Jianjie Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jianjie Li has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Zhiqiang Cao
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
4 shared publications - Chengpeng Wang
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2 shared publications - Junzhi Yu
Peking University
2 shared publications - Peiyu Guan
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2 shared publications - Shuo Wang
Chinese Academy of Sciences
2 shared publications - Jing Yang
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (15) , 1
A Novel LiDAR-Inertial Sensor-Fused Localization System with Directed Geometric Gaussian Feature
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (15) , 1
A Novel LiDAR-Inertial Sensor-Fused Localization System with Directed Geometric Gaussian Feature
- 23 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 17 (4) , 1035-1045
DG-NBV: A Cognitive Framework for Direct Generation of Next Best View in Continuous View Space
The next best view (NBV) plays an important role in the three-dimensional object reconstruction. Existing NBV methods mainly adopt the generate-and-test strategy to select the best view in the discrete view space. This affects the adaptation to diverse objects. To solve this problem, a new NBV paradigm to directly generate the next best view in the continuous view space according to the input point cloud is proposed. Specifically, a point cloud feature extraction module with learnable view and position tokens is presented. These tokens are added upon the neighborhood and the position features of the point cloud to fully mine global contextual information, enhancing the feature representation. The predicted view from the proposed network is linked to a pre-trained view evaluation network. By duplicating this prediction view and then concatenating the duplication result with the extracted point cloud feature, the evaluation network is endowed with the ability to evaluate arbitrary views. Take the evaluation score of the evaluation network corresponding to the predicted view as the supervision signal, the network is trained. In this way, an effective solution of the next best view selection in the continuous view space is obtained. Accordingly, the adaptability to different objects is reinforced. Experimental results on the ShapeNet and MIT CSAIL datasets demonstrate the effectiveness of the proposed method.
- 23 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 17 (4) , 1035-1045
DG-NBV: A Cognitive Framework for Direct Generation of Next Best View in Continuous View Space
The next best view (NBV) plays an important role in the three-dimensional object reconstruction. Existing NBV methods mainly adopt the generate-and-test strategy to select the best view in the discrete view space. This affects the adaptation to diverse objects. To solve this problem, a new NBV paradigm to directly generate the next best view in the continuous view space according to the input point cloud is proposed. Specifically, a point cloud feature extraction module with learnable view and position tokens is presented. These tokens are added upon the neighborhood and the position features of the point cloud to fully mine global contextual information, enhancing the feature representation. The predicted view from the proposed network is linked to a pre-trained view evaluation network. By duplicating this prediction view and then concatenating the duplication result with the extracted point cloud feature, the evaluation network is endowed with the ability to evaluate arbitrary views. Take the evaluation score of the evaluation network corresponding to the predicted view as the supervision signal, the network is trained. In this way, an effective solution of the next best view selection in the continuous view space is obtained. Accordingly, the adaptability to different objects is reinforced. Experimental results on the ShapeNet and MIT CSAIL datasets demonstrate the effectiveness of the proposed method.
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 11 (7) , 783-792
LiDAR Place Recognition Based on Range Image and Column-Shift-Invariant Attention
LiDAR place recognition is a crucial component for the robust localization of intelligent vehicles with LiDAR sensors. The existing methods based on range image often resort to the permutation invariance of NetVLAD for rotation robustness, which restricts the change of feature scales and affects the recognition performance. In this paper, a LiDAR place recognition method based on range image and column-shift-invariant attention is proposed. Instead of relying on the invariance of NetVLAD, we design an attention mechanism whose attention map shifts synchronously with the input features. Under the weighted form of matrix multiplication, the attention module achieves the invariance to the cyclic column shift of range image while capturing the global contextual information. This enables the variation of feature scales. On this basis, a multi-scale module with feature downsampling and mixing is presented to mine multi-scale information after the attention. It enhances the discriminability of the global descriptor and further facilitates place recognition performance. The effectiveness of proposed method is evaluated on the KITTI, Ford Campus, and NCLT datasets.
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 11 (7) , 783-792
LiDAR Place Recognition Based on Range Image and Column-Shift-Invariant Attention
LiDAR place recognition is a crucial component for the robust localization of intelligent vehicles with LiDAR sensors. The existing methods based on range image often resort to the permutation invariance of NetVLAD for rotation robustness, which restricts the change of feature scales and affects the recognition performance. In this paper, a LiDAR place recognition method based on range image and column-shift-invariant attention is proposed. Instead of relying on the invariance of NetVLAD, we design an attention mechanism whose attention map shifts synchronously with the input features. Under the weighted form of matrix multiplication, the attention module achieves the invariance to the cyclic column shift of range image while capturing the global contextual information. This enables the variation of feature scales. On this basis, a multi-scale module with feature downsampling and mixing is presented to mine multi-scale information after the attention. It enhances the discriminability of the global descriptor and further facilitates place recognition performance. The effectiveness of proposed method is evaluated on the KITTI, Ford Campus, and NCLT datasets.
- 5 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (1) , 1423-1435
Hierarchical Distribution-Based Tightly-Coupled LiDAR Inertial Odometry
LiDAR inertial odometry (LIO) has attracted much attention due to the complementarity of LiDAR and IMU measurements. In the distribution-based LIO, the components related to distribution covariance in the residual and residual uncertainty from the LiDAR measurement noise is neutralized. And the resultant point cloud constraint degeneration problem severely affects the accuracy of pose estimation. In this paper, a hierarchical tightly-coupled LIO based on distribution is proposed. By excluding the eigenvalue elements in the distribution covariance component with the designed loss function, the uncertainty of corresponding residual is rectified. As a result, the degeneration problem is solved. With anti-degeneration point-to-distribution constraints, a LiDAR inertial odometry based on iterated extended Kalman filter and a factor graph optimization are designed and organized in a hierarchical way to achieve coarse-to-fine pose estimation, where LiDAR and IMU measurements are tightly coupled in both layers. In this way, the respective advantages of high efficiency and high accuracy from filtering and optimization are combined, which offers high-fidelity estimation results in real time. The effectiveness of the proposed method is verified through experiments on the public NC and ENC datasets.
- 5 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (1) , 1423-1435
Hierarchical Distribution-Based Tightly-Coupled LiDAR Inertial Odometry
LiDAR inertial odometry (LIO) has attracted much attention due to the complementarity of LiDAR and IMU measurements. In the distribution-based LIO, the components related to distribution covariance in the residual and residual uncertainty from the LiDAR measurement noise is neutralized. And the resultant point cloud constraint degeneration problem severely affects the accuracy of pose estimation. In this paper, a hierarchical tightly-coupled LIO based on distribution is proposed. By excluding the eigenvalue elements in the distribution covariance component with the designed loss function, the uncertainty of corresponding residual is rectified. As a result, the degeneration problem is solved. With anti-degeneration point-to-distribution constraints, a LiDAR inertial odometry based on iterated extended Kalman filter and a factor graph optimization are designed and organized in a hierarchical way to achieve coarse-to-fine pose estimation, where LiDAR and IMU measurements are tightly coupled in both layers. In this way, the respective advantages of high efficiency and high accuracy from filtering and optimization are combined, which offers high-fidelity estimation results in real time. The effectiveness of the proposed method is verified through experiments on the public NC and ENC datasets.