A Cascade Learning Approach for Automated Detection of Locomotive Speed Sensor Using Imbalanced Data in ITS

Abstract

Automatic and intelligent railway locomotive inspection and maintenance are fundamental issues in high-speed rail applications and intelligent transportation system (ITS). Traditional locomotive equipment inspection is carried out manually on-site by workers, and the task is exhausting, cumbersome, and unsafe. Based on computer vision and machine learning, this paper presents an approach to the automatic detection of the locomotive speed sensor equipment, an important device in locomotives. Challenges to the detection of speed sensor mainly concerns complex background, motion blur, muddy noise, and variable shapes. In this paper, a cascade learning framework is proposed, which includes two learning stages: target localization and speed sensor detection, to reduce the complexity of the research object and solve the imbalance of samples. In the first stage, histogram of oriented gradient feature and support vector machine (HOG-SVM) model is used for multi-scale detection. Then, an improved LeNet-5 model is adopted in the second stage. To solve the problem of the imbalance of positive and negative samples of speed sensor, a combination strategy which draws on four individual classifiers is designed to construct an ensemble of classifier for recognition, and the results of three different algorithms are compared. The experimental results demonstrate that our approach is effective and robust with respect to changes in speed sensor patterns for robust equipment identification.

Keywords

• Cascade learning
• speed sensor detection
• imbalanced data
• ensemble learning