Wentao Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wentao Liu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Guizhen Yu
Beihang University
6 shared publications - Zhangyu Wang
Beihang University
6 shared publications - Songyue Yang
School of Transportation Science and Engineering, Beihang University, Beijing, China
5 shared publications - Bin Zhou
School of Transportation Science and Engineering, Beihang University, Beijing, China
3 shared publications - Peng Chen
Beihang University
2 shared publications Yunpeng Wang
School of Transportation Science and Engineering, the State Key Laboratory of Intelligent Transportation System, and the Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, Beihang University, Beijing, China
1 shared publication
Latest Publications
- 11 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. PP (15513203) , 1-12
3DRailNet: A Multifocal Cameras Fusion Network for Long-Range 3-D Rail-Track Detection
Accurate 3-D rail-track detection is vital to the perception of the railway environments for autonomous trains. However, existing methods based on monocular image cannot capture 3-D spatial features, facing challenges in detecting 3-D rail-track in turnouts and distant scenarios. This study introduces 3DRailNet, a long-range 3-D rail-track detection network using multifocal cameras. 3DRailNet consists of two modules: disparity-based feature extraction (DFE) module and long-short rail-track detection (LSRD) module. Specifically, the DFE module utilizes multifocal images to generate a disparity image and depth image, acquiring 3-D depth features to enhance the spatial information of rail-track. Based on the 3-D depth features, the LSRD module designs a detection head for long and short focal cameras to predict the 3-D position of rail-track. Experimental results demonstrate that the mean F1 score (mF1) of our proposed 3DRailNet is 83.2%, establishing it as the state-of-the-art method in this field. All these results indicate that 3DRailNet has the potential to be readily applicable in 3-D rail-track detection in railway environments.
- 11 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. PP (15513203) , 1-12
3DRailNet: A Multifocal Cameras Fusion Network for Long-Range 3-D Rail-Track Detection
Accurate 3-D rail-track detection is vital to the perception of the railway environments for autonomous trains. However, existing methods based on monocular image cannot capture 3-D spatial features, facing challenges in detecting 3-D rail-track in turnouts and distant scenarios. This study introduces 3DRailNet, a long-range 3-D rail-track detection network using multifocal cameras. 3DRailNet consists of two modules: disparity-based feature extraction (DFE) module and long-short rail-track detection (LSRD) module. Specifically, the DFE module utilizes multifocal images to generate a disparity image and depth image, acquiring 3-D depth features to enhance the spatial information of rail-track. Based on the 3-D depth features, the LSRD module designs a detection head for long and short focal cameras to predict the 3-D position of rail-track. Experimental results demonstrate that the mean F1 score (mF1) of our proposed 3DRailNet is 83.2%, establishing it as the state-of-the-art method in this field. All these results indicate that 3DRailNet has the potential to be readily applicable in 3-D rail-track detection in railway environments.
- 19 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
RailBEV: A Vision-Based Bird’s-Eye-View Representation Network for 3-D Railway Object Detection
Three-dimensional railway object detection is vital to the environmental perception of intelligent railway transportation systems. However, owing to the complexity of railway environments, critical issues such as the detection of multiscale and distant objects remain to be overcome. This study proposes a vision-based architecture called RailBEV, which introduces bird’s-eye-view (BEV) representation within 3-D railway object detection. RailBEV is mainly divided into two parallel parts: the depth supervision view transformation (DSVT) and long-range supervision (LRS) modules. Specifically, the DSVT module designed a novel depth supervision method to transform the front view (FV) images into the BEV plane. The LRS module leverages an additional 3-D detection head to guide a 2-D image backbone to learn extra 3-D object information and enhance the capability of long-range object detection. Experimental results demonstrate that the proposed RailBEV exhibits a mean average precision (mAP) of 38.6%, which is 4.4% higher than the baseline 3-D object detection network BEVDepth. Moreover, the results show that RailBEV effectively supports long-range detection and identifies multiscale and short-range objects. All these indicate that RailBEV has the potential to be readily applicable in 3-D railway object detection.
- 19 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
RailBEV: A Vision-Based Bird’s-Eye-View Representation Network for 3-D Railway Object Detection
Three-dimensional railway object detection is vital to the environmental perception of intelligent railway transportation systems. However, owing to the complexity of railway environments, critical issues such as the detection of multiscale and distant objects remain to be overcome. This study proposes a vision-based architecture called RailBEV, which introduces bird’s-eye-view (BEV) representation within 3-D railway object detection. RailBEV is mainly divided into two parallel parts: the depth supervision view transformation (DSVT) and long-range supervision (LRS) modules. Specifically, the DSVT module designed a novel depth supervision method to transform the front view (FV) images into the BEV plane. The LRS module leverages an additional 3-D detection head to guide a 2-D image backbone to learn extra 3-D object information and enhance the capability of long-range object detection. Experimental results demonstrate that the proposed RailBEV exhibits a mean average precision (mAP) of 38.6%, which is 4.4% higher than the baseline 3-D object detection network BEVDepth. Moreover, the results show that RailBEV effectively supports long-range detection and identifies multiscale and short-range objects. All these indicate that RailBEV has the potential to be readily applicable in 3-D railway object detection.
- 10 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (8) , 12761-12773
RailFusion: A Lidar-Camera Data Interaction Network for 3-D Railway Object Detection
Accurate detection of 3D objects is vital to the perception of the railway environments for the safe operation autonomous trains, particularly given the complexity of railway environments and the challenges in detecting objects of variable sizes and of distant objects. This study introduces RailFusion, a LiDAR-Camera fusion network for integrating multi-modal features. RailFusion consists of two main modules: Cross-Domain Feature Extraction (CDFE) and Multi-Modal Fusion (MMF). Specifically, the CDFE module is designed with a novel feature extraction method to enhance cross-domain features interaction by utilizing LiDAR spatial depth and image semantic information. The MMF module uses deformable attention for aligning and fusing multi-modal features. Further to this, the channel normalization fusion is proposed to assign channel weights. Experimental results show that the mean average-precision (mAP) of our proposed RailFusion is 57.2%, which is 8.4% higher than the baseline 3D object detection network BEVFusion. Moreover, the results show that RailFusion is applicable to long-range detection as well as for detecting varying sized and short-range objects. All these indicate that RailFusion has the potential to be readily applicable in 3D object detection in railway environments.
- 10 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (8) , 12761-12773
RailFusion: A Lidar-Camera Data Interaction Network for 3-D Railway Object Detection
Accurate detection of 3D objects is vital to the perception of the railway environments for the safe operation autonomous trains, particularly given the complexity of railway environments and the challenges in detecting objects of variable sizes and of distant objects. This study introduces RailFusion, a LiDAR-Camera fusion network for integrating multi-modal features. RailFusion consists of two main modules: Cross-Domain Feature Extraction (CDFE) and Multi-Modal Fusion (MMF). Specifically, the CDFE module is designed with a novel feature extraction method to enhance cross-domain features interaction by utilizing LiDAR spatial depth and image semantic information. The MMF module uses deformable attention for aligning and fusing multi-modal features. Further to this, the channel normalization fusion is proposed to assign channel weights. Experimental results show that the mean average-precision (mAP) of our proposed RailFusion is 57.2%, which is 8.4% higher than the baseline 3D object detection network BEVFusion. Moreover, the results show that RailFusion is applicable to long-range detection as well as for detecting varying sized and short-range objects. All these indicate that RailFusion has the potential to be readily applicable in 3D object detection in railway environments.
- 7 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (5) , 4077-4088
Key Point Estimate Network for Rail-Track Detection
Rail-track detection is a crucial function for an active obstacle avoidance system in trains. However, existing methods face challenges in effectively detecting rail-tracks, particularly in turnout scenarios. This study introduces a novel rail-track detection approach using a key-point estimate network. The network treats the rail-track as a pair and constructs a dedicated model for detection. Additionally, a pseudo-attention mechanism leverages the detection output from previous stages, enabling the network to focus on the rail-track region. Also, a dislocation assignment mechanism is proposed to address label assignment confusion at turnouts. Moreover, a rail-track generalized IoU is also introduced, treating the rail-track as a pair and adds a correction term to enhance detection performance. Experimental results demonstrate that the proposed method achieves a remarkable mF1 score of 69.42%, establishing it as the state-of-the-art (SOTA) in this field. Furthermore, the effectiveness of the proposed method has been validated and applied in real-world testing on the Hong Kong Metro Tsuen Wan Line.
- 7 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (5) , 4077-4088
Key Point Estimate Network for Rail-Track Detection
Rail-track detection is a crucial function for an active obstacle avoidance system in trains. However, existing methods face challenges in effectively detecting rail-tracks, particularly in turnout scenarios. This study introduces a novel rail-track detection approach using a key-point estimate network. The network treats the rail-track as a pair and constructs a dedicated model for detection. Additionally, a pseudo-attention mechanism leverages the detection output from previous stages, enabling the network to focus on the rail-track region. Also, a dislocation assignment mechanism is proposed to address label assignment confusion at turnouts. Moreover, a rail-track generalized IoU is also introduced, treating the rail-track as a pair and adds a correction term to enhance detection performance. Experimental results demonstrate that the proposed method achieves a remarkable mF1 score of 69.42%, establishing it as the state-of-the-art (SOTA) in this field. Furthermore, the effectiveness of the proposed method has been validated and applied in real-world testing on the Hong Kong Metro Tsuen Wan Line.
- 17 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (19) , 23780-23791
FecNet: A Feature Enhancement and Cascade Network for Object Detection Using Roadside LiDAR
Roadside LiDAR is commonly used to record the traffic data of the whole intersection scene or road segment in intelligent transportation systems (ITS). However, general deep-learning object detection methods do not adequately consider the static background captured by roadside LiDAR. Moreover, critical issues remain to be overcome in object detection using roadside LiDAR: false alarms caused by complex background interference and multi-scale objects with limited characteristics. To this end, a feature enhancement and cascade network (FecNet) is proposed to alleviate the problems. From the perspective of feature enhancement, FecNet improves foreground feature discrimination by extracting foreground information and fusing it with feature maps of multiple stages. Also, from the perspective of feature cascade, a feature cascade backbone is proposed to enhance the localization and contextual information of multi-scale objects with limited characteristics. Comprehensive experiments are conducted using a roadside LiDAR dataset. The experimental results suggest that FecNet is superior to the benchmark detectors and achieves better computational efficiency and detection accuracy.
- 17 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (19) , 23780-23791
FecNet: A Feature Enhancement and Cascade Network for Object Detection Using Roadside LiDAR
Roadside LiDAR is commonly used to record the traffic data of the whole intersection scene or road segment in intelligent transportation systems (ITS). However, general deep-learning object detection methods do not adequately consider the static background captured by roadside LiDAR. Moreover, critical issues remain to be overcome in object detection using roadside LiDAR: false alarms caused by complex background interference and multi-scale objects with limited characteristics. To this end, a feature enhancement and cascade network (FecNet) is proposed to alleviate the problems. From the perspective of feature enhancement, FecNet improves foreground feature discrimination by extracting foreground information and fusing it with feature maps of multiple stages. Also, from the perspective of feature cascade, a feature cascade backbone is proposed to enhance the localization and contextual information of multi-scale objects with limited characteristics. Comprehensive experiments are conducted using a roadside LiDAR dataset. The experimental results suggest that FecNet is superior to the benchmark detectors and achieves better computational efficiency and detection accuracy.
- 5 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (10) , 11057-11069
FPPNet: A Fixed-Perspective-Perception Module for Small Object Detection Based on Background Difference
A roadside sensing unit can provide over-the-horizon perception information for autonomous vehicles due to its high perception perspective. However, numerous challenges need to be overcome such as the missing detection of small objects and occluded objects. To this end, this study proposed a Fixed Perspective Perception (FPP) module, which considered background subtraction and a fixed camera for small object detection. The proposed FPP module was divided into two parts: a Grayscale Background Subtraction (GBS) sub-module and a Background-Current Image Fusion (BCF) sub-module. Specifically, the GBS sub-module introduces background spatial information into a current frame and the BCF sub-module combines feature maps of a current frame and background by using channel attention. Moreover, we designed an object detection network called FPPNet which uses the FPP module to facilitate small object detection. Experimental results demonstrate that the FPPNet achieved 39.8% average precision small(AP S ) and 65.7% average precision( AP ) in a Dair-V2X-I dataset. Futhermore, we conducted an extension of the FPP module to mainstream object detection networks such as CenterNet, Faster-Rcnn and RetinaNet. Experimental results show that the proposed module can effectively improve small object detection accuracy of the networks mentioned above.
- 5 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (10) , 11057-11069
FPPNet: A Fixed-Perspective-Perception Module for Small Object Detection Based on Background Difference
A roadside sensing unit can provide over-the-horizon perception information for autonomous vehicles due to its high perception perspective. However, numerous challenges need to be overcome such as the missing detection of small objects and occluded objects. To this end, this study proposed a Fixed Perspective Perception (FPP) module, which considered background subtraction and a fixed camera for small object detection. The proposed FPP module was divided into two parts: a Grayscale Background Subtraction (GBS) sub-module and a Background-Current Image Fusion (BCF) sub-module. Specifically, the GBS sub-module introduces background spatial information into a current frame and the BCF sub-module combines feature maps of a current frame and background by using channel attention. Moreover, we designed an object detection network called FPPNet which uses the FPP module to facilitate small object detection. Experimental results demonstrate that the FPPNet achieved 39.8% average precision small(AP S ) and 65.7% average precision( AP ) in a Dair-V2X-I dataset. Futhermore, we conducted an extension of the FPP module to mainstream object detection networks such as CenterNet, Faster-Rcnn and RetinaNet. Experimental results show that the proposed module can effectively improve small object detection accuracy of the networks mentioned above.