Ning Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ning Sun has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Guangbing Xiao
College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing 210037, China
2 shared publications - Fengzhou Ji
Faculty of Automotive and Traffic Engineering, Nanjing Forestry University, Nanjing, Jiangsu 210044, P. R. China
1 shared publication Guangbing Xiao
School of Automotive and Traffic Engineering, Nanjing Forestry University, Nanjing, China
1 shared publication- Guodong Yin
Southeast University
1 shared publication Haibo Zhang
Department of Computer Science
1 shared publicationJiamin Shi
Department of Automobile and Traffic Engineering
1 shared publication
Latest Publications
- 24 October 2025
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 35 (05)
Fast Redundant Feature Point Elimination for Enhanced Real-Time Panoramic Image Matching in Driver Assistance Systems
The vehicle-mounted panoramic imaging system has gradually been implemented in vehicles with driver assistance functions. Through panoramic images, drivers can obtain richer road scene information, significantly enhancing driving safety and comfort. The future realization of autonomous driving will also depend on the development of this technology. A key component of this technology is image feature matching. Classical image feature matching algorithms generate a large number of redundant feature points during the feature extraction phase, leading not only to increased matching times but also to reduced matching accuracy. To address this issue, this paper proposes a new method for fast redundant feature point elimination (FRFEM). This algorithm assesses the redundancy of feature points using defined distance and description redundancy metrics, subsequently eliminating redundant feature points based on this assessment. Additionally, a new filtering strategy tailored to the characteristics of vehicle-mounted panoramic imaging is designed, which avoids unnecessary computations by excluding nonredundant feature points rather than searching for potential redundant ones. This strategy is implemented using a subspace clustering filtering method, employing low-cost distance estimates instead of precise high-dimensional calculations, thereby significantly reducing computational costs and improving real-time performance. To validate the performance of the FRFEM algorithm, multiple comparative experiments were designed for evaluation. The results indicate that the FRFEM algorithm enhances the matching accuracy, repeatability, and root mean square error (RMSE) of scale-invariant feature transform (SIFT). When applied to the SURF algorithm, it achieves up to a 16% improvement in matching accuracy and reduces matching time by as much as 44% compared to the original SURF algorithm. In summary, the FRFEM algorithm can significantly enhance the generation speed and accuracy of vehicle-mounted panoramic imaging.
- 24 October 2025
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 35 (05)
Fast Redundant Feature Point Elimination for Enhanced Real-Time Panoramic Image Matching in Driver Assistance Systems
The vehicle-mounted panoramic imaging system has gradually been implemented in vehicles with driver assistance functions. Through panoramic images, drivers can obtain richer road scene information, significantly enhancing driving safety and comfort. The future realization of autonomous driving will also depend on the development of this technology. A key component of this technology is image feature matching. Classical image feature matching algorithms generate a large number of redundant feature points during the feature extraction phase, leading not only to increased matching times but also to reduced matching accuracy. To address this issue, this paper proposes a new method for fast redundant feature point elimination (FRFEM). This algorithm assesses the redundancy of feature points using defined distance and description redundancy metrics, subsequently eliminating redundant feature points based on this assessment. Additionally, a new filtering strategy tailored to the characteristics of vehicle-mounted panoramic imaging is designed, which avoids unnecessary computations by excluding nonredundant feature points rather than searching for potential redundant ones. This strategy is implemented using a subspace clustering filtering method, employing low-cost distance estimates instead of precise high-dimensional calculations, thereby significantly reducing computational costs and improving real-time performance. To validate the performance of the FRFEM algorithm, multiple comparative experiments were designed for evaluation. The results indicate that the FRFEM algorithm enhances the matching accuracy, repeatability, and root mean square error (RMSE) of scale-invariant feature transform (SIFT). When applied to the SURF algorithm, it achieves up to a 16% improvement in matching accuracy and reduces matching time by as much as 44% compared to the original SURF algorithm. In summary, the FRFEM algorithm can significantly enhance the generation speed and accuracy of vehicle-mounted panoramic imaging.
- Open Access
- 22 May 2025
- Published by Elsevier in Chinese Journal of Mechanical Engineering
- Vol. 38 (1) , 1-16
FS-DRL: Fine-Grained Scheduling of Autonomous Vehicles at Non-Signalized Intersections via Dual Reinforced Learning
- 22 May 2025
- Published by Elsevier in Chinese Journal of Mechanical Engineering
- Vol. 38 (1) , 1-16
Open AccessFS-DRL: Fine-Grained Scheduling of Autonomous Vehicles at Non-Signalized Intersections via Dual Reinforced Learning
- Open Access
- 1 January 2019
- Published by Wiley in Complexity
- Vol. 2019 (1)
Cooperative Bargain for the Autonomous Separation of Traffic Flows in Smart Reversible Lanes
Spacer bars in the smart reversible lanes make periodically broadcast of messages to share their local observed traffic information with each other. This aims to help other spacer bars acquire the global traffic information and make consistent movement when separating the flows. However, radio interference and vehicles in the traffic may degrade the qualities of wireless communication links and cause frequent message losses in the broadcast. Existing solutions tend to use data forwarding to enhance the message dissemination, which may cause imbalanced load in the spacer bars. For instance, the nodes close to the sink have to forward more messages, whereas the ones far away from the sink have fewer messages for forwarding. The unbalanced distribution of network load has a high risk of blocking the wireless communication links and yield inconsistent movement in the reversible lanes. In this paper, we propose a Cooperative Bargain (CoB) scheme where each spacer bar carries some received messages to help other spacer bars recover their lost messages. Since the spacer bars can only acquire the local information, we formulate a cooperative bargain game to negotiate how to allocate the task of message recovery with a balanced network load until a consensus is achieved. CoB is evaluated with the real‐world Wi‐Fi communication traces in Isti/rural. Simulation results show that CoB can recover an average of 98.6% messages within 100 milliseconds in a 50‐node network. CoB does not require the global network information but it can still achieve a comparable performance to other broadcast schemes.
- 1 January 2019
- Published by Wiley in Complexity
- Vol. 2019 (1)
Open AccessCooperative Bargain for the Autonomous Separation of Traffic Flows in Smart Reversible Lanes
Spacer bars in the smart reversible lanes make periodically broadcast of messages to share their local observed traffic information with each other. This aims to help other spacer bars acquire the global traffic information and make consistent movement when separating the flows. However, radio interference and vehicles in the traffic may degrade the qualities of wireless communication links and cause frequent message losses in the broadcast. Existing solutions tend to use data forwarding to enhance the message dissemination, which may cause imbalanced load in the spacer bars. For instance, the nodes close to the sink have to forward more messages, whereas the ones far away from the sink have fewer messages for forwarding. The unbalanced distribution of network load has a high risk of blocking the wireless communication links and yield inconsistent movement in the reversible lanes. In this paper, we propose a Cooperative Bargain (CoB) scheme where each spacer bar carries some received messages to help other spacer bars recover their lost messages. Since the spacer bars can only acquire the local information, we formulate a cooperative bargain game to negotiate how to allocate the task of message recovery with a balanced network load until a consensus is achieved. CoB is evaluated with the real‐world Wi‐Fi communication traces in Isti/rural. Simulation results show that CoB can recover an average of 98.6% messages within 100 milliseconds in a 50‐node network. CoB does not require the global network information but it can still achieve a comparable performance to other broadcast schemes.
- 1 January 2012
- Published by Springer Nature
- p. 1074-1081
Association of Attack Factors Based on Fuzzy Information Fusion
- 1 January 2012
- Published by Springer Nature
- p. 1074-1081
Association of Attack Factors Based on Fuzzy Information Fusion