From 0e29728126fd8646800dee5273ee74081e3612f1 Mon Sep 17 00:00:00 2001
From: Your Name <you@example.com>
Date: Sat, 4 Jan 2025 15:19:23 +0800
Subject: [PATCH] add filter time_group_overlap

---
 filter/time_group_overlap_filter.py |  6 +--
 odm_preprocess.py                   | 84 +++++++++++++----------------
 2 files changed, 39 insertions(+), 51 deletions(-)

diff --git a/filter/time_group_overlap_filter.py b/filter/time_group_overlap_filter.py
index 15ece6f..9f7a4f9 100644
--- a/filter/time_group_overlap_filter.py
+++ b/filter/time_group_overlap_filter.py
@@ -90,12 +90,8 @@ class TimeGroupOverlapFilter:
             return intersection_area / smaller_area
         return 0
 
-    def filter_overlapping_groups(self, time_threshold=timedelta(minutes=5)):
+    def filter_overlapping_groups(self, gps_points, time_threshold=timedelta(minutes=5)):
         """过滤重叠的时间组"""
-        # 提取GPS数据
-        extractor = GPSExtractor(self.image_dir)
-        gps_points = extractor.extract_all_gps()
-
         # 按时间分组
         time_groups = self._group_by_time(gps_points, time_threshold)
 
diff --git a/odm_preprocess.py b/odm_preprocess.py
index 07e164c..103df42 100644
--- a/odm_preprocess.py
+++ b/odm_preprocess.py
@@ -97,9 +97,8 @@ class ImagePreprocessor:
         extractor = GPSExtractor(self.config.image_dir)
         self.gps_points = extractor.extract_all_gps()
         self.logger.info(f"成功提取 {len(self.gps_points)} 个GPS点")
-        return self.gps_points
 
-    def cluster(self) -> pd.DataFrame:
+    def cluster(self):
         """使用DBSCAN对GPS点进行聚类，只保留最大的类"""
         self.logger.info("开始聚类")
         previous_points = self.gps_points.copy()
@@ -124,44 +123,10 @@ class ImagePreprocessor:
         self.visualizer.visualize_filter_step(
             self.gps_points, previous_points, "1-Clustering")
 
-        return self.gps_points
-
-    def filter_time_group_overlap(self) -> pd.DataFrame:
-        """过滤重叠的时间组"""
-        self.logger.info("开始过滤重叠时间组")
-
-        self.logger.info("开始过滤重叠时间组")
-        previous_points = self.gps_points.copy()
-
-        filter = TimeGroupOverlapFilter(
-            self.config.image_dir,
-            self.config.output_dir,
-            overlap_threshold=self.config.time_group_overlap_threshold
-        )
-
-        deleted_files = filter.filter_overlapping_groups(
-            time_threshold=self.config.time_group_interval
-        )
-
-        # 更新GPS点数据，移除被删除的图像
-        self.gps_points = self.gps_points[~self.gps_points['file'].isin(
-            deleted_files)]
-        self.logger.info(f"重叠时间组过滤后剩余 {len(self.gps_points)} 个GPS点")
-
-        # 可视化过滤结果
-        self.visualizer.visualize_filter_step(
-            self.gps_points, previous_points, "2-Time Group Overlap")
-
-        return self.gps_points
-
-    # TODO 过滤算法还需要更新
-    def filter_points(self) -> pd.DataFrame:
-        """过滤GPS点"""
-
-        self.logger.info("开始过滤GPS点")
+    def filter_isolated_points(self):
+        """过滤孤立点"""
+        self.logger.info("开始过滤孤立点")
         filter = GPSFilter(self.config.output_dir)
-
-        # 过滤孤立点
         previous_points = self.gps_points.copy()
         self.logger.info(
             f"开始过滤孤立点(距离阈值: {self.config.filter_distance_threshold}, "
@@ -176,7 +141,36 @@ class ImagePreprocessor:
 
         # 可视化孤立点过滤结果
         self.visualizer.visualize_filter_step(
-            self.gps_points, previous_points, "3-Isolated Points")
+            self.gps_points, previous_points, "2-Isolated Points")
+
+    def filter_time_group_overlap(self):
+        """过滤重叠的时间组"""
+        self.logger.info("开始过滤重叠时间组")
+        previous_points = self.gps_points.copy()
+
+        filter = TimeGroupOverlapFilter(
+            self.config.image_dir,
+            self.config.output_dir,
+            overlap_threshold=self.config.time_group_overlap_threshold
+        )
+
+        deleted_files = filter.filter_overlapping_groups(
+            self.gps_points,
+            time_threshold=self.config.time_group_interval
+        )
+
+        # 更新GPS点数据，移除被删除的图像
+        self.gps_points = self.gps_points[~self.gps_points['file'].isin(
+            deleted_files)]
+        self.logger.info(f"重叠时间组过滤后剩余 {len(self.gps_points)} 个GPS点")
+
+        # 可视化过滤结果
+        self.visualizer.visualize_filter_step(
+            self.gps_points, previous_points, "3-Time Group Overlap")
+
+    # # TODO 过滤密集点算法还需要更新
+    # def filter_points(self):
+    #     """过滤GPS点"""
 
         # # 过滤密集点
         # previous_points = self.gps_points.copy()
@@ -196,8 +190,6 @@ class ImagePreprocessor:
         # self.visualizer.visualize_filter_step(
         #     self.gps_points, previous_points, "4-Dense Points")
 
-        return self.gps_points
-
     def divide_grids(self) -> Tuple[Dict[tuple, pd.DataFrame], Dict[tuple, tuple]]:
         """划分网格
         Returns:
@@ -262,8 +254,8 @@ class ImagePreprocessor:
         try:
             self.extract_gps()
             self.cluster()
-            # self.filter_time_group_overlap()
-            self.filter_points()
+            self.filter_isolated_points()
+            self.filter_time_group_overlap()
             grid_points, translations = self.divide_grids()
             self.copy_images(grid_points)
             self.logger.info("预处理任务完成")
@@ -280,8 +272,8 @@ class ImagePreprocessor:
 if __name__ == "__main__":
     # 创建配置
     config = PreprocessConfig(
-        image_dir=r"/home/cug/datasets/1815/project/images",
-        output_dir=r"/home/cug/ODM_output/1815",
+        image_dir=r"/home/cug/datasets/134/code/images",
+        output_dir=r"/home/cug/ODM_output/134",
 
         cluster_eps=0.01,
         cluster_min_samples=5,