point'] # 根据最远点的位置判断 if arrow_tip[0] < cx: arrow_direction = "left" else: arrow_direction = "right" if observe and arrow_tip: print(f"步骤12: 找到可能的箭头尖端 - 位置: {arrow_tip}") tip_img = img.copy() cv2.circle(tip_img, arrow_tip, 8, (0, 255, 255), -1) cv2.line(tip_img, (cx, cy), arrow_tip, (255, 0, 255), 2) cv2.imshow("箭头尖端", tip_img) cv2.waitKey(delay) # 使用多种特征综合判断箭头方向 if arrow_tip is None: # 如果没有找到明显的箭头尖端,使用最小外接矩形来判断 width = rect[1][0] height = rect[1][1] if observe: print(f"未找到明显尖端,使用矩形判断 - 宽: {width}, 高: {height}") # 矩形的方向向量 if width > height: # 水平箭头 # 考虑角度的定义 if angle > 45: arrow_direction = "left" else: arrow_direction = "right" else: # 垂直箭头,不在我们的考虑范围内 if observe: print("垂直箭头,不在考虑范围") return "unknown" else: # 已经在上面的代码中确定了方向 pass # 附加检查:计算轮廓边界上的点,确认箭头的形状特征 x, y, w, h = cv2.boundingRect(max_contour) aspect_ratio = float(w) / h # 计算轮廓周长和面积 perimeter = cv2.arcLength(max_contour, True) area = cv2.contourArea(max_contour) # 计算轮廓的形状复杂度 complexity = perimeter / (4 * np.sqrt(area)) if observe: print(f"轮廓分析 - 宽高比: {aspect_ratio:.2f}, 复杂度: {complexity:.2f}") # 箭头形状特征检查 # 一般来说,箭头的复杂度会在一定范围内 if 1.1 < complexity < 3.0: # 根据形状特征进一步确认方向判断 # 使用质心位置相对于轮廓边界的偏移 relative_cx = (cx - x) / w if observe: print(f"质心相对位置: {relative_cx:.2f}") # 如果质心偏向左侧,箭头可能指向右侧 # 如果质心偏向右侧,箭头可能指向左侧 # 这是一个启发式规则,可能需要根据具体箭头形状调整 if relative_cx < 0.4: # 质心在左侧,可能是右箭头 if arrow_direction == "left": # 当前方法判断为左,但质心位置特征表明可能是右 # 增加额外的检查 if aspect_ratio > 1.5: # 宽大于高 arrow_direction = "right" elif relative_cx > 0.6: # 质心在右侧,可能是左箭头 if arrow_direction == "right": # 当前方法判断为右,但质心位置特征表明可能是左 if aspect_ratio > 1.5: # 宽大于高 arrow_direction = "left" if observe: print(f"基于综合特征判断: {arrow_direction}箭头") return arrow_direction def visualize_arrow_detection(image, save_path=None, observe=False, delay=500): """ 可视化箭头检测过程,显示中间结果 参数: image: 输入图像,可以是文件路径或者已加载的图像数组 save_path: 保存结果图像的路径(可选) observe: 是否输出中间状态信息和可视化结果,默认为False delay: 展示每个步骤的等待时间(毫秒),默认为500ms """ # 如果输入是字符串(文件路径),则加载图像 if isinstance(image, str): img = cv2.imread(image) else: img = image.copy() if img is None: print("无法加载图像") return if observe: print("\n开始可视化箭头检测过程") # 转换到HSV颜色空间 hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV) # 绿色的HSV范围 lower_green = np.array([40, 50, 50]) upper_green = np.array([80, 255, 255]) # 创建绿色的掩码 mask = cv2.inRange(hsv, lower_green, upper_green) # 应用掩码,只保留绿色部分 green_only = cv2.bitwise_and(img, img, mask=mask) # 查找轮廓 contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) # 创建输出图像 output = img.copy() # 如果找到轮廓,绘制最大轮廓 if contours: max_contour = max(contours, key=cv2.contourArea) cv2.drawContours(output, [max_contour], -1, (0, 0, 255), 2) # 获取轮廓的最小外接矩形 rect = cv2.minAreaRect(max_contour) box = cv2.boxPoints(rect) box = np.int0(box) cv2.drawContours(output, [box], 0, (255, 0, 0), 2) # 计算轮廓的矩 M = cv2.moments(max_contour) # 避免除以零 if M["m00"] != 0: cx = int(M["m10"] / M["m00"]) cy = int(M["m01"] / M["m00"]) # 绘制中心点 cv2.circle(output, (cx, cy), 5, (255, 0, 0), -1) # 绘制凸包 hull = cv2.convexHull(max_contour) cv2.drawContours(output, [hull], 0, (0, 255, 0), 2) # 绘制凸缺陷 if len(max_contour) > 3: defects = cv2.convexityDefects(max_contour, cv2.convexHull(max_contour, returnPoints=False)) if defects is not None: for i in range(defects.shape[0]): s, e, f, d = defects[i, 0] start = tuple(max_contour[s][0]) end = tuple(max_contour[e][0]) far = tuple(max_contour[f][0]) cv2.circle(output, far, 5, (0, 0, 255), -1) # 在凸缺陷点绘制红色圆点 # 获取箭头方向 direction = detect_arrow_direction(img, observe=observe, delay=delay) # 在图像上添加方向文本 cv2.putText(output, f"Direction: {direction}", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2) # 如果提供了保存路径,保存结果图像 if save_path: cv2.imwrite(save_path, output) if observe: print(f"结果已保存到: {save_path}") # 创建一个包含所有图像的窗口 result = np.hstack((img, green_only, output)) # 调整大小以便查看 scale_percent = 50 # 缩放到原来的50% width = int(result.shape[1] * scale_percent / 100) height = int(result.shape[0] * scale_percent / 100) dim = (width, height) resized = cv2.resize(result, dim, interpolation=cv2.INTER_AREA) # 显示结果 cv2.imshow('Arrow Detection Process', resized) cv2.waitKey(0) cv2.destroyAllWindows() # 用法示例 if __name__ == "__main__": # 替换为实际图像路径 image_path = "path/to/arrow/image.png" # 检测箭头方向,使用较长的延迟时间(1500毫秒) direction = detect_arrow_direction(image_path, observe=True, delay=1500) print(f"检测到的箭头方向: {direction}") # 可视化检测过程,使用较长的延迟时间 visualize_arrow_detection(image_path, observe=True, delay=1500)