Kewei Li

Kewei Li


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
26 December 2023 in Sensors
Verified
Journal Article
Open access
PDF file
JZJiachen Zhou
Jiachen Zhou
TSTaoyong Su
Taoyong Su
KLKewei Li
Kewei Li
JDJiyang Dai
Jiyang Dai
Object detection in drone aerial imagery has been a consistent focal point of research. Aerial images present more intricate backgrounds, greater variation in object scale, and a higher occurrence of small objects compared to standard images. Consequently, conventional object detection algorithms are often unsuitable for direct application in drone scenarios. To address these challenges, this study proposes a drone object detection algorithm model based on YOLOv5, named SMT-YOLOv5 (Small Target-YOLOv5). The enhancement strategy involves improving the feature fusion network by incorporating detection layers and implementing a weighted bidirectional feature pyramid network. Additionally, the introduction of the Combine Attention and Receptive Fields Block (CARFB) receptive field feature extraction module and DyHead dynamic target detection head aims to broaden the receptive field, mitigate information loss, and enhance perceptual capabilities in spatial, scale, and task domains. Experimental validation on the VisDrone2021 dataset confirms a significant improvement in the target detection accuracy of SMT-YOLOv5. Each improvement strategy yields effective results, raising the average precision by 12.4 percentage points compared to the original method. Detection improvements for large, medium, and small targets increase by 6.9%, 9.5%, and 7.7%, respectively, compared to the original method. Similarly, applying the same improvement strategies to the low-complexity YOLOv8n results in SMT-YOLOv8n, which is comparable in complexity to SMT-YOLOv5s. The results indicate that, relative to SMT-YOLOv8n, SMT-YOLOv5s achieves a 2.5 percentage point increase in average precision. Furthermore, comparative experiments with other enhancement methods demonstrate the effectiveness of the improvement strategies.

10 October 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YNYunfeng Nie
Yunfeng Nie
KAKang An
Kang An
Xingfeng ChenXingfeng Chen
Xingfeng Chen
LZLimin Zhao
Limin Zhao
WLWantao Liu
Wantao Liu
ZZZhaozhong Zhang
Zhaozhong Zhang
The extraction of sandy roads from remote sensing images is important for field ecological patrols and path planning. Extraction studies on sandy roads face limitations because of various factors (e.g., sandy roads may have poor continuity, may be obscured by external objects, and/or have multi-scale and banding characteristics), in addition to the absence of publicly available datasets. Accordingly, in this study, we propose using the remote sensing imagery of a sandy road (RSISR) dataset and design a sandy road extraction model (Parallel Attention Mechanism-Unet, or PAM-Unet) based on Gaofen-2 (GF-2) satellite images. Firstly, the model uses a residual stacking module, which can solve the problem of poor road feature consistency and improve the extraction of fine features. Secondly, we propose a parallel attention module (PAM), which can reduce the occlusion effect of foreign objects on roads during the extraction process and improve feature map reduction. Finally, with this model, the SASPP (Strip Atrous Spatial Pyramid Pooling) structure, which enhances the model’s ability to perceive contextual information and capture banding features, is introduced at the end of the encoder. For this study, we conducted experiments on road extraction using the RSISR dataset and the DeepGlobe dataset. The final results show the following: (a) On the RSISR dataset, PAM-Unet achieves an IoU value of 0.762, and its F1 and IoU values are improved by 2.7% and 4.1%, respectively, compared to U-Net. In addition, compared to the models Unet++ and DeepLabv3+, PAM-Unet improves IoU metrics by 3.6% and 5.3%, respectively. (b) On the DeepGlobe dataset, the IoU value of PAM-Unet is 0.658; compared with the original U-Net, the F1 and IoU values are improved by 2.5% and 3.1%, respectively. The experimental results show that PAM-Unet has a positive impact by way of improving the continuity of sandy road extraction and reducing the occlusion of irrelevant features, and it is an accurate, reliable, and effective road extraction method.

7 October 2023 in Sustainability
Verified
Journal Article
Open access
PDF file
FLFeng Lu
Feng Lu
KLKewei Li
Kewei Li
YNYunfeng Nie
Yunfeng Nie
YTYejia Tao
Yejia Tao
YYYihao Yu
Yihao Yu
Xing WangXing Wang
Xing Wang
Object detection methods of UAV (Unmanned Aerial Vehicle) images are greatly improved with the development of UAV technology. In comparison, the existing object detection methods of UAV images lack outstanding performance in the face of challenges such as small targets, dense scenes, sparse distribution, occlusion, and complex background, especially prominent in the task of vehicle detection. This paper proposed an improved YOLOv5s method to perform vehicle detection of UAV images. The CA (Coordinate Attention) is first applied to the neck of YOLOv5s to generate direction-aware and position-sensitive feature maps, respectively, to improve the detection accuracy of sparsely distributed vehicle targets in complex backgrounds. Then, an improved PAFPN (Path Aggregation Feature Pyramid Network) at the neck of YOLOv5s is proposed for more efficient detection of small and dense vehicle targets. Finally, the CIoU (Complete Intersection Over Union) loss function was used to calculate the bounding box regression to obtain a more comprehensive overlap measure to accommodate different shapes of vehicle targets. We conducted extensive experiments on the self-built UAV-OP (Unmanned Aerial Vehicle from Orthographic Perspective) dataset. The experimental results show that our method achieves the best detection accuracy with a small quantity of calculation increase compared with YOLOv5s. The mAP50 improved by 3%, and the mAP50:95 improved by 1.7% with a 0.3 GFlops increase.

6 March 2025 in The Visual Computer
Verified
Journal Article
Closed access
PDF file
CHChen ke Hao
Chen ke Hao
ZZZhiping Zhou
Zhiping Zhou
KLKewei Li
Kewei Li
TSTaoyong Su
Taoyong Su
ZZZhiping Zhou
Zhiping Zhou
CYChenghao Ying
Chenghao Ying

24 December 2023 in Aerospace
Verified
Journal Article
Open access
PDF file
CLChangwu Liang
Changwu Liang
HLHong Li
Hong Li
TSTaoyong Su
Taoyong Su
CFCaleb Alistair Frank
Caleb Alistair Frank
KLKewei Li
Kewei Li
An electrically controlled rotor (ECR), also known as a swashplateless rotor, eliminates the swashplate system to implement the primary control via the trailing-edge flaps (TEFs), which can result in enhancements in rotor performance, as well as substantial reductions in weight, drag, and cost. In this paper, the unsteady aerodynamic characteristics of the airfoil with TEF of a sample ECR under unsteady freestream condition are investigated. The CFD results are obtained with sliding and overset grid techniques that simulate the airfoil pitching and flap deflection. Comparative analysis of the aerodynamic characteristics under steady and unsteady freestream conditions at different advance ratios is conducted. At various advance ratios, the lift and drag coefficients are higher at a small angle of attack under unsteady freestream condition; however, it is the opposite at a large angle of attack. The peak values of the lift and drag coefficients show an increased trend with the increase in the advance ratio. On the contrary, the pitch moment and flap hinge moment coefficients demonstrate minor variation under unsteady freestream condition. Furthermore, the aerodynamic characteristics of airfoils become more unsteady with variation in the freestream. Therefore, the lift and drag coefficients of the ECR airfoil with TEF show significant differences between steady and unsteady freestream conditions; however, the pitch moment and the flap hinge moment coefficients show little difference.

6 April 2025 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
CYChenghao Ying
Chenghao Ying
ZZZhiping Zhou
Zhiping Zhou
KLKewei Li
Kewei Li
ZZZhaozhong Zhang
Zhaozhong Zhang
QYQingshuang Yang
Qingshuang Yang