In this paper,deep learning technology was utilited to solve the railway track recognition in intrusion detection problem.The railway track recognition can be viewed as semantic segmentation task which extends image p...In this paper,deep learning technology was utilited to solve the railway track recognition in intrusion detection problem.The railway track recognition can be viewed as semantic segmentation task which extends image processing to pixel level prediction.An encoder-decoder architecture DeepLabv3+model was applied in this work due to its good performance in semantic segmentation task.Since images of the railway track collected from the video surveillance of the train cab were used as experiment dataset in this work,the following improvements were made to the model.The first aspect deals with over-fitting problem due to the limited amount of training data.Data augmentation and transfer learning are applied consequently to rich the diversity of data and enhance model robustness during the training process.Besides,different gradient descent methods are compared to obtain the optimal optimizer for training model parameters.The third problem relates to data sample imbalance,cross entropy(CE)loss is replaced by focal loss(FL)to address the issue of serious imbalance between positive and negative sample.Effectiveness of the improved DeepLabv3+model with above solutions is demonstrated by experiment results with different system parameters.展开更多
基金the Key Special Project in Intergovernmental International Scientific and Technological Innovation Cooperation of the National Key Research and Development Program of China(2017YFE0118600)。
文摘In this paper,deep learning technology was utilited to solve the railway track recognition in intrusion detection problem.The railway track recognition can be viewed as semantic segmentation task which extends image processing to pixel level prediction.An encoder-decoder architecture DeepLabv3+model was applied in this work due to its good performance in semantic segmentation task.Since images of the railway track collected from the video surveillance of the train cab were used as experiment dataset in this work,the following improvements were made to the model.The first aspect deals with over-fitting problem due to the limited amount of training data.Data augmentation and transfer learning are applied consequently to rich the diversity of data and enhance model robustness during the training process.Besides,different gradient descent methods are compared to obtain the optimal optimizer for training model parameters.The third problem relates to data sample imbalance,cross entropy(CE)loss is replaced by focal loss(FL)to address the issue of serious imbalance between positive and negative sample.Effectiveness of the improved DeepLabv3+model with above solutions is demonstrated by experiment results with different system parameters.
