可视化模块修改

utils/directory_manager.py

@@ -15,8 +15,11 @@ class DirectoryManager:
     def clean_output_dir(self):
         """清理输出目录"""
         try:
-            shutil.rmtree(self.config.output_dir)
+            if os.path.exists(self.config.output_dir):
-            print(f"已清理输出目录: {self.config.output_dir}")
+                shutil.rmtree(self.config.output_dir)
+                print(f"已清理输出目录: {self.config.output_dir}")
+            else:
+                pass
         except Exception as e:
             print(f"清理输出目录时发生错误: {str(e)}")
             raise
@@ -65,7 +68,7 @@ class DirectoryManager:
         free_space = disk_usage.free
 
         # 计算所需空间（输入大小的10倍）
-        required_space = input_size * 10
+        required_space = input_size * 8
 
         if free_space < required_space:
             error_msg = (

utils/logger.py

@@ -2,34 +2,35 @@ import logging
 import os
 from datetime import datetime
 
+
 def setup_logger(output_dir):
     # 创建logs目录
     log_dir = os.path.join(output_dir, 'logs')
-    
+
     # 创建日志文件名（包含时间戳）
     timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
     log_file = os.path.join(log_dir, f'preprocess_{timestamp}.log')
-    
+
     # 配置日志格式
     formatter = logging.Formatter(
         '%(asctime)s - %(name)s - %(levelname)s - %(message)s',
         datefmt='%Y-%m-%d %H:%M:%S'
     )
-    
+
     # 配置文件处理器
     file_handler = logging.FileHandler(log_file, encoding='utf-8')
     file_handler.setFormatter(formatter)
-    
+
     # 配置控制台处理器
     console_handler = logging.StreamHandler()
     console_handler.setFormatter(formatter)
-    
+
     # 获取根日志记录器
     logger = logging.getLogger('UAV_Preprocess')
     logger.setLevel(logging.INFO)
-    
+
     # 添加处理器
     logger.addHandler(file_handler)
     logger.addHandler(console_handler)
-    
+
-    return logger 
+    return logger

utils/odm_monitor.py

@@ -85,21 +85,20 @@ class ODMProcessMonitor:
                 self.logger.error("容器运行失败的详细错误日志：")
                 for line in error_msg:
                     self.logger.error(line)
+                container.remove()
+                time.sleep(5)
             else:
                 # 获取所有日志
                 logs = container.logs().decode("utf-8").splitlines()
-
                 # 输出最后 50 行日志
                 self.logger.info("容器运行完成，以下是最后 50 行日志：")
                 for line in logs[-50:]:
                     self.logger.info(line)
                 success = True
                 error_msg = ""
+                container.remove()
                 break
 
-            # 删除容器
-            container.remove()
-            time.sleep(5)
 
         return success, error_msg
 

utils/visualizer.py

@@ -8,11 +8,11 @@ from pyproj import Transformer
 
 class FilterVisualizer:
     """过滤结果可视化器"""
-    
+
     def __init__(self, output_dir: str):
         """
         初始化可视化器
-        
+
         Args:
             output_dir: 输出目录路径
         """
@@ -24,28 +24,28 @@ class FilterVisualizer:
             "EPSG:32649",  # UTM49N
             always_xy=True
         )
-        
+
     def _convert_to_utm(self, lon: pd.Series, lat: pd.Series) -> tuple:
         """
         将经纬度坐标转换为UTM坐标
-        
+
         Args:
             lon: 经度序列
             lat: 纬度序列
-            
+
         Returns:
             tuple: (x坐标, y坐标)
         """
         return self.transformer.transform(lon, lat)
-        
+
-    def visualize_filter_step(self, 
+    def visualize_filter_step(self,
-                            current_points: pd.DataFrame,
+                              current_points: pd.DataFrame,
-                            previous_points: pd.DataFrame,
+                              previous_points: pd.DataFrame,
-                            step_name: str,
+                              step_name: str,
-                            save_name: Optional[str] = None):
+                              save_name: Optional[str] = None):
         """
         可视化单个过滤步骤的结果
-        
+
         Args:
             current_points: 当前步骤后的点
             previous_points: 上一步骤的点
@@ -53,39 +53,43 @@ class FilterVisualizer:
             save_name: 保存文件名，默认为step_name
         """
         self.logger.info(f"开始生成{step_name}的可视化结果")
-        
+
         # 找出被过滤掉的点
-        filtered_files = set(previous_points['file']) - set(current_points['file'])
+        filtered_files = set(
-        filtered_points = previous_points[previous_points['file'].isin(filtered_files)]
+            previous_points['file']) - set(current_points['file'])
-        
+        filtered_points = previous_points[previous_points['file'].isin(
+            filtered_files)]
+
         # 转换坐标到UTM
-        current_x, current_y = self._convert_to_utm(current_points['lon'], current_points['lat'])
+        current_x, current_y = self._convert_to_utm(
-        filtered_x, filtered_y = self._convert_to_utm(filtered_points['lon'], filtered_points['lat'])
+            current_points['lon'], current_points['lat'])
-        
+        filtered_x, filtered_y = self._convert_to_utm(
+            filtered_points['lon'], filtered_points['lat'])
+
         # 创建图形
-        plt.rcParams['font.sans-serif']=['SimHei']#黑体
+        plt.rcParams['font.sans-serif'] = ['SimHei']  # 黑体
         plt.rcParams['axes.unicode_minus'] = False
-        plt.figure()
+        plt.figure(figsize=(20, 20))
-        
+
         # 绘制保留的点
         plt.scatter(current_x, current_y,
-                   color='blue', label='保留的点',
+                    color='blue', label='保留的点',
-                   alpha=0.6, s=50)
+                    alpha=0.6, s=5)
-        
+
         # 绘制被过滤的点
         if not filtered_points.empty:
             plt.scatter(filtered_x, filtered_y,
-                       color='red', marker='x', label='过滤的点',
+                        color='red', marker='x', label='过滤的点')
-                       alpha=0.6, s=100)
+
-        
         # 设置图形属性
         plt.title(f"{step_name}后的GPS点\n"
-                 f"(过滤: {len(filtered_points)}, 保留: {len(current_points)})",
+                  f"(过滤: {len(filtered_points)}, 保留: {len(current_points)})",
-                 fontsize=14)
+                  fontsize=14)
         plt.xlabel("东向坐标 (米)", fontsize=12)
         plt.ylabel("北向坐标 (米)", fontsize=12)
         plt.grid(True)
-        
+        plt.axis('equal')
+
         # 添加统计信息
         stats_text = (
             f"原始点数: {len(previous_points)}\n"
@@ -94,20 +98,21 @@ class FilterVisualizer:
             f"过滤率: {len(filtered_points)/len(previous_points)*100:.1f}%"
         )
         plt.figtext(0.02, 0.02, stats_text, fontsize=10,
-                   bbox=dict(facecolor='white', alpha=0.8))
+                    bbox=dict(facecolor='white', alpha=0.8))
-        
+
         # 添加图例
         plt.legend(loc='upper right', fontsize=10)
-        
+
         # 调整布局
         plt.tight_layout()
-        
+
         # 保存图形
         save_name = save_name or step_name.lower().replace(' ', '_')
-        save_path = os.path.join(self.output_dir, 'filter_imgs', f'filter_{save_name}.png')
+        save_path = os.path.join(
+            self.output_dir, 'filter_imgs', f'filter_{save_name}.png')
         plt.savefig(save_path, dpi=300, bbox_inches='tight')
         plt.close()
-        
+
         self.logger.info(
             f"{step_name}过滤可视化结果已保存至 {save_path}\n"
             f"过滤掉 {len(filtered_points)} 个点，"
@@ -120,11 +125,11 @@ if __name__ == '__main__':
     # 测试代码
     import numpy as np
     from datetime import datetime
-    
+
     # 创建测试数据
     np.random.seed(42)
     n_points = 1000
-    
+
     # 生成随机点
     test_data = pd.DataFrame({
         'lon': np.random.uniform(120, 121, n_points),
@@ -132,16 +137,16 @@ if __name__ == '__main__':
         'file': [f'img_{i}.jpg' for i in range(n_points)],
         'date': [datetime.now() for _ in range(n_points)]
     })
-    
+
     # 随机选择点作为过滤后的结果
     filtered_data = test_data.sample(n=800)
-    
+
     # 测试可视化
     visualizer = FilterVisualizer('test_output')
     os.makedirs('test_output', exist_ok=True)
-    
+
     visualizer.visualize_filter_step(
         filtered_data,
         test_data,
         "Test Filter"
-    ) 
+    )