refactor(检测器): 重构物体检测逻辑并添加日志记录

将print语句替换为logger，添加检测结果日志记录功能
支持中英文人体类别检测，优化代码结构

dual_camera_system/panorama_camera.py

@@ -13,6 +13,7 @@ import numpy as np
 import threading
 import queue
 import time
+import logging
 from typing import Optional, List, Tuple, Dict, Any
 from dataclasses import dataclass
 
@@ -20,6 +21,8 @@ from config import PANORAMA_CAMERA, DETECTION_CONFIG
 from dahua_sdk import DahuaSDK, PTZCommand
 from video_lock import safe_read, safe_is_opened
 
+logger = logging.getLogger(__name__)
+
 
 @dataclass
 class DetectedObject:
@@ -582,33 +585,43 @@ class ObjectDetector:
                 results.append(obj)
                 
         except Exception as e:
-            print(f"RKNN/ONNX 检测错误: {e}")
+            logger.error(f"RKNN/ONNX 检测错误: {e}")
         
         return results
     
     def detect(self, frame: np.ndarray) -> List[DetectedObject]:
-        """
-        使用YOLO11检测物体
-        Args:
-            frame: 输入图像
-        Returns:
-            检测结果列表
-        """
+        """检测物体返回所有类别结果"""
         if frame is None:
             return []
         
-        # 优先使用 RKNN/ONNX 模型
         if hasattr(self, 'rknn') and self.rknn is not None:
-            return self._detect_rknn(frame)
+            results = self._detect_rknn(frame)
+            if results:
+                self._log_detections("RKNN", results, frame)
+            return results
         elif hasattr(self, 'session') and self.session is not None:
-            return self._detect_rknn(frame)
-        # 使用 YOLO 模型
+            results = self._detect_rknn(frame)
+            if results:
+                self._log_detections("ONNX", results, frame)
+            return results
         elif self.model is not None:
-            return self._detect_yolo(frame)
+            results = self._detect_yolo(frame)
+            if results:
+                self._log_detections("YOLO", results, frame)
+            return results
         else:
-            print("[错误] 没有可用的检测模型")
+            logger.error("[YOLO] 没有可用的检测模型")
             return []
     
+    def _log_detections(self, model_type: str, results: List[DetectedObject], frame: np.ndarray):
+        if not results:
+            return
+        class_counts = {}
+        for r in results:
+            class_counts[r.class_name] = class_counts.get(r.class_name, 0) + 1
+        h, w = frame.shape[:2]
+        logger.info(f"[YOLO] {model_type}: {len(results)}个目标 {class_counts} (帧尺寸={w}x{h})")
+    
     def _detect_yolo(self, frame: np.ndarray) -> List[DetectedObject]:
         """使用 YOLO 模型检测"""
         results = []
@@ -655,7 +668,7 @@ class ObjectDetector:
                     results.append(obj)
                     
         except Exception as e:
-            print(f"YOLO11检测错误: {e}")
+            logger.error(f"YOLO11检测错误: {e}")
         
         return results
     
@@ -670,15 +683,10 @@ class ObjectDetector:
         return self.detect(frame)
     
     def detect_persons(self, frame: np.ndarray) -> List[DetectedObject]:
-        """
-        检测人体
-        Args:
-            frame: 输入图像
-        Returns:
-            检测到的人体列表
-        """
-        results = self.detect(frame)
-        return [obj for obj in results if obj.class_name == 'person']
+        """检测人体（支持中英文类别名）"""
+        all_detections = self.detect(frame)
+        person_classes = {'person', '人'}
+        return [obj for obj in all_detections if obj.class_name in person_classes]
     
     def release(self):
         """释放模型资源"""