upda0914

Bank_second_part/xbank_detect_process/analysis_result/same_model_img.py

@@ -0,0 +1,47 @@
+from tools_analysis import select_bbox_by_labels, iou_result_two
+
+
+def same_model_img_analysis_labels(example_list, result_dicts_list, relevancy, relevancy_para):
+    '''
+    example_list: 需要关联处理的目标标签集合
+    result_dicts_list: 当前图片检测结果，格式为[{labels1:result1},{labels2:result2},{labels2:result2}...]
+    '''
+
+    # 获得当前结果的标签集
+    result_labels_list = [list(re.keys())[0] for re in result_dicts_list]
+
+    # 判断是否存在example_list中的所有标签
+    continue_para = False
+    compara_labellist = [
+        label for label in example_list if label not in result_labels_list]
+
+    if compara_labellist:
+        return continue_para
+
+    else:
+
+        result_dicts_list_change = select_bbox_by_labels(
+            example_list, result_dicts_list)
+
+        if relevancy == 'overlap':
+
+            if len(example_list) == 2:
+
+                overlap_list = iou_result_two(
+                    result_dicts_list_change, relevancy_para)
+
+                return overlap_list
+
+        if relevancy == 'in_bbox':
+
+            pass
+
+
+def model_labels_selet(example_list, result_dict_list):
+    '''
+    直接从result中获得目标列表
+    '''
+    compara_labellist = [result_dict for result_dict in result_dict_list if list(
+        result_dict.keys()) in example_list]
+
+    return compara_labellist

Bank_second_part/xbank_detect_process/analysis_result/tools_analysis.py

@@ -0,0 +1,74 @@
+def iou_result_two(result_dict_list,iou_para):
+
+    result_0 = list(result_dict_list[0].values())[0]
+    result_1 = list(result_dict_list[1].values())[0]
+    label_0 = list(result_dict_list[0].keys())[0]
+    label_1 = list(result_dict_list[1].keys())[0]
+
+    return_lists = []
+
+    for re_0 in result_0:
+
+        for re_1 in result_1:
+
+            iou = calculate_iou(re_0, re_1)
+
+            if iou > iou_para:
+
+                label_dict_0 = {label_0: re_0}
+                label_dict_1 = {label_1: re_1}
+
+                return_lists.append(label_dict_0)
+                return_lists.append(label_dict_1)
+
+    return return_lists
+
+
+def calculate_iou(box1, box2):
+    """
+    计算两个边界框之间的IoU值
+
+    参数:
+    box1: 边界框1的坐标（x1, y1, x2, y2）
+    box2: 边界框2的坐标（x1, y1, x2, y2）
+
+    返回值:
+    iou: 两个边界框之间的IoU值
+    """
+    x1 = max(box1[0], box2[0])
+    y1 = max(box1[1], box2[1])
+    x2 = min(box1[2], box2[2])
+    y2 = min(box1[3], box2[3])
+
+    # 计算交集区域面积
+    intersection_area = max(0, x2 - x1 + 1) * max(0, y2 - y1 + 1)
+
+    # 计算边界框1和边界框2的面积
+    box1_area = (box1[2] - box1[0] + 1) * (box1[3] - box1[1] + 1)
+    box2_area = (box2[2] - box2[0] + 1) * (box2[3] - box2[1] + 1)
+
+    # 计算并集区域面积
+    union_area = box1_area + box2_area - intersection_area
+
+    # 计算IoU值
+    iou = intersection_area / union_area
+
+    return iou
+
+
+def select_bbox_by_labels(example_list, result_dicts_list):
+    '''
+    将result列表中的example列表内的bbox挑选出来,放到同一字典下
+    '''
+
+    result_dict_list_change = []
+    for label in example_list:
+        bbox_list = []
+        for result in result_dicts_list:
+            if list(result.keys()) == label:
+                bbox_list.append(list(result.values()))
+
+        result_dict_change = {label: bbox_list}
+        result_dict_list_change.append(result_dict_change)
+
+    return result_dict_list_change