| 城市轨道交通小型障碍物检测 |
| |
| 引用本文： | 张林,沈拓,张轩雄.城市轨道交通小型障碍物检测[J].上海理工大学学报,2021,43(5):468-473. |
| |
| 作者姓名： | 张林 沈拓 张轩雄 |
| |
| 作者单位： | 上海理工大学 光电信息与计算机工程学院, 上海 200093;上海理工大学 光电信息与计算机工程学院, 上海 200093;同济大学 铁路基础设施和系统安全上海重点实验室, 上海 201804 |
| |
| 基金项目： | 国家自然科学基金资助项目(U1734211) |
| |
| 摘 要： | 障碍物是影响列车行车安全的重要因素，小型障碍物由于体积小，在检测中容易被遗漏。针对上述问题，提出了一种基于卷积神经网络的自动化检测算法。算法首先通过数据增强策略平衡样本数量，然后使用卷积网络进行特征融合，很好地结合了小型障碍物的位置信息和语义信息。实验结果表明，算法对列车前方的小型障碍物有良好的检测效果，能较好地实现小型障碍物的探测。
|
| 关 键 词： | 深度学习 卷积神经网络 小型障碍物 数据增强 特征融合 轨道交通 |
| 收稿时间： | 2021/1/4 0:00:00 |
Detection of small obstacles in urban rail transit |
| |
| ZHANG Lin,SHEN Tuo,ZHANG Xuanxiong.Detection of small obstacles in urban rail transit[J].Journal of University of Shanghai For Science and Technology,2021,43(5):468-473. |
| |
| Authors: | ZHANG Lin SHEN Tuo ZHANG Xuanxiong |
| |
| Institution: | School of Optical-Electrical and Computer Engineering, University of Shanghai of Science and Technology, Shanghai 200093, China;School of Optical-Electrical and Computer Engineering, University of Shanghai of Science and Technology, Shanghai 200093, China;Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety, Tongji University, Shanghai 201804, China |
| |
| Abstract: | Obstacles are an important factor affecting train operation safety.Due to little size, small obstacles can be ignored easily. To solve above problems, an automatic detection algorithm had been proposed based on convolutional neural network. Data augmentation was used in this algorithm to balance the sample size and then convolutional neural network is used to feature fusion, combining the location information and semantic information of small obstacles. The experimental results show that the algorithm mentioned has good detection effect on small obstacles. |
| |
| Keywords: | deep learning convolutional neural network small obstacles data augmentation feature fusion rail transit |
|
| 点击此处可从《上海理工大学学报》浏览原始摘要信息 |
| 点击此处可从《上海理工大学学报》下载免费的PDF全文 |
