Railway Track Identification and Extraction Based on Improved Convolutional Neural Network
Journal Title: Urban Mass Transit - Year 2024, Vol 27, Issue 9
Abstract
Objective Prevention and protection of foreign objects intrusion into railway becomes a hot research topic, and the division of intrusion areas requires detection of the track location. In order to determine the track location in the image, a method based on improved Mask R-CNN (Mask region convolutional neural network) combined with mathematical model is proposed to identify and extract the railway track. Method Firstly, Mask R-CNN is optimized and added with attention mechanism, and transfer learning is introduced into the above method to improve the model′s generalization ability. Then the optimized model is used to identify and segment the track, extracting the segmentation data and fitting with the corresponding mathematical expression to realize the identification and extraction of the track. The track in the image is divided into four categories and labeled with the Labelme labeling software, forming a training set and a test set. The training set is used to train the optimized model, and the test set to evaluate the detection results of the optimized model. Result & Conclusion The research results show that compared with other segmenting models and the original model, the proposed method performs well under the same training intensity, reaching 97.5% of the accuracy rate in track type determination, and basically above 80% in track segmentation. Tests show that the proposed method improves the general applicability of the detection by using the good performance of neural network, and can accurately determine the track type and segment the track.
Authors and Affiliations
Wen CHEN, Guoyi JI, Jinbai ZOU, Lidong ZHANG, Yanhan QIAO
Keywords
Related Articles
- EP ID EP744357
- DOI 10.16037/j.1007-869x.2024.09.049
- Views 7
- Downloads 0
Train Speed Measurement Approach Based on Wheel-axle Creep Rate Detection
Objective In urban rail transit systems, train velocity measuring and positioning technology offers critical information to many applications such as train autonomous driving, collision avoidance, dispatching and directi...
Stratum Deformation Characteristics Analysis of Underground-excavated Metro Tunnel in Construction Waste Backfill Layer
Objective There are more and more cases of metro tunnel engineering crossing through miscellaneous fill strata featured by high porosity, low strength, and easy deformation, resulting in unclear land subsidence mechanism...
Experimental Study of Rail Beam Joint Bolt Loosening Impact on Rail Structure Vibration in High-Speed Maglev Maintenance Base
Objective During the train debugging process, significant vibrations may occur in the steel rail beams of high-speed maglev maintenance bases due to their unique structural characteristics, potentially leading to bolt lo...
Optimization Design of Metro Vehicle Air Compressor Frame Structure Based on Adaptive Response Surface Method
Objective A finite element model of metro vehicle air compressor frame is established and verified through modal testing and vibration testing. It is found that the vertical bending modal frequency of the dryer frame coi...
Integration Research on Next Generation Comprehensive Monitoring System for Urban Underground Infrastructure Operation
Objective The development of urban underground space in China is showing a trend towards diversification, depth, and complexity, making it challenging to diagnose and decision-making on causative factors through multi-di...