bushu

angle_base_obb/angle_caculate.py

@@ -25,6 +25,7 @@ def predict_obb_best_angle(model_path, image_path, save_path=None):
     # 3. 推理 OBB
     results = model(img, save=False, imgsz=640, conf=0.5, mode='obb')
     result = results[0]
+    print(result)
 
     # 4. 可视化
     annotated_img = result.plot()
@@ -62,8 +63,8 @@ def predict_obb_best_angle(model_path, image_path, save_path=None):
 
 # ------------------- 测试 -------------------
 if __name__ == "__main__":
-    weight_path = r'best.pt'
-    image_path = r"./test_image/3.jpg"
+    weight_path = r'obb.pt'
+    image_path = r"./test_image/7.jpg"
     save_path = "./inference_results/detected_3.jpg"
 
     #angle_deg, annotated_img = predict_obb_best_angle(weight_path, image_path, save_path)

angle_base_obb/angle_caculate_file.py

@@ -91,8 +91,8 @@ def process_obb_images(model_path, image_dir, output_dir="./inference_results",
 
 # ------------------- 测试调用 -------------------
 if __name__ == "__main__":
-    MODEL_PATH = r'best.pt'
-    IMAGE_SOURCE_DIR = r"./test_image"
+    MODEL_PATH = r'obb.pt'
+    IMAGE_SOURCE_DIR = r"/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/obb4/val"
     OUTPUT_DIR = "./inference_results"
 
     results = process_obb_images(MODEL_PATH, IMAGE_SOURCE_DIR, OUTPUT_DIR)

angle_base_obb/label_view.py

@@ -0,0 +1,120 @@
+import cv2
+import numpy as np
+import matplotlib.pyplot as plt
+import os
+
+# =========================
+# 强制使用非 GUI 后端（关键！）
+# =========================
+import matplotlib
+
+matplotlib.use('Agg')  # 必须在 import pyplot 之前设置
+
+
+def visualize_obb(image_path, label_path, output_dir="output_visualizations"):
+    """
+    可视化图片及其 OBB 标签，并保存结果图像到指定目录。
+
+    :param image_path: 图片路径
+    :param label_path: 标签路径
+    :param output_dir: 输出目录（自动创建）
+    """
+    # 读取图像
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"❌ 无法读取图像: {image_path}")
+        return
+
+    h, w = image.shape[:2]
+    print(f"✅ 正在处理图像: {os.path.basename(image_path)} | 尺寸: {w} x {h}")
+
+    # 创建用于绘图的副本（BGR → 绘图用）
+    img_draw = image.copy()
+
+    # 读取标签
+    try:
+        with open(label_path, 'r') as f:
+            lines = f.readlines()
+    except Exception as e:
+        print(f"❌ 无法读取标签文件 {label_path}: {e}")
+        return
+
+    for line in lines:
+        parts = line.strip().split()
+        if len(parts) < 9:
+            print(f"⚠️ 跳过无效标签行: {line}")
+            continue
+
+        # 解析：class_id x1 y1 x2 y2 x3 y3 x4 y4
+        try:
+            points = np.array([float(x) for x in parts[1:9]]).reshape(4, 2)
+        except:
+            print(f"⚠️ 坐标解析失败: {line}")
+            continue
+
+        # 归一化坐标 → 像素坐标
+        points[:, 0] *= w  # x
+        points[:, 1] *= h  # y
+        points = np.int32(points)
+
+        # 绘制四边形（绿色）
+        cv2.polylines(img_draw, [points], isClosed=True, color=(0, 255, 0), thickness=3)
+
+        # 绘制顶点（红色圆圈）
+        for (x, y) in points:
+            cv2.circle(img_draw, (x, y), 6, (0, 0, 255), -1)  # 红色实心圆
+
+    # 转为 RGB 用于 matplotlib 保存
+    img_rgb = cv2.cvtColor(img_draw, cv2.COLOR_BGR2RGB)
+
+    # 创建输出目录
+    os.makedirs(output_dir, exist_ok=True)
+
+    # 生成输出路径
+    filename = os.path.splitext(os.path.basename(image_path))[0] + "_vis.png"
+    output_path = os.path.join(output_dir, filename)
+
+    # 使用 matplotlib 保存图像（不显示）
+    plt.figure(figsize=(16, 9), dpi=100)
+    plt.imshow(img_rgb)
+    plt.title(f"OBB Visualization - {os.path.basename(image_path)}", fontsize=14)
+    plt.axis('off')
+    plt.tight_layout()
+    plt.savefig(output_path, bbox_inches='tight', pad_inches=0)
+    plt.close()  # 释放内存
+
+    print(f"✅ 可视化结果已保存: {output_path}")
+
+
+def process_directory(directory):
+    """
+    遍历目录，处理所有图片和对应的 .txt 标签文件
+    """
+    print(f"🔍 开始处理目录: {directory}")
+    count = 0
+
+    for filename in os.listdir(directory):
+        if filename.lower().endswith(('.png', '.jpg', '.jpeg', '.bmp', '.tiff')):
+            image_path = os.path.join(directory, filename)
+            label_path = os.path.splitext(image_path)[0] + ".txt"
+
+            if os.path.exists(label_path):
+                visualize_obb(image_path, label_path)
+                count += 1
+            else:
+                print(f"🟡 跳过 (无标签): {filename}")
+
+    print(f"🎉 处理完成！共处理 {count} 张图像。")
+
+
+# =========================
+# 主程序入口
+# =========================
+if __name__ == "__main__":
+    # 设置你的数据目录
+    directory = '/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/obb4/labels'
+
+    if not os.path.exists(directory):
+        raise FileNotFoundError(f"目录不存在: {directory}")
+
+    process_directory(directory)

angle_base_obb/tongji.py

@@ -0,0 +1,101 @@
+import cv2
+import os
+import numpy as np
+from ultralytics import YOLO
+
+IMG_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.tif', '.tiff', '.webp'}
+
+
+def process_obb_images_for_angle_distribution(model_path, image_dir, conf_thresh=0.15, imgsz=640):
+    """
+    批量处理图像的 OBB 推理，计算每张图像检测目标的主方向和夹角，并统计夹角分布情况。
+
+    输入：
+        model_path: YOLO 权重路径
+        image_dir: 图像文件夹路径
+        conf_thresh: 置信度阈值
+        imgsz: 输入图像大小
+    输出：
+        angle_distribution: {'<6': count, '6-20': count, '>20': count}
+    """
+    results_dict = {}
+    angle_distribution = {'<6': 0, '6-20': 0, '>20': 0}
+
+    print("加载 YOLO 模型...")
+    model = YOLO(model_path)
+    print("✅ 模型加载完成")
+
+    # 获取图像文件
+    image_files = [f for f in os.listdir(image_dir) if os.path.splitext(f.lower())[1] in IMG_EXTENSIONS]
+    if not image_files:
+        print(f"❌ 未找到图像文件：{image_dir}")
+        return angle_distribution
+
+    print(f"发现 {len(image_files)} 张图像待处理")
+
+    for img_filename in image_files:
+        img_path = os.path.join(image_dir, img_filename)
+        print(f"\n正在处理：{img_filename}")
+
+        img = cv2.imread(img_path)
+        if img is None:
+            print(f"❌ 跳过：无法读取图像 {img_path}")
+            continue
+
+        # 推理 OBB
+        results = model(img, save=False, imgsz=imgsz, conf=conf_thresh, mode='obb')
+        result = results[0]
+
+        # 提取旋转角
+        boxes = result.obb
+        angles_deg = []
+        if boxes is None or len(boxes) == 0:
+            print("❌ 该图像中未检测到任何目标")
+        else:
+            for i, box in enumerate(boxes):
+                cx, cy, w, h, r_rad = box.xywhr.cpu().numpy()[0]
+                direction = r_rad if w >= h else r_rad + np.pi / 2
+                direction = direction % np.pi
+                angle_deg = np.degrees(direction)
+                angles_deg.append(angle_deg)
+
+        # 两两夹角
+        pairwise_angles_deg = []
+        if len(angles_deg) >= 2:
+            for i in range(len(angles_deg)):
+                for j in range(i + 1, len(angles_deg)):
+                    diff_rad = abs(np.radians(angles_deg[i]) - np.radians(angles_deg[j]))
+                    min_diff_rad = min(diff_rad, np.pi - diff_rad)
+                    angle_deg_diff = np.degrees(min_diff_rad)
+                    pairwise_angles_deg.append(angle_deg_diff)
+
+                    # 更新角度分布统计
+                    if angle_deg_diff < 6:
+                        angle_distribution['<6'] += 1
+                    elif 6 <= angle_deg_diff <= 20:
+                        angle_distribution['6-20'] += 1
+                    else:
+                        angle_distribution['>20'] += 1
+
+                    print(f"  Box {i + 1} 与 Box {j + 1} 夹角: {angle_deg_diff:.2f}°")
+
+        # 保存每张图像结果
+        results_dict[img_filename] = {
+            "angles_deg": angles_deg,
+            "pairwise_angles_deg": pairwise_angles_deg
+        }
+
+    print("\n所有图像处理完成！")
+    return angle_distribution
+
+
+# ------------------- 测试调用 -------------------
+if __name__ == "__main__":
+    MODEL_PATH = r'best1.pt'
+    IMAGE_SOURCE_DIR = r"/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/obb3/train"
+
+    distribution = process_obb_images_for_angle_distribution(MODEL_PATH, IMAGE_SOURCE_DIR)
+    print("\n夹角分布统计:")
+    print(f"小于6度的夹角数量: {distribution['<6']}")
+    print(f"在6至20度之间的夹角数量: {distribution['6-20']}")
+    print(f"大于20度的夹角数量: {distribution['>20']}")

angle_base_obb/view_E.py

@@ -2,15 +2,18 @@ import os
 import cv2
 import numpy as np
 from ultralytics import YOLO
+import matplotlib.pyplot as plt
 
 # ================== 配置参数 ==================
-MODEL_PATH = r"/home/hx/yolo/ultralytics_yolo11-main/runs/train/exp_obb4/weights/best.pt"
-IMAGE_SOURCE_DIR = r"/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/obb2/test"
+MODEL_PATH = r"obb.pt"
+IMAGE_SOURCE_DIR = r"/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/obb4/train"
 LABEL_SOURCE_DIR = IMAGE_SOURCE_DIR  # 假设标签和图像在同一目录
 OUTPUT_DIR = "./inference_results"
-
+VISUAL_DIR = os.path.join(OUTPUT_DIR, "visual_errors_gt5deg")  # 保存误差 >5° 的可视化图
 IMG_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.tif', '.tiff', '.webp'}
+
 os.makedirs(OUTPUT_DIR, exist_ok=True)
+os.makedirs(VISUAL_DIR, exist_ok=True)
 
 # 加载模型
 print("🔄 加载 YOLO OBB 模型...")
@@ -27,32 +30,38 @@ if not image_files:
     print(f"❌ 错误：未找到图像文件")
     exit(1)
 print(f"📁 发现 {len(image_files)} 张图像待处理")
+
 all_angle_errors = []  # 存储每张图的夹角误差（度）
 
 # ================== 工具函数 ==================
 
-def parse_obb_label_file(label_path):
-    """解析 OBB 标签文件，返回 [{'cls': int, 'points': (4,2)}]"""
+def parse_obb_label_file(label_path, img_shape):
+    """
+    解析 OBB 标签文件，并将归一化坐标转换为像素坐标
+    img_shape: (height, width) 用于去归一化
+    """
     boxes = []
+    h, w = img_shape[:2]
     if not os.path.exists(label_path):
+        print(f"⚠️  标签文件不存在: {label_path}")
         return boxes
     with open(label_path, 'r') as f:
         for line in f:
             parts = line.strip().split()
             if len(parts) != 9:
+                print(f"⚠️  标签行格式错误 (期望9列): {parts}")
                 continue
             cls_id = int(parts[0])
             coords = list(map(float, parts[1:]))
             points = np.array(coords).reshape(4, 2)
+            points[:, 0] *= w  # x * width
+            points[:, 1] *= h  # y * height
             boxes.append({'cls': cls_id, 'points': points})
     return boxes
 
 
 def compute_main_direction(points):
-    """
-    根据四个顶点计算旋转框的主方向（长边方向），
-    返回 [0, π) 范围内的弧度值。
-    """
+    """根据四个顶点计算旋转框的主方向（长边方向），返回 [0, π) 范围内的弧度值"""
     edges = []
     for i in range(4):
         p1 = points[i]
@@ -65,11 +74,8 @@ def compute_main_direction(points):
     if not edges:
         return 0.0
 
-    # 找最长边
     longest_edge = max(edges, key=lambda x: x[0])[1]
     angle_rad = np.arctan2(longest_edge[1], longest_edge[0])
-
-    # 归一化到 [0, π)
     angle_rad = angle_rad % np.pi
     return angle_rad
 
@@ -78,9 +84,29 @@ def compute_min_angle_between_two_dirs(dir1_rad, dir2_rad):
     """计算两个方向之间的最小夹角（0 ~ 90°），返回角度制"""
     diff = abs(dir1_rad - dir2_rad)
     min_diff_rad = min(diff, np.pi - diff)
-    return np.degrees(min_diff_rad)  # 返回 0~90°
+    return np.degrees(min_diff_rad)
 
 
+def draw_boxes_on_image(image, pred_boxes=None, true_boxes=None):
+    """在图像上绘制预测框（绿色）和真实框（红色）"""
+    img_vis = image.copy()
+
+    # 绘制真实框（红色）
+    if true_boxes is not None:
+        for box in true_boxes:
+            pts = np.int32(box['points']).reshape((-1, 1, 2))
+            cv2.polylines(img_vis, [pts], isClosed=True, color=(0, 0, 255), thickness=2)
+
+    # 绘制预测框（绿色）
+    if pred_boxes is not None:
+        for box in pred_boxes:
+            xyxyxyxy = box.xyxyxyxy.cpu().numpy()[0]
+            pts = xyxyxyxy.reshape(4, 2).astype(int)
+            pts = pts.reshape((-1, 1, 2))
+            cv2.polylines(img_vis, [pts], isClosed=True, color=(0, 255, 0), thickness=2)
+
+    return img_vis
+
 # ================== 主循环 ==================
 for img_filename in image_files:
     img_path = os.path.join(IMAGE_SOURCE_DIR, img_filename)
@@ -102,7 +128,7 @@ for img_filename in image_files:
     # === 提取预测框主方向 ===
     pred_dirs = []
     if pred_boxes is not None and len(pred_boxes) >= 2:
-        for box in pred_boxes[:2]:  # 只取前两个
+        for box in pred_boxes[:2]:
             xywhr = box.xywhr.cpu().numpy()[0]
             cx, cy, w, h, r_rad = xywhr
             main_dir = r_rad if w >= h else r_rad + np.pi / 2
@@ -113,13 +139,13 @@ for img_filename in image_files:
         continue
 
     # === 提取真实框主方向 ===
-    true_boxes = parse_obb_label_file(label_path)
+    true_boxes = parse_obb_label_file(label_path, img.shape)
     if len(true_boxes) < 2:
         print("❌ 标签框不足两个")
         continue
 
     true_dirs = []
-    for tb in true_boxes[:2]:  # 取前两个
+    for tb in true_boxes[:2]:
         d = compute_main_direction(tb['points'])
         true_dirs.append(d)
     true_angle = compute_min_angle_between_two_dirs(true_dirs[0], true_dirs[1])
@@ -132,6 +158,17 @@ for img_filename in image_files:
     print(f"  🔹 真实夹角: {true_angle:.2f}°")
     print(f"  🔺 夹角误差: {error_deg:.2f}°")
 
+    # === 可视化误差 >5° 的情况 ===
+    if error_deg > 3:
+        print(f"  🎯 误差 >5°，生成可视化图像...")
+        img_with_boxes = draw_boxes_on_image(img, pred_boxes=pred_boxes, true_boxes=true_boxes)
+        # 添加文字
+        cv2.putText(img_with_boxes, f"Error: {error_deg:.2f}°", (20, 50),
+                    cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2, cv2.LINE_AA)
+        vis_output_path = os.path.join(VISUAL_DIR, f"error_{error_deg:.2f}deg_{img_filename}")
+        cv2.imwrite(vis_output_path, img_with_boxes)
+        print(f"  ✅ 已保存可视化图像: {vis_output_path}")
+
 # ================== 输出统计 ==================
 print("\n" + "=" * 60)
 print("📊 夹角误差统计（基于两框间最小夹角）")