目标检测数据集：行人跌倒检测（VOC标注格式的xml文件，已经做了训练集和测试集划分，对大部分公开数据集进行融合）

from lxml import etree import cv2 # 读取 xml 文件信息，并返回字典形式 def parse_xml_to_dict(xml): if len(xml) == 0: # 遍历到底层，直接返回 tag对应的信息 return {xml.tag: xml.text} result = {} for child in xml: child_result = parse_xml_to_dict(child) # 递归遍历标签信息 if child.tag != 'object': result[child.tag] = child_result[child.tag] else: if child.tag not in result: # 因为object可能有多个，所以需要放入列表里 result[child.tag] = [] result[child.tag].append(child_result[child.tag]) return {xml.tag: result} # xml 标注文件的可视化 def xmlShow(img, xml, save=True): image = cv2.imread(img) with open(xml, encoding='gb18030', errors='ignore') as fid: # 防止出现非法字符报错 xml_str = fid.read() xml = etree.fromstring(xml_str) data = parse_xml_to_dict(xml)["annotation"] # 读取 xml文件信息 ob = [] # 存放目标信息 for i in data['object']: # 提取检测框 name = str(i['name']) # 检测的目标类别 bbox = i['bndbox'] xmin = int(bbox['xmin']) ymin = int(bbox['ymin']) xmax = int(bbox['xmax']) ymax = int(bbox['ymax']) tmp = [name, xmin, ymin, xmax, ymax] # 单个检测框 ob.append(tmp) # 绘制检测框 for name, x1, y1, x2, y2 in ob: cv2.rectangle(image, (x1, y1), (x2, y2), color=(255, 0, 0), thickness=2) # 绘制矩形框 cv2.putText(image, name, (x1, y1 - 10), fontFace=cv2.FONT_HERSHEY_SIMPLEX, fontScale=0.5, thickness=1, color=(0, 0, 255)) # 保存图像 if save: cv2.imwrite('result.png', image) # # 展示图像 # cv2.imshow('test', image) # cv2.waitKey() # cv2.destroyAllWindows() if __name__ == "__main__": import os import random img_path = './data/train/images/' # 传入图片 image = [os.path.join(img_path, i) for i in os.listdir(img_path)] r = random.randint(0, len(image) - 1) # 生成随机索引 image_path = image[r] labels_path = image_path.replace('images', 'labels') # 自动获取对应的 xml 标注文件 labels_path = labels_path.replace('.jpg', '.xml') xmlShow(img=image_path, xml=labels_path, save=True)