LLLirong Lian

Lirong Lian

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lirong Lian has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • RGBD Feature-Level Fusion Object Detection for Fastener Defect and Foreign Matter in Track

    by Yang Gao, Yong Qin, Zhiwei Cao, Lirong Lian, Genwang Peng, Linlin Kou

  • 3-D Object Detection for Railway: A Comprehensive Survey

    by Lirong Lian, Yong Qin, Zhiwei Cao, Yang Gao, Zhenhao Liu, Qiao Li, Xiaoqing Cheng

    Reliable 3D perception is indispensable for the next generation of autonomous railways (GoA4). This paper presents a comprehensive survey of 3D object detection tailored for railway environments. Unlike conventional automotive-focused reviews, our contributions are threefold. First, we establish a robust metrological foundation by deriving quantitative sensor requirements, such as angular resolution and focal length, necessary to detect critical obstacles at ultra-long ranges (>500 m). Second, we propose a systematic hierarchical taxonomy that organizes the landscape of detection methods, encompassing LiDAR, cameras, and other vital sensors like millimeter-wave radar, distributed fiber optic sensing (DFOS), and infrared thermal imaging. We critically evaluate these modalities and their multi-modal fusion strategies against specific railway demands regarding data sparsity and operational reliability. Third, we offer insightful perspectives on key open challenges, including real-time edge deployment, uncertainty-based fail-safe mechanisms, and air-ground-vehicle cooperative perception. This survey bridges deep learning algorithms with railway instrumentation standards, providing a crucial reference for developing safer, more robust intelligent railway perception systems.


  • Segmented-Aggregated Framework With Internal–External Constraint Mechanism for Unsupervised Track Anomaly Detection

    by Yang Gao, Zhiwei Cao, Yong Qin, Lirong Lian, Linlin Kou, Yaguan Wang

    The track is the basis of railway, and track defect detection is very important for train safety. Currently, the supervised track defect detection methods focus on detecting known category defects, but these methods cannot cover all categories of defects. Furthermore, the serious interference of complex environments also poses a significant challenge to the unknown category track defect detection. To address the deficiencies, this paper proposes an unsupervised track anomaly detection algorithm using segmented-aggregated framework with internal-external constraint mechanism, comprising three fundamental modules. First, the regional segmentation module is proposed to facilitate the precise regionalization of key track components at the pixel level, minimizing the complex background interference. Second, a novel self-generating feature parameterization module is proposed, which employs a self-generating feature aggregation network and fitting function to obtain the optimal fitting parameters. Finally, this paper presents an internal-external constraint metric anomaly score calculation module to detect anomalies complementally. The external constraint considers the difference between the test image and normal images, while the internal constraint complements measurement of internal difference in the test image. The efficacy of the algorithm is verified on the track anomaly dataset and publicly available dataset. The results indicate that the image AUROC and pixel AUROC of the proposed algorithm can reach 97.82% and 99.85% respectively. And the image F1 can reach 88.34% and is markedly superior to other state-of-the-art anomaly detection algorithms.


  • RAE3D: Multiscale Aggregation-Enhanced 3D Object Detection for Rail Transit Obstacle Perception

    by Lirong Lian, Zhiwei Cao, Yong Qin, Yang Gao, Wei Li, Jie Bai, Xuanyu Ge, Tangwen Yang

    Point cloud-based 3D object detection technology provides precise information for detecting obstacles in front of trains. In rail transit scenarios, obstacles are usually located at a distance, and the sparsity of point cloud data leads to information loss during feature extraction and spatial transformation, adversely affecting the accuracy of obstacle detection. To tackle this issue, we propose RAE3D, a single-stage end-to-end architecture that incorporates a multiscale voxel feature aggregation module on point queries (MVA-PQ) and a bird's-eye view multilevel auxiliary (BEV-MLA) module for efficient 3D object detection. The MVA-PQ module encodes multiscale voxel features into centroids of the final voxel layer, integrating spatial and scale information. The BEV-MLA module converts shallow 3D features into sparse 2D features using height compression, guiding the network to learn the spatial structure of small objects. We also introduce a 3D centroid offset loss for optimizing bounding boxes. Extensive experiments on the Rail3D and KITTI datasets have demonstrated the superiority of the proposed RAE3D.


  • A Continuous Autonomous Train Positioning Method Using Stereo Vision and Object Tracking

    by Lirong Lian, Yong Qin, Zhiwei Cao, Yang Gao, Jie Bai, Xuanyu Ge, Baoqing Guo

    Accurate and reliable train positioning is essential for safe railway operations. However, traditional infrastructure-based methods lack the ability for autonomy and continuous positioning. To solve the problem, we propose a novel modular visual processing framework for continuous train positioning. Environmental information captured by stereo vision sensors is processed using a feature extraction algorithm to detect landmarks along the railway. The detection results are input into a dual-stream parallel processing architecture, where an anchor-based stereo matching module calculates the depth values of detected landmarks, providing essential spatial information. Simultaneously, a dynamic region of interest-based multiobject tracking module assigns unique identification codes to each landmark, facilitating the integration of landmark detection results with their corresponding depth values. This correlation allows for the tracking of changes in landmark positions and the calculation of displacement caused by train motion, leading to a more accurate estimation of the train's location. Subsequently, the train mileage is matched against a database track map to obtain the final precise position. Field tests on Beijing Metro Line 9 and the Capital Airport Line demonstrate an average mean relative error of 0.19% and positioning accuracy within 1 m over a range of 100 m.


  • An Anomaly Detection Method for Railway Track Using Semisupervised Learning and Vision-Lidar Decision Fusion

    by Xuanyu Ge, Zhiwei Cao, Yong Qin, Yang Gao, Lirong Lian, Jie Bai, Hang Yu

    Anomaly detection of the railway track is essential to protect the safety of railway transportation. However, the railway track is often disturbed by unknown anomalies, making it challenging to detect anomalies using only supervised learning and visual sensors. To address these problems, this paper proposes a railway track anomaly detection method using semi-supervised learning and vision-lidar decision fusion. The method consists of three parts: supervised pre-detection, semi-supervised re-detection, and decision-level fusion. In the pre-detection stage, an enhanced instance segmentation algorithm is used to predetect known and unknown anomalies to improve the overall performance. In the re-detection stage, the reconstruction method, semi-supervised learning, and structured light point cloud are combined to re-detect anomalies, especially unknown anomalies. In the fusion stage, the fusion of pre-detection and redetection at the decision level further advances the accuracy and credibility of anomaly detection. Experimental results show that the proposed method achieves a mean average precision (mAP 0.50:0.95) of 92.2% and a mean average recall (mAR 0.50:0.95) of 94.5%. The proposed method is superior to the single vision-based or point cloud-based methods in anomaly detection. In addition, the proposed method provides a general solution to anomaly detection and extends the application of structured light point cloud.


  • Densely Multiscale Fusion Network for Lightweight and Accurate Semantic Segmentation of Railway Scenes

    by Lirong Lian, Zhiwei Cao, Yong Qin, Yang Gao, Jie Bai, Hang Yu, Limin Jia

    Semantic segmentation in railway scenes constitutes a fundamental task in the context of autonomous train driving, serving as a critical source of positional information for other visual tasks. Yet, prior semantic segmentation algorithms have faced challenges in achieving real-time and precise railway panoptic segmentation. Railway scene images often have highly imbalanced content density. Hence, the distribution of different regions in the image is highly non-uniform, which leads to the issue of semantic sample imbalance. To achieve this, we propose a dense multi-scale fusion network (DMFNet), a lightweight and precise semantic segmentation framework tailored for railway scenes. DMFNet employs a network framework that combines dense connections and multi-scale fusion to efficiently extract and utilize features. To enhance the feature extraction capability of the neural network, we design a lightweight residual block with multiple scales, composed of large convolution kernels. Additionally, we introduce a novel method for reassigning loss function weights to balance the samples within railway scenes. Extensive experimentation demonstrates that our DMFNet achieves outstanding results on railway scene datasets. It is designed to provide a lightweight and accurate semantic segmentation solution for railway scenes.