Songyue Yang

Dr. Songyue Yang

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 October 2021 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
Zhangyu WangZhangyu Wang
Zhangyu Wang
GYGuizhen Yu
Guizhen Yu
Peng ChenPeng Chen
Peng Chen
Bin ZhouBin Zhou
Bin Zhou
Songyue YangSongyue Yang
Songyue Yang
Rail track segmentation is key to environmental perception of autonomous train. However, due to the complexity of railway track environment, critical issues such as the detection of rail tracks with different curvatures remain to be overcome. In this study, a novel architecture called FarNet is proposed for long-range railway track point cloud segmentation. The proposed FarNet is mainly divided into three parts, i.e., spherical projection, attention-aggregation network and results refinement. Specifically, spherical projection converts the LiDAR point cloud into a pseudo range image, and attention-aggregation network enables railway track detection using the pseudo range image. Furthermore, in the attention-aggregation network two components, i.e., spatial attention module and information aggregation module, are proposed to enhance the capability of rail track segmentation. Last, the results refinement helps further filter out the noise points after segmentation. Experimental results show that the proposed FarNet achieved 98.0% mean intersection-over-union (MIoU) and 98.9% mean pixel accuracy (MPA) for rail track segmentation.

9 December 2021 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
Songyue YangSongyue Yang
Songyue Yang
GYGuizhen Yu
Guizhen Yu
Zhangyu WangZhangyu Wang
Zhangyu Wang
Bin ZhouBin Zhou
Bin Zhou
Peng ChenPeng Chen
Peng Chen
QZQiang Zhang
Qiang Zhang
Rail-track detection is a core function for automated rail transit perception. However, existing methods cannot effectively detect the rail-tracks in a complex environment, especially in turnout scenarios. In this study, we propose a topology guided method to detect rail-tracks which includes the following four parts: Firstly, a neural network is used to obtain the pixels of the rail-lanes, and the geometric relationship between rail-lanes is mined by inverse perspective transformation. Secondly, the rail-lanes’ pixels are converted to rail-lanes’ key points and the topological relationship between the key points. Thirdly, the rail-lanes are reconnected through topological relationships between key points. Finally, the rail-track geometry features are used to match the rail-lanes. Experimental results show that the rail-track level F1 score of the proposed method reached 91.62%, which is state-of-the-art (SOTA) in this field. Furthermore, the proposed method has been tested and applied on the Hong Kong Metro Tsuen Wan Line.

5 April 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
WLWentao Liu
Wentao Liu
Bin ZhouBin Zhou
Bin Zhou
Zhangyu WangZhangyu Wang
Zhangyu Wang
GYGuizhen Yu
Guizhen Yu
Songyue YangSongyue Yang
Songyue Yang
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.

17 August 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
ZGZiren Gong
Ziren Gong
Zhangyu WangZhangyu Wang
Zhangyu Wang
GYGuizhen Yu
Guizhen Yu
WLWentao Liu
Wentao Liu
Songyue YangSongyue Yang
Songyue Yang
Bin ZhouBin Zhou
Bin Zhou
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.

3 November 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
HWHao Wang
Hao Wang
Zhangyu WangZhangyu Wang
Zhangyu Wang
GYGuizhen Yu
Guizhen Yu
Songyue YangSongyue Yang
Songyue Yang
YYYang Yang
Yang Yang
The integration of cameras and LiDAR sensors has emerged as a promising approach to enhance environmental perception and 3D reconstruction capabilities in autonomous vehicles and robotic systems. Precise extrinsic calibration is of paramount importance to achieve effective multi-sensor fusion applications. Traditional calibration methods often rely on manual procedures and specific calibration targets, which can be time-consuming and prone to errors. In contrast, Convolutional Neural Networks (CNNs) have shown potential in devising end-to-end calibration systems, leveraging their ability to extract robust features automatically. In this paper, MRCNet, an online end-to-end LiDAR-camera calibration network, which overcomes the limitations of traditional methods and previous CNN-based approaches, is proposed. This article introduces a multi-resolution feature extraction module, enabling the extraction of comprehensive and informative features from RGB images and depth images derived from point clouds. Additionally, the optical center distance loss, a novel concept that accounts for the camera’s optical imaging characteristics, facilitating more effective feature extraction is incorporated. MRCNet is the first online calibration network that considers the influence of camera imaging properties. This paper employs an iterative refinement process to progressively estimate the calibration error, allowing online extrinsic estimation. Evaluation tests on the KITTI Odometry dataset demonstrate the superior performance of MRCNet compared to existing learning-based methods, achieving a mean absolute calibration error of 0.350cm in translation and 0.033° in rotation. Furthermore, ablation studies validate the effectiveness of the modules of MRCNet. The code for MRCNet will be made publicly available at: https://github.com/AlexWang0214/MRCNet.

9 June 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Songyue YangSongyue Yang
Songyue Yang
Zhangyu WangZhangyu Wang
Zhangyu Wang
GYGuizhen Yu
Guizhen Yu
Bin ZhouBin Zhou
Bin Zhou
Peng ChenPeng Chen
Peng Chen
QZQiang Zhang
Qiang Zhang
Depth completion of forward objects is critical to safe and effective autonomous driving as it can estimate dense-depth from sparse LiDAR (i.e., Light Detection and Ranging) data and RGB images. The study proposes a self-supervised depth completion method to address the deficiency in depth sensing images caused by the uneven distribution of point-clouds generated by long-range LiDAR. The proposed method uses a stacked-hourglass-network structure as the backbone, which allows to perform multi-level deep fusion to extract features from uneven point-clouds. In addition, a fusion module is introduced to fuse global-local features from different stages of the network output, and a pooling guidance mechanism is designed to guide network convergence through adaptive pooling guidance depth construction. Field experiments were conducted on the Tsuen Wan Line in Hong Kong to verify the performance of the proposed network. The results indicate that the proposed network outperforms the benchmark self-supervised depth completion methods, with a root mean squared error (RMSE) of 8165.673mm and a mean absolute error (MAE) of 2596.418mm. Specifically, the RMSE and MAE were improved by 4.7% and 2.4%, respectively, compared to the benchmark methods.