Xiaojie Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaojie Li has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Qian Shen
Faculty of Automation, Huai’an University, Huai’an, China
2 shared publications - Rong Xue
Faculty of Automation, Huaiyin Institute of Technology, Huaian 223003, People’s Republic of China
2 shared publications - Yan Zhang
Faculty of Automation, Huaiyin Institute of Technology, Huaian 223003, People’s Republic of China
2 shared publications - Yuxiang Zhang
Faculty of Automation, Huai’an University, Huai’an, China
2 shared publications - Yin Wu
College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, China
1 shared publication
Latest Publications
- 10 August 2026
- Published by Elsevier in Physica A: Statistical Mechanics and its Applications
- Vol. 700
Magnitude-driven dynamic complex chaotic networks for lightweight encryption
- 10 August 2026
- Published by Elsevier in Physica A: Statistical Mechanics and its Applications
- Vol. 700
Magnitude-driven dynamic complex chaotic networks for lightweight encryption
- 8 April 2026
- Published by IOP Publishing in Physica Scripta
- Vol. 101 (17)
An integrated strategy of compressive sensing and chaotic encryption for traffic surveillance images: dynamical analysis and application
As high-definition surveillance proliferates in intelligent transportation systems (ITS), edge nodes face mounting pressure to efficiently compress and securely transmit massive image data. However, existing schemes lack scene adaptability or sacrifice security, limiting edge deployment. To address this, we propose a strategy that combines compressive sensing with encryption. Firstly, a traffic-adaptive measurement matrix generation method is designed. By constructing direction-adaptive fractal bases through gradient analysis and lane priors, it captures key road structures more effectively. Secondly, a hypergeometric spiral sampling strategy is devised. Leveraging fractal features to dynamically modulate the sampling trajectory, it directs resources to information-dense regions, preserving image structure even at low rates. Finally, 2D memory neural network map is constructed. Through dynamic memory variables, its sensitivity to initial conditions and orbital complexity are significantly enhanced, strengthening encryption security. Experiments show the proposed strategy improves the structural similarity index measure (SSIM) by at least 0.01 and the peak signal-to-noise ratio (PSNR) by at least 0.8 dB over existing approaches. It maintains robust reconstruction under noise and various algorithms while resisting statistical, differential, and noise attacks. This work presents a practical solution for image processing at ITS edge nodes.
- 8 April 2026
- Published by IOP Publishing in Physica Scripta
- Vol. 101 (17)
An integrated strategy of compressive sensing and chaotic encryption for traffic surveillance images: dynamical analysis and application
As high-definition surveillance proliferates in intelligent transportation systems (ITS), edge nodes face mounting pressure to efficiently compress and securely transmit massive image data. However, existing schemes lack scene adaptability or sacrifice security, limiting edge deployment. To address this, we propose a strategy that combines compressive sensing with encryption. Firstly, a traffic-adaptive measurement matrix generation method is designed. By constructing direction-adaptive fractal bases through gradient analysis and lane priors, it captures key road structures more effectively. Secondly, a hypergeometric spiral sampling strategy is devised. Leveraging fractal features to dynamically modulate the sampling trajectory, it directs resources to information-dense regions, preserving image structure even at low rates. Finally, 2D memory neural network map is constructed. Through dynamic memory variables, its sensitivity to initial conditions and orbital complexity are significantly enhanced, strengthening encryption security. Experiments show the proposed strategy improves the structural similarity index measure (SSIM) by at least 0.01 and the peak signal-to-noise ratio (PSNR) by at least 0.8 dB over existing approaches. It maintains robust reconstruction under noise and various algorithms while resisting statistical, differential, and noise attacks. This work presents a practical solution for image processing at ITS edge nodes.