A review of vision-based on-board obstacle detection and distance estimation in railways
D Ristić-Durrant, M Franke, K Michels - Sensors, 2021 - mdpi.com
This paper provides a review of the literature on vision-based on-board obstacle detection
and distance estimation in railways. Environment perception is crucial for autonomous …
and distance estimation in railways. Environment perception is crucial for autonomous …
Improved Mask R-CNN for obstacle detection of rail transit
D He, Y Qiu, J Miao, Z Zou, K Li, C Ren, G Shen - Measurement, 2022 - Elsevier
Accurate identification of obstacles shows great significance to improve the safety of
automatic operation trains. The ME Mask R-CNN is proposed to improve the accuracy of …
automatic operation trains. The ME Mask R-CNN is proposed to improve the accuracy of …
Obstacle detection of rail transit based on deep learning
D He, Z Zou, Y Chen, B Liu, X Yao, S Shan - Measurement, 2021 - Elsevier
Obstacle detection plays an important role in train automatic operation. To overcome the low
accuracy and poor real-time performance of traditional detection methods, and better detect …
accuracy and poor real-time performance of traditional detection methods, and better detect …
A camera and LiDAR data fusion method for railway object detection
W Zhangyu, Y Guizhen, W Xinkai… - IEEE Sensors …, 2021 - ieeexplore.ieee.org
Object detection on railway tracks, which is crucial for train operational safety, face
numerous challenges such as multiple types of objects and the complexity of train running …
numerous challenges such as multiple types of objects and the complexity of train running …
Rail transit obstacle detection based on improved CNN
D He, Z Zou, Y Chen, B Liu… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
With the continuous development of rail transit fully automatic operation, the urgent need to
improve train operation safety makes obstacle detection become the research focus. In this …
improve train operation safety makes obstacle detection become the research focus. In this …
Urban rail transit obstacle detection based on Improved R-CNN
D He, R Ren, K Li, Z Zou, R Ma, Y Qin, W Yang - Measurement, 2022 - Elsevier
Excellent active obstacle detection capability is critical to operate fully automatic trains safely
and reliably. There are some problems exist in the traditional sensor-based obstacle …
and reliably. There are some problems exist in the traditional sensor-based obstacle …
Learning from accidents: Machine learning for safety at railway stations
H Alawad, S Kaewunruen, M An - IEEE Access, 2019 - ieeexplore.ieee.org
In railway systems, station safety is a critical aspect of the overall structure, and yet,
accidents at stations still occur. It is time to learn from these errors and improve conventional …
accidents at stations still occur. It is time to learn from these errors and improve conventional …
A deep generative approach for rail foreign object detections via semisupervised learning
The automated inspection and detection of foreign objects help prevent potential accidents
and train derailments. Most existing approaches focus on the detection with prior labels …
and train derailments. Most existing approaches focus on the detection with prior labels …
Deep learning for real-time 3D multi-object detection, localisation, and tracking: Application to smart mobility
In core computer vision tasks, we have witnessed significant advances in object detection,
localisation and tracking. However, there are currently no methods to detect, localize and …
localisation and tracking. However, there are currently no methods to detect, localize and …
An efficient few-shot object detection method for railway intrusion via fine-tune approach and contrastive learning
T Ye, Z Zheng, X Li, Z Zhao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Railway intrusion detection plays an important role in the railway intelligent transportation
system, assisting the safe operation of trains. The existing deep-learning-based object …
system, assisting the safe operation of trains. The existing deep-learning-based object …