基于新型对抗自编码器的铁路货车车辆异物检测算法OACSCDCSTPCD
Foreign object detection algorithm for railway freight cars based on a novel adversarial autoencoder
货车运行故障动态图像检测系统通过人工方式对采集的铁路货车关键部位图像进行故障判别,效率低且易发生漏报.非人工故障检测多采用传统图像处理技术和基于深度学习的目标检测网络,存在受图像数据限制的缺点.为解决目前存在的故障图像的采集与标注难题,针对铁路货车故障中发生率最高的车辆异物故障,提出一种车辆异物检测算法.算法基于新型对抗自编码器,所用训练数据集由无标注的非异常图片组成.针对小目标异物,在对抗自编码器结构中引入注意力机制,并比较多种注意力机制在目标…查看全部>>
The Trouble of Moving Freight car Detection System(TFDS)utilizes manual methods to detect faults in captured images of key sections of railway freight cars,which is not only inefficient but also susceptible to false alarms.Non-manual fault detection methods typically employ traditional im-age processing techniques and deep learning-based target detection networks,which are limited by the available image data.To overcome the challenges associated with collect…查看全部>>
丁凤霞
北京交通大学 经济管理学院,北京 100044||国家能源投资集团有限责任公司,北京 100011
计算机与自动化
铁路货车车辆异物检测对抗自编码器故障检测注意力机制
railway freight carvehicle foreign object detectionadversarial autoencoderfault d-etectionattention mechanism
《北京交通大学学报》 2023 (5)
25-33,9
国家能源集团科技开发项目(CJNY-20-139)中央高校基本科研业务费专项资金(2022JBXT005)国家自然科学基金(52272429)Technology Development Program of China Energy Investment Corporation(CJNY-20-139)Fundamental Research Funds for the Central Universities(2022JBXT005)National Natural Science Foundation of China(52272429)
评论