重构目录结构：调整项目布局

vision/__init__.py

@@ -0,0 +1,18 @@
+# vision/__init__.py
+"""
+视觉处理模块
+包含摄像头控制和视觉检测功能
+"""
+from .camera import CameraController
+from .detector import VisionDetector
+from .angle_detector import get_current_door_angle
+from .overflow_detector import detect_overflow_from_image
+from .alignment_detector import detect_vehicle_alignment
+
+__all__ = [
+    'CameraController',
+    'VisionDetector',
+    'get_current_door_angle',
+    'detect_overflow_from_image',
+    'detect_vehicle_alignment'
+]

vision/alignment_detector.py

@@ -0,0 +1,30 @@
+# vision/alignment_detector.py
+def detect_vehicle_alignment(image_array, alignment_model):
+    """
+    通过图像检测模具车是否对齐
+    """
+    try:
+        # 检查模型是否已加载
+        if alignment_model is None:
+            print("对齐检测模型未加载")
+            return False
+
+        if image_array is None:
+            print("输入图像为空")
+            return False
+
+        # 直接使用模型进行推理
+        results = alignment_model(image_array)
+        pared_probs = results[0].probs.data.cpu().numpy().flatten()
+
+        # 类别0: 未对齐, 类别1: 对齐
+        class_id = int(pared_probs.argmax())
+        confidence = float(pared_probs[class_id])
+
+        # 只有当对齐且置信度>95%时才认为对齐
+        if class_id == 1 and confidence > 0.95:
+            return True
+        return False
+    except Exception as e:
+        print(f"对齐检测失败: {e}")
+        return False

vision/anger_caculate.py

@@ -0,0 +1,88 @@
+import cv2
+import os
+import numpy as np
+from ultralytics import YOLO
+
+def predict_obb_best_angle(model=None, model_path=None, image=None, image_path=None, save_path=None):
+    """
+    输入：
+        model: 预加载的YOLO模型实例（可选）
+        model_path: YOLO 权重路径（当model为None时使用）
+        image: 图像数组（numpy array）
+        image_path: 图片路径（当image为None时使用）
+        save_path: 可选，保存带标注图像
+    输出：
+        angle_deg: 置信度最高两个框的主方向夹角（度），如果检测少于两个目标返回 None
+        annotated_img: 可视化图像
+    """
+    # 1. 使用预加载的模型或加载新模型
+    if model is not None:
+        loaded_model = model
+    elif model_path is not None:
+        loaded_model = YOLO(model_path)
+    else:
+        raise ValueError("必须提供model或model_path参数")
+
+    # 2. 读取图像（优先使用传入的图像数组）
+    if image is not None:
+        img = image
+    elif image_path is not None:
+        img = cv2.imread(image_path)
+        if img is None:
+            print(f"无法读取图像: {image_path}")
+            return None, None
+    else:
+        raise ValueError("必须提供image或image_path参数")
+
+    # 3. 推理 OBB
+    results = loaded_model(img, save=False, imgsz=640, conf=0.5, mode='obb')
+    result = results[0]
+
+    # 4. 可视化
+    annotated_img = result.plot()
+    if save_path:
+        os.makedirs(os.path.dirname(save_path), exist_ok=True)
+        cv2.imwrite(save_path, annotated_img)
+        print(f"推理结果已保存至: {save_path}")
+
+    # 5. 提取旋转角度和置信度
+    boxes = result.obb
+    if boxes is None or len(boxes) < 2:
+        print("检测到少于两个目标，无法计算夹角。")
+        return None, annotated_img
+
+    box_info = []
+    for box in boxes:
+        conf = box.conf.cpu().numpy()[0]
+        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
+        box_info.append((conf, direction))
+
+    # 6. 取置信度最高两个框
+    box_info = sorted(box_info, key=lambda x: x[0], reverse=True)
+    dir1, dir2 = box_info[0][1], box_info[1][1]
+
+    # 7. 计算夹角（最小夹角，0~90°）
+    diff = abs(dir1 - dir2)
+    diff = min(diff, np.pi - diff)
+    angle_deg = np.degrees(diff)
+
+    print(f"置信度最高两个框主方向夹角: {angle_deg:.2f}°")
+    return angle_deg, annotated_img
+
+
+# ------------------- 测试 -------------------
+# if __name__ == "__main__":
+#     weight_path = r'angle.pt'
+#     image_path = r"./test_image/3.jpg"
+#     save_path = "./inference_results/detected_3.jpg"
+#
+#     #angle_deg, annotated_img = predict_obb_best_angle(weight_path, image_path, save_path)
+#     angle_deg,_ = predict_obb_best_angle(model_path=weight_path, image_path=image_path, save_path=save_path)
+#     annotated_img = None
+#     print(angle_deg)
+#     if annotated_img is not None:
+#         cv2.imshow("YOLO OBB Prediction", annotated_img)
+#         cv2.waitKey(0)
+#         cv2.destroyAllWindows()

vision/angle_detector.py

@@ -0,0 +1,27 @@
+# vision/angle_detector.py
+import sys
+import os
+from vision.anger_caculate import predict_obb_best_angle
+
+# 添加项目根目录到Python路径
+sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
+
+def get_current_door_angle(model=None, image=None, image_path=None):
+    """
+    通过视觉系统获取当前出砼门角度
+    :param model: 模型实例
+    :param image: 图像数组（numpy array）
+    :param image_path: 图片路径
+    :return: 角度值（度）
+    """
+    try:
+        # 调用实际的角度检测函数
+        angle_deg, _ = predict_obb_best_angle(
+            model=model,
+            image=image,
+            image_path=image_path
+        )
+        return angle_deg
+    except Exception as e:
+        print(f"角度检测失败: {e}")
+        return None

vision/camera.py

@@ -0,0 +1,67 @@
+# vision/camera.py
+import cv2
+
+
+class CameraController:
+    def __init__(self):
+        self.camera = None
+        self.camera_type = "ip"
+        self.camera_ip = "192.168.1.51"
+        self.camera_port = 554
+        self.camera_username = "admin"
+        self.camera_password = "XJ123456"
+        self.camera_channel = 1
+
+    def set_config(self, camera_type="ip", ip=None, port=None, username=None, password=None, channel=1):
+        """
+        设置摄像头配置
+        """
+        self.camera_type = camera_type
+        if ip:
+            self.camera_ip = ip
+        if port:
+            self.camera_port = port
+        if username:
+            self.camera_username = username
+        if password:
+            self.camera_password = password
+        self.camera_channel = channel
+
+    def setup_capture(self, camera_index=0):
+        """
+        设置摄像头捕获
+        """
+        try:
+            rtsp_url = f"rtsp://{self.camera_username}:{self.camera_password}@{self.camera_ip}:{self.camera_port}/streaming/channels/{self.camera_channel}01"
+            self.camera = cv2.VideoCapture(rtsp_url)
+
+            if not self.camera.isOpened():
+                print(f"无法打开网络摄像头: {rtsp_url}")
+                return False
+            print(f"网络摄像头初始化成功，地址: {rtsp_url}")
+            return True
+        except Exception as e:
+            print(f"摄像头设置失败: {e}")
+            return False
+
+    def capture_frame(self):
+        """捕获当前帧并返回numpy数组"""
+        try:
+            if self.camera is None:
+                print("摄像头未初始化")
+                return None
+
+            ret, frame = self.camera.read()
+            if ret:
+                return frame
+            else:
+                print("无法捕获图像帧")
+                return None
+        except Exception as e:
+            print(f"图像捕获失败: {e}")
+            return None
+
+    def release(self):
+        """释放摄像头资源"""
+        if self.camera is not None:
+            self.camera.release()

vision/detector.py

@@ -0,0 +1,86 @@
+# vision/detector.py
+import os
+from ultralytics import YOLO
+from vision.angle_detector import get_current_door_angle
+from vision.overflow_detector import detect_overflow_from_image
+from vision.alignment_detector import detect_vehicle_alignment
+
+
+class VisionDetector:
+    def __init__(self, settings):
+        self.settings = settings
+
+        # 模型实例
+        self.angle_model = None
+        self.overflow_model = None
+        self.alignment_model = None
+
+    def load_models(self):
+        """
+        加载所有视觉检测模型
+        """
+        success = True
+
+        # 加载夹角检测模型
+        try:
+            if not os.path.exists(self.settings.angle_model_path):
+                print(f"夹角检测模型不存在: {self.settings.angle_model_path}")
+                success = False
+            else:
+                # 注意：angle.pt模型通过predict_obb_best_angle函数使用，不需要预加载
+                print(f"夹角检测模型路径: {self.settings.angle_model_path}")
+        except Exception as e:
+            print(f"检查夹角检测模型失败: {e}")
+            success = False
+
+        # 加载堆料检测模型
+        try:
+            if not os.path.exists(self.settings.overflow_model_path):
+                print(f"堆料检测模型不存在: {self.settings.overflow_model_path}")
+                success = False
+            else:
+                self.overflow_model = YOLO(self.settings.overflow_model_path)
+                print(f"成功加载堆料检测模型: {self.settings.overflow_model_path}")
+        except Exception as e:
+            print(f"加载堆料检测模型失败: {e}")
+            success = False
+
+        # 加载对齐检测模型
+        try:
+            if not os.path.exists(self.settings.alignment_model_path):
+                print(f"对齐检测模型不存在: {self.settings.alignment_model_path}")
+                success = False
+            else:
+                self.alignment_model = YOLO(self.settings.alignment_model_path)
+                print(f"成功加载对齐检测模型: {self.settings.alignment_model_path}")
+        except Exception as e:
+            print(f"加载对齐检测模型失败: {e}")
+            success = False
+
+        return success
+
+    def detect_angle(self, image=None, image_path=None):
+        """
+        通过视觉系统获取当前出砼门角度
+        """
+        return get_current_door_angle(
+            model=self.angle_model,
+            image=image,
+            image_path=image_path
+        )
+
+    def detect_overflow(self, image_array):
+        """
+        通过图像检测是否溢料
+        """
+        return detect_overflow_from_image(
+            image_array,
+            self.overflow_model,
+            self.settings.roi_file_path
+        )
+
+    def detect_vehicle_alignment(self, image_array):
+        """
+        通过图像检测模具车是否对齐
+        """
+        return detect_vehicle_alignment(image_array, self.alignment_model)

vision/overflow_detector.py

@@ -0,0 +1,47 @@
+# vision/overflow_detector.py
+import sys
+import os
+from vision.resize_tuili_image_main import classify_image_weighted, load_global_rois, crop_and_resize
+
+# 添加项目根目录到Python路径
+sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
+
+def detect_overflow_from_image(image_array, overflow_model, roi_file_path):
+    """
+    通过图像检测是否溢料
+    :param image_array: 图像数组
+    :param overflow_model: 溢料检测模型
+    :param roi_file_path: ROI文件路径
+    :return: 是否检测到溢料 (True/False)
+    """
+    try:
+        # 检查模型是否已加载
+        if overflow_model is None:
+            print("堆料检测模型未加载")
+            return False
+
+        # 加载ROI区域
+        rois = load_global_rois(roi_file_path)
+
+        if not rois:
+            print(f"没有有效的ROI配置: {roi_file_path}")
+            return False
+
+        if image_array is None:
+            print("输入图像为空")
+            return False
+
+        # 裁剪和调整图像大小
+        crops = crop_and_resize(image_array, rois, 640)
+
+        # 对每个ROI区域进行分类检测
+        for roi_resized, _ in crops:
+            final_class, _, _, _ = classify_image_weighted(roi_resized, overflow_model, threshold=0.4)
+            if "大堆料" in final_class or "小堆料" in final_class:
+                print(f"检测到溢料: {final_class}")
+                return True
+
+        return False
+    except Exception as e:
+        print(f"溢料检测失败: {e}")
+        return False

vision/resize_main.py

@@ -0,0 +1,106 @@
+import os
+import shutil
+from pathlib import Path
+from ultralytics import YOLO
+import cv2
+
+# ---------------------------
+# ROI 裁剪函数
+# ---------------------------
+def load_global_rois(txt_path):
+    """加载全局 ROI 坐标"""
+    rois = []
+    if not os.path.exists(txt_path):
+        print(f"❌ ROI 文件不存在: {txt_path}")
+        return rois
+    with open(txt_path, 'r') as f:
+        for line in f:
+            line = line.strip()
+            if line:
+                try:
+                    x, y, w, h = map(int, line.split(','))
+                    rois.append((x, y, w, h))
+                    print(f"📌 加载 ROI: (x={x}, y={y}, w={w}, h={h})")
+                except Exception as e:
+                    print(f"⚠️ 无法解析 ROI 行: {line}, 错误: {e}")
+    return rois
+
+def crop_and_resize(img, rois, target_size=640):
+    """根据 ROI 裁剪并 resize"""
+    crops = []
+    for i, (x, y, w, h) in enumerate(rois):
+        h_img, w_img = img.shape[:2]
+        if x < 0 or y < 0 or x + w > w_img or y + h > h_img:
+            print(f"⚠️ ROI 越界，跳过: {x},{y},{w},{h}")
+            continue
+        roi_img = img[y:y+h, x:x+w]
+        roi_resized = cv2.resize(roi_img, (target_size, target_size), interpolation=cv2.INTER_AREA)
+        crops.append((roi_resized, i))
+    return crops
+
+# ---------------------------
+# 分类函数
+# ---------------------------
+def classify_and_save_images(model_path, input_folder, output_root, roi_file, target_size=640):
+    # 加载模型
+    model = YOLO(model_path)
+
+    # 确保输出根目录存在
+    output_root = Path(output_root)
+    output_root.mkdir(parents=True, exist_ok=True)
+
+    # 创建类别子文件夹 (class0 到 class4)
+    class_dirs = []
+    for i in range(5):  # 假设有5个类别 (0-4)
+        class_dir = output_root / f"class{i}"
+        class_dir.mkdir(exist_ok=True)
+        class_dirs.append(class_dir)
+
+    # 加载 ROI
+    rois = load_global_rois(roi_file)
+    if len(rois) == 0:
+        print("❌ 没有有效 ROI，退出")
+        return
+
+    # 遍历输入文件夹
+    for img_path in Path(input_folder).glob("*.*"):
+        if img_path.suffix.lower() not in ['.jpg', '.jpeg', '.png', '.bmp', '.tif']:
+            continue
+
+        try:
+            # 读取原图
+            img = cv2.imread(str(img_path))
+            if img is None:
+                print(f"❌ 无法读取图像: {img_path}")
+                continue
+
+            # 根据 ROI 裁剪
+            crops = crop_and_resize(img, rois, target_size)
+
+            for roi_img, roi_idx in crops:
+                # YOLO 推理
+                results = model(roi_img)
+
+                pred = results[0].probs.data  # 获取概率分布
+                class_id = int(pred.argmax())
+
+                # 保存到对应类别文件夹
+                suffix = f"_roi{roi_idx}" if len(crops) > 1 else ""
+                dst_path = class_dirs[class_id] / f"{img_path.stem}{suffix}{img_path.suffix}"
+                cv2.imwrite(dst_path, roi_img)  # 保存裁剪后的 ROI 图像
+                print(f"Processed {img_path.name}{suffix} -> Class {class_id}")
+
+        except Exception as e:
+            print(f"Error processing {img_path.name}: {str(e)}")
+
+# ---------------------------
+# 主程序
+# ---------------------------
+if __name__ == "__main__":
+    model_path = r"models/overflow.pt"
+    input_folder = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/f6"
+    output_root = "/media/hx/04e879fa-d697-4b02-ac7e-a4148876ebb0/dataset/class111"
+    roi_file = "./roi_coordinates/1_rois.txt"  # 训练时使用的 ROI 文件
+    target_size = 640
+
+    classify_and_save_images(model_path, input_folder, output_root, roi_file, target_size)

vision/resize_tuili_image_main.py

@@ -0,0 +1,184 @@
+import os
+from pathlib import Path
+import cv2
+import numpy as np
+from ultralytics import YOLO
+
+# ---------------------------
+# 类别映射
+# ---------------------------
+CLASS_NAMES = {
+    0: "未堆料",
+    1: "小堆料",
+    2: "大堆料",
+    3: "未浇筑满",
+    4: "浇筑满"
+}
+
+
+# ---------------------------
+# 加载 ROI 列表
+# ---------------------------
+def load_global_rois(txt_path):
+    rois = []
+    if not os.path.exists(txt_path):
+        print(f"ROI 文件不存在: {txt_path}")
+        return rois
+    with open(txt_path, 'r') as f:
+        for line in f:
+            s = line.strip()
+            if s:
+                try:
+                    x, y, w, h = map(int, s.split(','))
+                    rois.append((x, y, w, h))
+                except Exception as e:
+                    print(f"无法解析 ROI 行 '{s}': {e}")
+    return rois
+
+
+# ---------------------------
+# 裁剪并 resize ROI
+# ---------------------------
+def crop_and_resize(img, rois, target_size=640):
+    crops = []
+    h_img, w_img = img.shape[:2]
+    for i, (x, y, w, h) in enumerate(rois):
+        if x < 0 or y < 0 or x + w > w_img or y + h > h_img:
+            continue
+        roi = img[y:y + h, x:x + w]
+        roi_resized = cv2.resize(roi, (target_size, target_size), interpolation=cv2.INTER_AREA)
+        crops.append((roi_resized, i))
+    return crops
+
+
+# ---------------------------
+# class1/class2 加权判断
+# ---------------------------
+def weighted_small_large(pred_probs, threshold=0.4, w1=0.3, w2=0.7):
+    p1 = float(pred_probs[1])
+    p2 = float(pred_probs[2])
+    total = p1 + p2
+    if total > 0:
+        score = (w1 * p1 + w2 * p2) / total
+    else:
+        score = 0.0
+    final_class = "大堆料" if score >= threshold else "小堆料"
+    return final_class, score, p1, p2
+
+
+# ---------------------------
+# 单张图片推理函数
+# ---------------------------
+def classify_image_weighted(image, model, threshold=0.4):
+    results = model(image)
+    pred_probs = results[0].probs.data.cpu().numpy().flatten()
+    class_id = int(pred_probs.argmax())
+    confidence = float(pred_probs[class_id])
+    class_name = CLASS_NAMES.get(class_id, f"未知类别({class_id})")
+
+    # class1/class2 使用加权得分
+    if class_id in [1, 2]:
+        final_class, score, p1, p2 = weighted_small_large(pred_probs, threshold=threshold)
+    else:
+        final_class = class_name
+        score = confidence
+        p1 = float(pred_probs[1])
+        p2 = float(pred_probs[2])
+
+    return final_class, score, p1, p2
+
+
+# ---------------------------
+# 实时视频流推理函数
+# ---------------------------
+def real_time_inference(rtsp_url, model_path, roi_file, target_size=640, threshold=0.4):
+    """
+    从RTSP流实时推理
+    :param rtsp_url: RTSP流URL
+    :param model_path: 模型路径
+    :param roi_file: ROI文件路径
+    :param target_size: 目标尺寸
+    :param threshold: 分类阈值
+    """
+    # 加载模型
+    model = YOLO(model_path)
+
+    # 加载ROI
+    rois = load_global_rois(roi_file)
+    if not rois:
+        print("❌ 没有有效 ROI，退出")
+        return
+
+    # 打开RTSP流
+    cap = cv2.VideoCapture(rtsp_url)
+
+    if not cap.isOpened():
+        print(f"❌ 无法打开视频流: {rtsp_url}")
+        return
+
+    print(f"✅ 成功连接到视频流: {rtsp_url}")
+    print("按 'q' 键退出，按 's' 键保存当前帧")
+
+    frame_count = 0
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            print("❌ 无法读取帧，可能连接已断开")
+            break
+
+        frame_count += 1
+        print(f"\n处理第 {frame_count} 帧")
+
+        try:
+            # 裁剪并调整ROI
+            crops = crop_and_resize(frame, rois, target_size)
+
+            for roi_resized, roi_idx in crops:
+                final_class, score, p1, p2 = classify_image_weighted(roi_resized, model, threshold=threshold)
+
+                print(f"ROI {roi_idx} -> 类别: {final_class}, 加权分数: {score:.2f}, "
+                      f"class1 置信度: {p1:.2f}, class2 置信度: {p2:.2f}")
+
+                # 判断是否溢料
+                if "大堆料" in final_class or "浇筑满" in final_class:
+                    print(f"🚨 检测到溢料: ROI {roi_idx} - {final_class}")
+
+                # 可视化（可选）
+                cv2.imshow(f'ROI {roi_idx}', roi_resized)
+
+            # 显示原始帧
+            cv2.imshow('Original Frame', frame)
+
+        except Exception as e:
+            print(f"处理帧时出错: {e}")
+            continue
+
+        # 键盘控制
+        key = cv2.waitKey(1) & 0xFF
+        if key == ord('q'):  # 按q退出
+            break
+        elif key == ord('s'):  # 按s保存当前帧
+            cv2.imwrite(f"frame_{frame_count}.jpg", frame)
+            print(f"保存帧到 frame_{frame_count}.jpg")
+
+    # 清理资源
+    cap.release()
+    cv2.destroyAllWindows()
+    print("✅ 视频流处理结束")
+
+
+# ---------------------------
+# 主函数 - 实时推理示例
+# ---------------------------
+# if __name__ == "__main__":
+#     # RTSP流URL
+#     rtsp_url = "rtsp://admin:XJ123456@192.168.1.51:554/streaming/channels/101"
+#
+#     # 配置参数
+#     model_path = r"models/overflow.pt"
+#     roi_file = r"./roi_coordinates/1_rois.txt"
+#     target_size = 640
+#     threshold = 0.4
+#
+#     print("开始实时视频流推理...")
+#     real_time_inference(rtsp_url, model_path, roi_file, target_size, threshold)

vision/roi_coordinates/1_rois.txt

@@ -0,0 +1 @@
+859,810,696,328