Target aided identification in passive human THz-image
-
摘要: 提出一种被动式人体太赫兹安检仪的图像目标标注方法,用于辅助识别被安检人员隐藏携带的违禁物品。分析了探测器中心频率为0.1 THz的被动式太赫兹人体安检仪图像特点,根据其特点进行图像增强、分割、轮廓提取等处理,进而实现图像中的目标检测,将其目标位置映射在同场景同时间采集的可见光图像上。实验结果表明,该方法可以有效地提取并标示可疑目标,帮助快速发现衣物下的隐匿物品,提高太赫兹安检仪的实用性。Abstract: The THz image enhancement, segmentation and contour extraction algorithms are studied to achieve effective target image detection. Firstly, the terahertz images are enhanced and their grayscales are stretched. Then we apply global threshold segmentation to extracting the target, and finally the targets are marked on the visible image. The experimental results show that the algorithm proposed in this paper can extract and mark targets effectively, so that people can find suspicious objects under clothing more quickly. The algorithm can improve the usefulness of the terahertz security apparatus we have developed.
-
Key words:
- image processing /
- image enhancement /
- passive terahertz imaging /
- contour extraction /
- target detection
点击查看大图
计量
- 文章访问数: 1823
- HTML全文浏览量: 331
- PDF下载量: 691
- 被引次数: 0