Content area
Abstract
In railway transportation, the information is provided in literature and graphic styles. Generally, quite a lot information can not be obtained directly from the images. As a result, an artificial intelligence system, which can obtain information and perceive the environment, has to be established. In the driving equipment monitoring system, there is a lack of comprehensive analysis and utilization of the multiple monitoring data. This paper briefly introduces the research ideas and optimization directions of image-based data acquiring, such as template matching, support vector machine (SVM), and convolutional neural network (CNN) from the perspective of image detection. Then the characteristics, application scenarios, and possible future research directions of these three types of algorithms are compared and analyzed.