Tianrui Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tianrui Shen has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
Lai Kang
3 shared publications- Haixuan Wang
National University of Defense Technology; College of Systems Engineering, National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China
2 shared publications - Shanshan Wan
National University of Defense Technology; College of Systems Engineering, National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China
2 shared publications - Yee-Hong Yang
University of Alberta
2 shared publications Yingmei Wei
2 shared publications- Jingqian Gong
Beijing University Of Technology; College of Economics and Management, Beijing University Of Technology,Department of Management Science and Engineering,Beijing,China
1 shared publication
Latest Publications
- Open Access
- 11 June 2025
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 227, 69-83
Aerial path planning for 3D urban scene reconstruction with dual-task reconstructability learning and adaptive viewpoints selection
- 11 June 2025
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 227, 69-83
Open AccessAerial path planning for 3D urban scene reconstruction with dual-task reconstructability learning and adaptive viewpoints selection
- 25 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 510-517
CAD4Real: Training Drone Object Detection Models without Manual Ingestion
The performance of current pre-trained models for unmanned aerial vehicle (UAV) detection is directly impacted by dataset quality, and the manual ingestion and labeling required for dataset updates are both time and labor consuming. We present an automated procedure to constructing UAV synthetic datasets utilizing 3D photorealistic graphics. By implementing a targeted training strategy, we significantly enhance the performance of object detection algorithms under similar conditions. Experimental results demonstrate that, compared to a baseline training model, our model, trained with only 100 data samples, achieves a 64.9% increase in the mAP@0.95 metric relative to the original model. Moreover, with 5,000 data samples, our model outperforms the performance achieved by the traditional model trained on 10,000 samples. This reduction in the requirement for real drone data samples streamlines the training process for UAV detection models.
- 25 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 510-517
CAD4Real: Training Drone Object Detection Models without Manual Ingestion
The performance of current pre-trained models for unmanned aerial vehicle (UAV) detection is directly impacted by dataset quality, and the manual ingestion and labeling required for dataset updates are both time and labor consuming. We present an automated procedure to constructing UAV synthetic datasets utilizing 3D photorealistic graphics. By implementing a targeted training strategy, we significantly enhance the performance of object detection algorithms under similar conditions. Experimental results demonstrate that, compared to a baseline training model, our model, trained with only 100 data samples, achieves a 64.9% increase in the mAP@0.95 metric relative to the original model. Moreover, with 5,000 data samples, our model outperforms the performance achieved by the traditional model trained on 10,000 samples. This reduction in the requirement for real drone data samples streamlines the training process for UAV detection models.
- Top Cited Papers
- 17 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (3) , 1456-1468
MCCG: A ConvNeXt-Based Multiple-Classifier Method for Cross-View Geo-Localization
The key to crossview geolocalization is to match images of the same target from different viewpoints, e.g., images from drones and satellites. It is a challenging problem due to the changing appearance of objects from variable viewpoints. Most existing methods focus mainly on extracting global features or on segmenting feature maps, causing the loss of information contained in the images. To address the above issues, we propose a new ConvNeXt-based method called MCCG, which stands for Multiple Classifier for Cross-view Geolocalization. The proposed method captures rich discriminative information by cross-dimension interaction and acquires multiple feature representations, realizing a comprehensive feature representation. Additionally, the robustness of the model is improved crediting the multiple feature representations exploiting more contextual information despite position shifting or scale variations. Extensive experiments on the widely used public benchmarks University-1652 and SUES-200 demonstrate that the proposed method achieves state-of-the-art performance in both drone-view target localization and drone navigation applications by over 3% compared to existing methods. Our code and model are available at https://github.com/mode-str/crossview.
- 17 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (3) , 1456-1468
Top Cited PapersMCCG: A ConvNeXt-Based Multiple-Classifier Method for Cross-View Geo-Localization
The key to crossview geolocalization is to match images of the same target from different viewpoints, e.g., images from drones and satellites. It is a challenging problem due to the changing appearance of objects from variable viewpoints. Most existing methods focus mainly on extracting global features or on segmenting feature maps, causing the loss of information contained in the images. To address the above issues, we propose a new ConvNeXt-based method called MCCG, which stands for Multiple Classifier for Cross-view Geolocalization. The proposed method captures rich discriminative information by cross-dimension interaction and acquires multiple feature representations, realizing a comprehensive feature representation. Additionally, the robustness of the model is improved crediting the multiple feature representations exploiting more contextual information despite position shifting or scale variations. Extensive experiments on the widely used public benchmarks University-1652 and SUES-200 demonstrate that the proposed method achieves state-of-the-art performance in both drone-view target localization and drone navigation applications by over 3% compared to existing methods. Our code and model are available at https://github.com/mode-str/crossview.