Sheng Xu

Dr. Sheng Xu


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
16 September 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
AHAng He
Ang He
XLXiaobo Li
Xiaobo Li
XWXimei Wu
Ximei Wu
CSChengyue Su
Chengyue Su
JCJing Chen
Jing Chen
Xiaobin GuoXiaobin Guo
Xiaobin Guo
Unmanned aerial vehicles (UAVs) equipped with thermal infrared (TIR) cameras play a crucial role in combating nocturnal wildlife poaching. However, TIR images often face challenges such as jitter, and wildlife overlap, necessitating UAVs to possess the capability to identify blurred and overlapping small targets. Current traditional lightweight networks deployed on UAVs struggle to extract features from blurry small targets. To address this issue, we developed ALSS-YOLO, an efficient and lightweight detector optimized for TIR aerial images. Firstly, we propose a novel Adaptive Lightweight Channel Split and Shuffling (ALSS) module. This module employs an adaptive channel split strategy to optimize feature extraction and integrates a channel shuffling mechanism to enhance information exchange between channels. This improves the extraction of blurry features, crucial for handling jitter-induced blur and overlapping targets. Secondly, we developed a Lightweight Coordinate Attention (LCA) module that employs adaptive pooling and grouped convolution to integrate feature information across dimensions. This module ensures lightweight operation while maintaining high detection precision and robustness against jitter and target overlap. Additionally, we developed a single-channel focus module to aggregate the width and height information of each channel into four-dimensional channel fusion, which improves the feature representation efficiency of infrared images. Finally, we modify the localization loss function to emphasize the loss value associated with small objects to improve localization accuracy. Extensive experiments on the BIRDSAI and ISOD TIR UAV wildlife datasets show that ALSS-YOLO achieves state-of-the-art performance, Our code is openly available at https://github.com/helloworlder8/computer_vision .

3 March 2022 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
LHLirong Huang
Lirong Huang
SXSheng Xu
Sheng Xu
Input delay could lead to instability of an impulsive control system. But the problem of input delay has been seldom studied. This work addresses the fundamentally important problem in impulsive control theory. By a novel approach, we establish Lyapunov-Razumikhin-type theorems on exponential stability of stochastic impulsive delay systems. Based on our fundamental results, we develop a foundational theory for impulsive stabilization of stochastic delay systems with input delay. Our proposed theory provides an impulsive control design method for systems with input delay and the upper bound of input delay which the designed impulsive control scheme can admit while the resulting controlled system remains exponentially stable. As future work, we present event-triggered impulsive control systems that are a natural and significant generalization of the classical impulsive control systems in the literature.

11 February 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
HWHeqing Wang
Heqing Wang
SXSheng Xu
Sheng Xu
YCYuandian Chen
Yuandian Chen
CSChengyue Su
Chengyue Su
Falls are one of the significant safety hazards for the elderly. Current object detection models for fall detection often suffer from high computational complexity, limiting their deployment on resource-constrained edge devices. Although lightweight models can reduce computational requirements, they typically compromise detection accuracy. To address these challenges, and considering the more lightweight architecture of YOLOv5 compared to other YOLO series models such as YOLOv8, we propose a lightweight fall detection model based on YOLOv5, named Lightweight Fall Detection YOLO (LFD-YOLO). Our method introduces a novel lightweight feature extraction module, Cross Split RepGhost (CSRG), which reduces information loss during feature map transmission. We also integrate an Efficient Multi-scale Attention (EMA) to enhance focus on the human pose. Moreover, we propose a Weighted Fusion Pyramid Network (WFPN) and utilize Group Shuffle Convolutions (GSConv) to reduce the model’s computational complexity and improve the efficiency of multi-scale feature fusion. Additionally, we design an Inner Weighted Intersection over Union (Inner-WIoU) loss to accelerate model convergence and enhance generalization. We construct a Person Fall Detection Dataset (PFDD) dataset covering diverse scenarios. Experimental results on the PFDD and the publicly available Falling Posture Image Dataset (FPID) datasets show that, compared to YOLOv5s, LFD-YOLO improves mAP0.5 by 1.5% and 1.7%, respectively, while reducing the number of parameters and calculations by 19.2% and 21.3%. Furthermore, compared to YOLOv8s, LFD-YOLO reduces the number of parameters and calculations by 48.6% and 56.1%, respectively, while improving mAP0.5 by 0.3% and 0.5%. These results demonstrate that LFD-YOLO achieves higher detection accuracy and lower computational complexity, making it well-suited for fall detection tasks.

24 April 2025 in Nonlinear Dynamics
Verified
Journal Article
Closed access
PDF file
LLLiwei Luo
Liwei Luo
SXSheng Xu
Sheng Xu
CSChengyue Su
Chengyue Su
MXMengshan Xie
Mengshan Xie
JLJinfa Li
Jinfa Li

7 January 2025 in Frontiers in Plant Science
Verified
Journal Article
Open access
PDF file
AHAng He
Ang He
XWXimei Wu
Ximei Wu
XXXing Xu
Xing Xu
JCJing Chen
Jing Chen
Xiaobin GuoXiaobin Guo
Xiaobin Guo
SXSheng Xu
Sheng Xu
Precise segmentation of unmanned aerial vehicle (UAV)-captured images plays a vital role in tasks such as crop yield estimation and plant health assessment in banana plantations. By identifying and classifying planted areas, crop areas can be calculated, which is indispensable for accurate yield predictions. However, segmenting banana plantation scenes requires a substantial amount of annotated data, and manual labeling of these images is both timeconsuming and labor-intensive, limiting the development of large-scale datasets. Furthermore, challenges such as changing target sizes, complex ground backgrounds, limited computational resources, and correct identification of crop categories make segmentation even more difficult. To address these issues, we propose a comprehensive solution. First, we designed an iterative optimization annotation pipeline leveraging SAM2’s zero-shot capabilities to generate high-quality segmentation annotations, thereby reducing the cost and time associated with data annotation significantly. Second, we developed ALSS-YOLO-Seg, an efficient lightweight segmentation model optimized for UAV imagery. The model’s backbone includes an Adaptive Lightweight Channel Splitting and Shuffling (ALSS) module to improve information exchange between channels and optimize feature extraction, aiding accurate crop identification. Additionally, a Multi-Scale Channel Attention (MSCA) module combines multi-scale feature extraction with channel attention to tackle challenges of varying target sizes and complex ground backgrounds. We evaluated the zero-shot segmentation performance of SAM2 on the ADE20K and Javeri datasets. Our iterative optimization annotation pipeline demonstrated a significant reduction in manual annotation effort while achieving high-quality segmentation labeling. Extensive experiments on our custom Banana Plantation segmentation dataset show that ALSS-YOLO-Seg achieves state-of-the-art performance. Our code is openly available at https://github.com/helloworlder8/computer_vision.

16 April 2019 in International Journal of Aerospace Engineering
Verified
Journal Article
Open access
PDF file
JSJianmin Su
Jianmin Su
CSCHENGYUE SU
CHENGYUE SU
SXSheng Xu
Sheng Xu
XYXiaoxing Yang
Xiaoxing Yang
A tilt-rotor aircraft can switch between two flight configurations (the helicopter configuration and the fixed-wing plane configuration) by tilting its rotors. In the process of rotor tilting, the nacelles which drive the rotors tilt together with the rotors. Because the mass of the nacelles cannot be ignored compared to the mass of the whole aircraft, the tilting of the nacelles is a coupling motion of the body and the nacelles. In order to better character the aircraft dynamics during the nacelle tilting, a multibody model is established in this paper. In this multibody model, Kane’s method is used to build a dynamic model of a tilt-rotor aircraft. The generalized rates are used to describe the movement of the body and the nacelles (with rotors). The generalized active forces and generalized inertial forces of both the body and the nacelles (with rotors) are obtained, respectively, and the first-order differential equations of the generalized rates are obtained. The longitudinal trim of the XV-15 aircraft is calculated according to the single-body model and our multibody model, in this paper, and the results verify the correctness of the multibody model. In the process of nacelle inclination angle command tracking, the multibody model can provide more information about the disturbance torque of the nacelle than the single-body model, and model inversion control based on the proposed multibody model can obtain a better tracking result than a PID control method only using nacelle angle feedback information.