Xiaochun Lei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaochun Lei has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Zetao Jiang
School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China
3 shared publications Chen Junyan
School of Computer and Information Security, Guilin University of Electronic Technology, Guilin 541004, China
2 shared publicationsChuyu Bai
Guilin University of Electronic Technology
1 shared publicationFeng Yizhou
School of Computer and Information Security, Guilin University of Electronic Technology, Guilin 541004, China
1 shared publication- Gang Yao
State Key Laboratory of Petroleum Resources and Prospecting and the Unconventional Petroleum Research Institute, China University of Petroleum (Beijing), Beijing, China
1 shared publication Huang Rongcun
School of Computer and Information Security, Guilin University of Electronic Technology, Guilin 541004, China
1 shared publication
Latest Publications
- 1 November 2025
- Published by Springer Nature
- p. 15-26
EAANet: Edge-Aware Attention Network for Real-Time Road Scene Understanding
- 1 November 2025
- Published by Springer Nature
- p. 15-26
EAANet: Edge-Aware Attention Network for Real-Time Road Scene Understanding
- 24 June 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (9) , 1-10
DSARFormer: A dynamic sparse axial rectangular transformer for real-time semantic segmentation
- 24 June 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (9) , 1-10
DSARFormer: A dynamic sparse axial rectangular transformer for real-time semantic segmentation
- 27 March 2024
- Published by Springer Nature in The Visual Computer
- Vol. 41 (1) , 229-241
BENet: boundary-enhanced network for real-time semantic segmentation
- 27 March 2024
- Published by Springer Nature in The Visual Computer
- Vol. 41 (1) , 229-241
BENet: boundary-enhanced network for real-time semantic segmentation
- Open Access
- 12 July 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (14) , 8130
LightSeg: Local Spatial Perception Convolution for Real-Time Semantic Segmentation
Semantic segmentation is increasingly being applied on mobile devices due to advancements in mobile chipsets, particularly in low-power consumption scenarios. However, the lightweight design of mobile devices poses limitations on the receptive field, which is crucial for dense prediction problems. Existing approaches have attempted to balance lightweight designs and high accuracy by downsampling features in the backbone. However, this downsampling may result in the loss of local details at each network stage. To address this challenge, this paper presents a novel solution in the form of a compact and efficient convolutional neural network (CNN) for real-time applications: our proposed model, local spatial perception convolution (LSPConv). Furthermore, the effectiveness of our architecture is demonstrated on the Cityscapes dataset. The results show that our model achieves an impressive balance between accuracy and inference speed. Specifically, our LightSeg, which does not rely on ImageNet pretraining, achieves an mIoU of 76.1 at a speed of 61 FPS on the Cityscapes validation set, utilizing an RTX 2080Ti GPU with mixed precision. Additionally, it achieves a speed of 115.7 FPS on the Jetson NX with int8 precision.
- 12 July 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (14) , 8130
Open AccessLightSeg: Local Spatial Perception Convolution for Real-Time Semantic Segmentation
Semantic segmentation is increasingly being applied on mobile devices due to advancements in mobile chipsets, particularly in low-power consumption scenarios. However, the lightweight design of mobile devices poses limitations on the receptive field, which is crucial for dense prediction problems. Existing approaches have attempted to balance lightweight designs and high accuracy by downsampling features in the backbone. However, this downsampling may result in the loss of local details at each network stage. To address this challenge, this paper presents a novel solution in the form of a compact and efficient convolutional neural network (CNN) for real-time applications: our proposed model, local spatial perception convolution (LSPConv). Furthermore, the effectiveness of our architecture is demonstrated on the Cityscapes dataset. The results show that our model achieves an impressive balance between accuracy and inference speed. Specifically, our LightSeg, which does not rely on ImageNet pretraining, achieves an mIoU of 76.1 at a speed of 61 FPS on the Cityscapes validation set, utilizing an RTX 2080Ti GPU with mixed precision. Additionally, it achieves a speed of 115.7 FPS on the Jetson NX with int8 precision.
- Open Access
- 1 August 2020
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1606 (1) , 012017
Design of Intelligent Robot Platform based on Multi-sensor Fusion
The mobile robot adapts to the more complicated indoor and outdoor environments, and can expand its scope of application. In order to reduce the influence of the cumulative error caused by navigation in complex environments, the indoor mobile robot that combines Inertial Measurement Unit (IMU) and encoder fusion is designed and implemented. In view of the limitations of the traditional single lidar scheme, a Multi-sensor Fusion scheme is proposed to achieve indoor map construction, path planning, multi-point navigation and other functions, and a MSIF KartoSLAM (Multi-sensor Information Fusion) algorithm is proposed, which combines the KartoSLAM algorithm and Multi-sensor information to achieve map construction in complex environments. Through comprehensive testing in the indoor environment, the results show that the Multi-sensor Fusion scheme is superior to the traditional single lidar scheme, and can achieve higher accuracy in mapping and navigation. At the same time, the robot platform can also be combined with the Internet of Things technology and integrated into intelligent housing system.
- 1 August 2020
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1606 (1) , 012017
Open AccessDesign of Intelligent Robot Platform based on Multi-sensor Fusion
The mobile robot adapts to the more complicated indoor and outdoor environments, and can expand its scope of application. In order to reduce the influence of the cumulative error caused by navigation in complex environments, the indoor mobile robot that combines Inertial Measurement Unit (IMU) and encoder fusion is designed and implemented. In view of the limitations of the traditional single lidar scheme, a Multi-sensor Fusion scheme is proposed to achieve indoor map construction, path planning, multi-point navigation and other functions, and a MSIF KartoSLAM (Multi-sensor Information Fusion) algorithm is proposed, which combines the KartoSLAM algorithm and Multi-sensor information to achieve map construction in complex environments. Through comprehensive testing in the indoor environment, the results show that the Multi-sensor Fusion scheme is superior to the traditional single lidar scheme, and can achieve higher accuracy in mapping and navigation. At the same time, the robot platform can also be combined with the Internet of Things technology and integrated into intelligent housing system.
- Open Access
- 1 August 2020
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1606 (1) , 012012
Design of People Flow Monitoring System in Public Place based on MD-MCNN
Due to the limitation of hardware resources, the traditional people flow monitoring system based on computer vision in public places can’t meet different crowd-scale scenarios. Therefore, a people flow monitoring system based on MD-MCNN algorithm is designed, which is an application system combining the improved SSD object detection algorithm MNSSD and MCNN density map regression algorithm. In the initial stage, the system uses MNSSD for accurate detection and counting. If the people flow gradually reaches a certain threshold, the system automatically uses MCNN to estimate people flow until the people flow falls below the threshold. Through the experimental verification, the system can realize the people flow statistics of low-density and high-density people in different scenarios, and can be applied on the existing embedded platform. This scheme can be extended to smart cities, smart scenic spots, smart transportation and other fields.
- 1 August 2020
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1606 (1) , 012012
Open AccessDesign of People Flow Monitoring System in Public Place based on MD-MCNN
Due to the limitation of hardware resources, the traditional people flow monitoring system based on computer vision in public places can’t meet different crowd-scale scenarios. Therefore, a people flow monitoring system based on MD-MCNN algorithm is designed, which is an application system combining the improved SSD object detection algorithm MNSSD and MCNN density map regression algorithm. In the initial stage, the system uses MNSSD for accurate detection and counting. If the people flow gradually reaches a certain threshold, the system automatically uses MCNN to estimate people flow until the people flow falls below the threshold. Through the experimental verification, the system can realize the people flow statistics of low-density and high-density people in different scenarios, and can be applied on the existing embedded platform. This scheme can be extended to smart cities, smart scenic spots, smart transportation and other fields.
- 17 April 2019
- Published by Springer Nature
- p. 481-488
Design and Implementation of an Automatic Scanning Tool of SQL Injection Vulnerability Based on Web Crawler
- 17 April 2019
- Published by Springer Nature
- p. 481-488
Design and Implementation of an Automatic Scanning Tool of SQL Injection Vulnerability Based on Web Crawler