Jun Li

Dr. Jun Li


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
31 March 2020 in IEEE Access
Verified
Journal Article
Open access
HZHuibing Zhang
Huibing Zhang
LQLongfei Qin
Longfei Qin
JLJun Li
Jun Li
YGYunchuan Guo
Yunchuan Guo
YZYa Zhou
Ya Zhou
ZXZhi Xu
Zhi Xu
It is very challenging to detect traffic signs using a high-precision real-time approach in realistic scenes with respect to driver-assistance systems for driving vehicles and autonomous driving. To address this challenge, in this paper, a new detection scheme (named MSA_YOLOv3) is proposed to accurately achieve real-time localization and classification of small traffic signs. First, data augmentation is achieved using image mixup technology. Second, a multi-scale spatial pyramid pooling block is introduced into the Darknet53 network to enable the network to learn object features more comprehensively. Finally, a bottom-up augmented path is designed to enhance the feature pyramid in YOLOv3, and the result is to achieve accurate localization of objects by utilizing fine-grained features effectively in the lower layers. According to the tests on the TT100K dataset (which is a dataset for traffic sign detection), the performance of the proposed MSA_YOLOv3 is better than that of YOLOv3 in detecting small traffic signs. The detection speed of MSA_YOLOv3 is 23.81 FPS, and the mAP (mean Average Precision) reaches up to 86%.

18 June 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JLJun Li
Jun Li
YFYongqiang Feng
Yongqiang Feng
YSYanhua Shao
Yanhua Shao
Feng LiuFeng Liu
Feng Liu
Despite their proficiency with typical environmental datasets, deep learning-based object detection algorithms struggle when faced with diverse adverse weather conditions. Moreover, existing methods often address single adverse weather scenarios, neglecting situations involving multiple concurrent adverse conditions. To tackle these challenges, we propose an enhanced approach to object detection in power construction sites under various adverse weather conditions, dubbed IDP-YOLOV9. This model leverages a parallel architecture comprising the Image Dehazing and Enhancement Processing (IDP) module and an improved YOLOV9 object detection module. Specifically, for images captured in adverse weather, our approach employs a parallel architecture that includes the Three-Weather Removal Algorithm (TRA) module and the Deep Learning-based Image Enhancement (DLIE) module, which, together, filter multiple weather factors to enhance image quality. Subsequently, we introduce an improved YOLOV9 detection network module that incorporates a three-layer routing attention mechanism for object detection. Experiments demonstrate that the IDP module significantly improves image quality by mitigating the impact of various adverse weather conditions. Compared to traditional single-processing models, our method improves recognition accuracy on complex weather datasets by 6.8% in terms of mean average precision (mAP50).

20 June 2024 in Annals of Data Science
Verified
Journal Article
Closed access
PDF file
JLJun Li
Jun Li
CZChenyang Zhang
Chenyang Zhang
WZWei Zhu
Wei Zhu
YRYawei Ren
Yawei Ren

17 June 2024 in Sensors
Verified
Journal Article
Open access
PDF file
JLJun Li
Jun Li
JZJiajie Zhang
Jiajie Zhang
YSYanhua Shao
Yanhua Shao
Feng LiuFeng Liu
Feng Liu
To tackle the intricate challenges associated with the low detection accuracy of images taken by unmanned aerial vehicles (UAVs), arising from the diverse sizes and types of objects coupled with limited feature information, we present the SRE-YOLOv8 as an advanced method. Our method enhances the YOLOv8 object detection algorithm by leveraging the Swin Transformer and a lightweight residual feature pyramid network (RE-FPN) structure. Firstly, we introduce an optimized Swin Transformer module into the backbone network to preserve ample global contextual information during feature extraction and to extract a broader spectrum of features using self-attention mechanisms. Subsequently, we integrate a Residual Feature Augmentation (RFA) module and a lightweight attention mechanism named ECA, thereby transforming the original FPN structure to RE-FPN, intensifying the network’s emphasis on critical features. Additionally, an SOD (small object detection) layer is incorporated to enhance the network’s ability to recognize the spatial information of the model, thus augmenting accuracy in detecting small objects. Finally, we employ a Dynamic Head equipped with multiple attention mechanisms in the object detection head to enhance its performance in identifying low-resolution targets amidst complex backgrounds. Experimental evaluation conducted on the VisDrone2021 dataset reveals a significant advancement, showcasing an impressive 9.2% enhancement over the original YOLOv8 algorithm.

27 May 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JLJun Li
Jun Li
GYGengyu Yang
Gengyu Yang
YSYanhua Shao
Yanhua Shao
Ransomware is a type of malicious software that encrypts or locks user files and demands a high ransom. It has become a major threat to cyberspace security, especially as it continues to be developed and updated at exponential rates. Ransomware detection technology has become a focus of research on information security risk detection methods. However, current ransomware detection techniques have high false positive and false negative rates, and traditional methods ignore global word co-occurrence and correlation information between key node steps in the entire process. This poses a significant challenge for accurately identifying and detecting ransomware. We propose a ransomware detection model based on co-occurrence information adaptive diffusion learning using a Text Graph Convolutional Network (ADC-TextGCN). Specifically, ADC-TextGCN first assign self-weights to word nodes based on sensitive API call functions and preserve co-occurrence information using Point Mutual Information Theory (COIR-PMI); then our model automatically learn the optimal neighborhood through an Adaptive Diffusion Convolution (ADC) strategy, thereby improving the ability to aggregate long-distance node information across layers and enhancing the network’s ability to represent ransomware behavior. Experimental results show that our method achieves an accuracy of over 96.6% in ransomware detection, proving its effectiveness and superiority compared to traditional methods based on CNN and RNN in ransomware detection.

25 May 2024 in Annals of Data Science
Verified
Journal Article
Closed access
PDF file
JLJun Li
Jun Li
CXChong Xie
Chong Xie
SWSizheng Wu
Sizheng Wu
YRYawei Ren
Yawei Ren