Yongbao Ai
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
Yongbao Ai has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Jianmeng Dong
National Innovation Institute of Defense Technology, Beijing 100071, China
2 shared publications - Qianchong Sun
National Innovation Institute of Defense Technology, Beijing 100071, China
2 shared publications - Xiang Wang
National Innovation Institute of Defense Technology, Beijing 100071, China
2 shared publications - Zhipeng Xi
National Institution of Defense Technology Innovation, Academy of Military Sciences of PLA China, Beijing, China
2 shared publications - Fanjie Meng
Department of Mechanical Engineering, College of Field Engineering, Army Engineering University of PLA, Nanjing 210007, China
1 shared publication - Lei Fu
College of Field Engineering, Army Engineering University of PLA, Nanjing 210000, China
1 shared publication
Latest Publications
- 3 September 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (11) , 509
MoR-ST: content-adaptive recursive computation for efficient vision transformers
- 3 September 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (11) , 509
MoR-ST: content-adaptive recursive computation for efficient vision transformers
- Open Access
- 12 August 2026
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (8) , 377
MoR–Swin: Efficient Vision Transformer Using Mixture of Recursions
Vision Transformers, especially Swin Transformer, have become default backbones for various vision tasks but suffer from high memory consumption and training costs. This letter proposes MoR–Swin, a novel architecture that integrates Mixture of Recursions (MoR) into Swin Transformer. An adaptive token-level recursion mechanism dynamically allocates computational depth based on semantic complexity. A recursive window attention module and a lightweight router with load balancing loss are introduced. Extensive experiments on ImageNet classification, COCO detection, and ADE20K segmentation show that MoR–Swin reduces parameters by about 50% and accelerates inference up to twofold at a modest accuracy cost (within about 0.5 points of Swin-B on ImageNet-1K). It provides a new technical pathway for optimizing Vision Transformer models, significantly enhancing their applicability in resource-constrained environments.
- 12 August 2026
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (8) , 377
Open AccessMoR–Swin: Efficient Vision Transformer Using Mixture of Recursions
Vision Transformers, especially Swin Transformer, have become default backbones for various vision tasks but suffer from high memory consumption and training costs. This letter proposes MoR–Swin, a novel architecture that integrates Mixture of Recursions (MoR) into Swin Transformer. An adaptive token-level recursion mechanism dynamically allocates computational depth based on semantic complexity. A recursive window attention module and a lightweight router with load balancing loss are introduced. Extensive experiments on ImageNet classification, COCO detection, and ADE20K segmentation show that MoR–Swin reduces parameters by about 50% and accelerates inference up to twofold at a modest accuracy cost (within about 0.5 points of Swin-B on ImageNet-1K). It provides a new technical pathway for optimizing Vision Transformer models, significantly enhancing their applicability in resource-constrained environments.
- Open Access
- 18 July 2023
- Published by MDPI AG in Electronics
- Vol. 12 (14) , 3112
Stereo SLAM in Dynamic Environments Using Semantic Segmentation
As we all know, many dynamic objects appear almost continuously in the real world that are immensely capable of impairing the performance of the majority of vision-based SLAM systems based on the static-world assumption. In order to improve the robustness and accuracy of visual SLAM in high-dynamic environments, a real-time and robust stereo SLAM system for dynamic scenes was proposed. To weaken the influence of dynamic content, the moving-object detection method was put forward in our visual odometry, and then the semantic segmentation network was combined in our stereo SLAM to extract pixel-level contours of dynamic objects. Then, the influences of dynamic objects were significantly weakened and the performance of our system increased markedly in dynamic, complex, and crowed city spaces. Following experiments with both the KITTI Odometry dataset and in a real-life scene, the results showed that our method could dramatically decrease the tracking error or drift, and improve the robustness and stability of our stereo SLAM in high dynamic outdoor scenarios.
- 18 July 2023
- Published by MDPI AG in Electronics
- Vol. 12 (14) , 3112
Open AccessStereo SLAM in Dynamic Environments Using Semantic Segmentation
As we all know, many dynamic objects appear almost continuously in the real world that are immensely capable of impairing the performance of the majority of vision-based SLAM systems based on the static-world assumption. In order to improve the robustness and accuracy of visual SLAM in high-dynamic environments, a real-time and robust stereo SLAM system for dynamic scenes was proposed. To weaken the influence of dynamic content, the moving-object detection method was put forward in our visual odometry, and then the semantic segmentation network was combined in our stereo SLAM to extract pixel-level contours of dynamic objects. Then, the influences of dynamic objects were significantly weakened and the performance of our system increased markedly in dynamic, complex, and crowed city spaces. Following experiments with both the KITTI Odometry dataset and in a real-life scene, the results showed that our method could dramatically decrease the tracking error or drift, and improve the robustness and stability of our stereo SLAM in high dynamic outdoor scenarios.
- Open Access
- 30 May 2023
- Published by MDPI AG in Preprints.org
Stereo SLAM in Dynamic Environments using Semantic Segmentation
As we all know, many more dynamic objects appear almost continuously in real world, which are immensely able to impair the performance of the majority of vision-based SLAM systems that are based on the static-world assumption. In order to improve the robustness and accuracy of visual SLAM in the high dynamic environment, a real-time and robust stereo SLAM system for dynamic scenes was proposed. To weaken influences of dynamic content, the moving object detection method was put forward in our visual odometry, then the semantic segmentation network was combined into our stereo SLAM to extract pixel-level contours of dynamic objects. Then influences of dynamic objects were extremely weaken and the performance of our system was increased markedly in dynamic, complex and crowed city spaces. Experiment with both on KITTI Odometry dataset and in a real-life scene, the results show that our method can dramatically decrease the tracking error or drift, improve the robustness and stability of our stereo SLAM in high dynamic outdoor scenarios.
- 30 May 2023
- Published by MDPI AG in Preprints.org
Open AccessStereo SLAM in Dynamic Environments using Semantic Segmentation
As we all know, many more dynamic objects appear almost continuously in real world, which are immensely able to impair the performance of the majority of vision-based SLAM systems that are based on the static-world assumption. In order to improve the robustness and accuracy of visual SLAM in the high dynamic environment, a real-time and robust stereo SLAM system for dynamic scenes was proposed. To weaken influences of dynamic content, the moving object detection method was put forward in our visual odometry, then the semantic segmentation network was combined into our stereo SLAM to extract pixel-level contours of dynamic objects. Then influences of dynamic objects were extremely weaken and the performance of our system was increased markedly in dynamic, complex and crowed city spaces. Experiment with both on KITTI Odometry dataset and in a real-life scene, the results show that our method can dramatically decrease the tracking error or drift, improve the robustness and stability of our stereo SLAM in high dynamic outdoor scenarios.
- Open Access
- 21 December 2019
- Published by MDPI AG in Electronics
- Vol. 9 (1) , 15
Parallel Multi-Branch Convolution Block Net for Fast and Accurate Object Detection
In order to maintain the high speed advantage of single-stage object detector and improve its detection accuracy, in this paper, we propose a parallel multi-branch convolution block, called PMCB, which can efficiently extract multi-scale object information at a specific layer to form a discriminative feature layer and boost the detection performance with little computational burden. Based on the PMCB module, we build PMCB Net on the basis of the single shot multibox detector (SSD) network by replacing the conventional convolution with PMCB at a specific layer. The performance of the proposed algorithm is compared with that of other state-of-the-art methods on PASCAL VOC2007, MS COCO test datasets. The experimental results show that the proposed algorithm greatly improved detection accuracy performance while only adding a negligible computational burden, which is very important for practical engineering applications.
- 21 December 2019
- Published by MDPI AG in Electronics
- Vol. 9 (1) , 15
Open AccessParallel Multi-Branch Convolution Block Net for Fast and Accurate Object Detection
In order to maintain the high speed advantage of single-stage object detector and improve its detection accuracy, in this paper, we propose a parallel multi-branch convolution block, called PMCB, which can efficiently extract multi-scale object information at a specific layer to form a discriminative feature layer and boost the detection performance with little computational burden. Based on the PMCB module, we build PMCB Net on the basis of the single shot multibox detector (SSD) network by replacing the conventional convolution with PMCB at a specific layer. The performance of the proposed algorithm is compared with that of other state-of-the-art methods on PASCAL VOC2007, MS COCO test datasets. The experimental results show that the proposed algorithm greatly improved detection accuracy performance while only adding a negligible computational burden, which is very important for practical engineering applications.
- Open Access
- 11 August 2016
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2016, 1-12
Optimization Design for Detonation Powerplant Based on LS-DYNA Simulation
To ensure the accuracy of the work capacity of the detonation powerplant, the explosive and shock process of detonation powerplants was simulated with LS-DYNA. Many maximum rising displacements of the cartridge indicating the work capacity of the device were obtained, under different fit clearances of the device. It was proved that fit clearances were the key factors affecting the work capacity of the device, and reasonable range for fit clearances was found. Besides, the objective function, constraint condition, and optimization design variables of the Genetic Algorithm were determined according to the design indicators of the detonation powerplant. The theoretical values of fit clearances of the optimization design of detonation powerplants were obtained. At last, the tests of the work capacity of the detonation powerplant and LS-DYNA simulation proved the rationality of the theoretical values from the Genetic Algorithm, providing an experimental proof for the accuracy design, which could control the service door movement accurately.
- 11 August 2016
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2016, 1-12
Open AccessOptimization Design for Detonation Powerplant Based on LS-DYNA Simulation
To ensure the accuracy of the work capacity of the detonation powerplant, the explosive and shock process of detonation powerplants was simulated with LS-DYNA. Many maximum rising displacements of the cartridge indicating the work capacity of the device were obtained, under different fit clearances of the device. It was proved that fit clearances were the key factors affecting the work capacity of the device, and reasonable range for fit clearances was found. Besides, the objective function, constraint condition, and optimization design variables of the Genetic Algorithm were determined according to the design indicators of the detonation powerplant. The theoretical values of fit clearances of the optimization design of detonation powerplants were obtained. At last, the tests of the work capacity of the detonation powerplant and LS-DYNA simulation proved the rationality of the theoretical values from the Genetic Algorithm, providing an experimental proof for the accuracy design, which could control the service door movement accurately.