Songpengcheng Xia

Songpengcheng Xia

Auto-generated profile, based on publicly available information

Songpengcheng Xia

Shanghai Key Laboratory of Navigation and Location-Based Services, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
7 December 2020 in IEEE Sensors Journal
Verified
Journal Article
Closed access
TLTao Li
Tao Li
LPLing Pei
Ling Pei
YXYan Xiang
Yan Xiang
QWQi Wu
Qi Wu
SXSongpengcheng Xia
Songpengcheng Xia
WYWenxian Yu
Wenxian Yu
Light Detection and Ranging (LiDAR) based Simultaneous Localization and Mapping (SLAM) has drawn increasing interests in autonomous driving. However, LiDAR-SLAM suffers from accumulating errors which can be significantly mitigated by Global Navigation Satellite System (GNSS). Precise Point Positioning (PPP), an accurate GNSS operation mode independent of base stations, gains growing popularity in unmanned systems. Considering the features of the two technologies, LiDAR-SLAM and PPP, this paper proposes a SLAM system, namely P3-LOAM (PPP based LiDAR Odometry and Mapping) which couples LiDAR-SLAM and PPP. For better integration, we derive LiDAR-SLAM positioning covariance by using Singular Value Decomposition (SVD) Jacobian model, since SVD provides an explicit analytic solution of Iterative Closest Point (ICP), which is a key issue in LiDAR-SLAM. A novel method is then proposed to evaluate the estimated LiDAR-SLAM covariance. In addition, to increase the reliability of GNSS in urban canyon environment, we develop a LiDAR-SLAM assisted GNSS Receiver Autonomous Integrity Monitoring (RAIM) algorithm. Finally, we validate P3-LOAM with UrbanNav, a challenging public dataset in urban canyon environment. Comprehensive test results prove that, in terms of accuracy and availability, P3-LOAM outperforms benchmarks such as Single Point Positioning (SPP), PPP, LeGO-LOAM, SPP-LOAM, and the loosely coupled navigation system proposed by the publisher of UrbanNav.

1 February 2021 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
LPLing Pei
Ling Pei
SXSongpengcheng Xia
Songpengcheng Xia
Lei ChuLei Chu
Lei Chu
FXFanyi Xiao
Fanyi Xiao
QWQi Wu
Qi Wu
RQRobert Caiming Qiu
Robert Caiming Qiu
Together with the rapid development of the Internet of Things, human activity recognition (HAR) using wearable inertial measurement units (IMUs) becomes a promising technology for many research areas. Recently, deep-learning-based methods pave a new way of understanding and performing analysis of the complex data in the HAR system. However, the performance of these methods is mostly based on the quality and quantity of the collected data. In this article, we innovatively propose to build a large data set based on virtual IMUs and then address technical issues by introducing a multiple-domain deep learning framework consisting of three technical parts. In the first part, we propose to learn the single-frame human activity from the noisy IMU data with hybrid convolutional neural networks in the semisupervised form. For the second part, the extracted data features are fused according to the principle of uncertainty-aware consistency, which reduces the uncertainty by weighting the importance of the features. The transfer learning is performed in the last part based on the newly released archive of motion capture as surface shapes data set, containing abundant synthetic human poses, which enhances the variety and diversity of the training data set and is beneficial for the process of training and feature transfer in the proposed method. The efficiency and effectiveness of the proposed method have been demonstrated in the real deep inertial poser data set. The experimental results show that the proposed methods can surprisingly converge within a few iterations and outperform all competing methods.

10 September 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
SXSongpengcheng Xia
Songpengcheng Xia
Lei ChuLei Chu
Lei Chu
LPLing Pei
Ling Pei
ZZZixuan Zhang
Zixuan Zhang
WYWenxian Yu
Wenxian Yu
RQRobert Caiming Qiu
Robert Caiming Qiu
Together with the rapid development of the sensors technology in recent years, sensor-based human activity recognition (HAR) has shown promising performance using well-known supervised deep learning methods. However, it remains challenging in a realistic scenario, i.e., limited number of labeled samples and sensors. This article proposes a novel deep learning method to achieve accurate and robust HAR with only a single inertial measurement unit (IMU) sensor. Our contributions are twofold. First, based on the skinned multiperson linear (SMPL) model, we build a large synthetic HAR dataset containing multimodal measurements: acceleration and angular velocity, which were generated according to the forward kinematics. Second, We propose a multiple-level domain adaptive learning model with information-theoretically stimulated constraints to simultaneously align the distributions of low- and high-level representations of virtual and real HAR data. The proposed mutual information constraints encourage the neural network to learn a disentangled representation for the multimodal sensing data. Comprehensive experimental results on three publicly available datasets demonstrate that the proposed method compares favorably with competing ones and has robust performance with variable labeled samples.

17 November 2020 in IEEE Sensors Journal
Verified
Journal Article
Closed access
JLJinquan Li
Jinquan Li
LPLing Pei
Ling Pei
DZDanping Zou
Danping Zou
SXSongpengcheng Xia
Songpengcheng Xia
QWQi Wu
Qi Wu
WYWenxian Yu
Wenxian Yu
This paper proposes a novel simultaneous localization and mapping (SLAM) approach, namely Attention-SLAM, which simulates human navigation mode by combining a visual saliency model (SalNavNet) with traditional monocular visual SLAM. Firstly a visual saliency model namely SalNavNet is proposed. In SalNavNet, we introduce a correlation module and propose an adaptive Exponential Moving Average (EMA) module. These modules mitigate the center bias, which most current saliency models have. This novel idea enables the saliency maps generated by SalNavNet to pay more attention to the same salient object. An open-source saliency SLAM dataset namely Salient-Euroc is published, it consists of Euroc dataset and corresponding saliency maps. Moreover, we propose a new optimization method called Weighted Bundle Adjustment (Weighted BA) in Attention-SLAM. Most SLAM methods treat all the features extracted from the images as equal importance during the optimization process. In weighted BA, the feature points extracted from the salient regions have greater importance. Comprehensive test results prove that Attention-SLAM outperforms benchmarks such as Direct Sparse Odometry (DSO), ORB-SLAM, and Salient DSO in the 7 of 11 test cases. The test cases are all indoor scenes, with varying brightness, speed, and image distortion. Compared with ORB-SLAM, our method improves the accuracy by 4% and efficiency by 6.5% on average.

10 May 2022 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
SXSongpengcheng Xia
Songpengcheng Xia
Lei ChuLei Chu
Lei Chu
LPLing Pei
Ling Pei
WYWenxian Yu
Wenxian Yu
RQRobert Caiming Qiu
Robert Caiming Qiu
With the development of industrial and sensing technology, sensor-based activity recognition has become a promising technology for informatics applications. However, in a typical activity recognition procedure, sensory data segmentation, usually considered a pre-process with sliding-windows, rarely has been investigated and significantly affected the recognition performance. In this paper, we propose a novel deep-learning method to jointly segment and recognize activities with wearable sensors. Our contributions are three-fold: first, we introduce a multi-stage temporal convolutional network (MS-TCN) for sample-level activity prediction to overcome the multi-class windows problem. Second, for alleviating over-segmentation errors, our model forms a multi-task learning framework with a boundary prediction module to adjust the entire model's gradients. Third, we innovatively propose a boundary consistency loss to enforce the consistency of the activity and boundary prediction. Our method shows impressive performance on three public datasets, especially achieving 16% improvement over very recently advanced competing methods with class-average F1-score.

26 March 2024 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
SXSongpengcheng Xia
Songpengcheng Xia
Lei ChuLei Chu
Lei Chu
LPLing Pei
Ling Pei
JYJiarui Yang
Jiarui Yang
WYWenxian Yu
Wenxian Yu
RQRobert Caiming Qiu
Robert Caiming Qiu
Human activity recognition (HAR) with wearables is one of the serviceable technologies in ubiquitous and mobile computing applications. The sliding-window scheme is widely adopted while suffering from the multi-class windows problem. As a result, there is a growing focus on joint segmentation and recognition with deep-learning methods, aiming at simultaneously dealing with HAR and time-series segmentation issues. However, obtaining the full activity annotations of wearable data sequences is resource-intensive or time-consuming, while unsupervised methods yield poor performance. To address these challenges, we propose a novel method for joint activity segmentation and recognition with timestamp supervision, in which only a single annotated sample is needed in each activity segment. However, the limited information of sparse annotations exacerbates the gap between recognition and segmentation tasks, leading to sub-optimal model performance. Therefore, the prototypes are estimated by class-activation maps to form a sample-to-prototype contrast module for well-structured embeddings. Moreover, with the optimal transport theory, our approach generates the sample-level pseudo-labels that take advantage of unlabeled data between timestamp annotations for further performance improvement. Comprehensive experiments on four public HAR datasets demonstrate that our model trained with timestamp supervision is superior to the state-of-the-art weakly-supervised methods and achieves comparable performance to the fully-supervised approaches.