Bo Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bo Yang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Yingdong Pi
State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, China
3 shared publications - Mi Wang
Wuhan University
2 shared publications - Zemin Geng
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China
2 shared publications Deren Li
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
1 shared publication- Kun Huang
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
1 shared publication Xin Li
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
1 shared publication
Latest Publications
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-17
Observation Anomaly Detection for Block Adjustment of Satellite Images Based on the Uncertainty Propagation
Due to the discrepancies of geometric and radiometric factors, automatic image matching often fails to generate tie points, leading to positioning inconsistences in satellite image blocks. To address this issue, we proposed a novel observation anomaly detection method based on uncertainty propagation and clustering analysis. The method propagates the geometric precision of a reference image throughout the image block under the intersection and elevation constraints. A feature space is then constructed based on the statistics of the geometric accuracies and the DBSCAN clustering algorithm is applied to distinguish anomalous images from normal ones. Experiments using 149 multispectral and 298 panchromatic GF-7 images demonstrated that the method achieved 100% detection accuracy under the optimal image-space compensation model and the optimal feature space. While some moderate observation anomalies were missed with a single reference image, incorporating multiple well-distributed reference images enabled accurate detection. Further analysis revealed significant discrepancies in positioning accuracies between anomalous and normal images after block adjustment, with mean differences up to 4.77 m and 5.40 m in line and sample directions, respectively. By adding approximately 1300 tie points to anomalous images, spatial connectivity was restored, reducing RMS errors by over 91% and aligning their precision with that of normal images.
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-17
Observation Anomaly Detection for Block Adjustment of Satellite Images Based on the Uncertainty Propagation
Due to the discrepancies of geometric and radiometric factors, automatic image matching often fails to generate tie points, leading to positioning inconsistences in satellite image blocks. To address this issue, we proposed a novel observation anomaly detection method based on uncertainty propagation and clustering analysis. The method propagates the geometric precision of a reference image throughout the image block under the intersection and elevation constraints. A feature space is then constructed based on the statistics of the geometric accuracies and the DBSCAN clustering algorithm is applied to distinguish anomalous images from normal ones. Experiments using 149 multispectral and 298 panchromatic GF-7 images demonstrated that the method achieved 100% detection accuracy under the optimal image-space compensation model and the optimal feature space. While some moderate observation anomalies were missed with a single reference image, incorporating multiple well-distributed reference images enabled accurate detection. Further analysis revealed significant discrepancies in positioning accuracies between anomalous and normal images after block adjustment, with mean differences up to 4.77 m and 5.40 m in line and sample directions, respectively. By adding approximately 1300 tie points to anomalous images, spatial connectivity was restored, reducing RMS errors by over 91% and aligning their precision with that of normal images.
- 15 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-18
FRIM: A Framework for Satellite-Borne Remote Sensing Image Matching
Satellite-borne remote sensing images cover extensive areas, and improvements in sensor resolution have dramatically increased the data volume of individual images. For example, a GF7 forward-looking image can span 31267×30996 pixels, with slight variations across datasets. To overcome the incompatibility of general-purpose image matching algorithms with large-scale satellite data, this study proposes a unified framework for adapting these algorithms to satellite-borne remote sensing images. The framework integrates two partitioning strategies—object-space-based and image-space-based—to balance computational efficiency and the uniform distribution of homologous points. Furthermore, an affine local aggregation strategy further enhances matching accuracy and spatial uniformity, achieving an 84.8% improvement in accuracy and a 97.2% enhancement in uniformity. Building on this, the dynamic recursive outlier elimination (DROE) method iteratively optimizes matching, increasing the precision of retained points by 14.5% and their uniformity by 89.5%, while effectively rejecting outliers. Experimental validation on multisource datasets confirms the framework’s ability to accurately match homologous points using general-purpose image matching algorithms, supporting both sparse and dense output requirements. The proposed framework will be publicly available at https://github.com/Geng-Zemin/RS-matching-framework
- 15 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-18
FRIM: A Framework for Satellite-Borne Remote Sensing Image Matching
Satellite-borne remote sensing images cover extensive areas, and improvements in sensor resolution have dramatically increased the data volume of individual images. For example, a GF7 forward-looking image can span 31267×30996 pixels, with slight variations across datasets. To overcome the incompatibility of general-purpose image matching algorithms with large-scale satellite data, this study proposes a unified framework for adapting these algorithms to satellite-borne remote sensing images. The framework integrates two partitioning strategies—object-space-based and image-space-based—to balance computational efficiency and the uniform distribution of homologous points. Furthermore, an affine local aggregation strategy further enhances matching accuracy and spatial uniformity, achieving an 84.8% improvement in accuracy and a 97.2% enhancement in uniformity. Building on this, the dynamic recursive outlier elimination (DROE) method iteratively optimizes matching, increasing the precision of retained points by 14.5% and their uniformity by 89.5%, while effectively rejecting outliers. Experimental validation on multisource datasets confirms the framework’s ability to accurately match homologous points using general-purpose image matching algorithms, supporting both sparse and dense output requirements. The proposed framework will be publicly available at https://github.com/Geng-Zemin/RS-matching-framework
- 25 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-16
MIRRIFT: Multimodal Image Rotation and Resolution Invariant Feature Transformation
Multimodal image matching success rates are often low due to non-linear radiation differences. Furthermore, when geometric transformations such as rotation and resolution exist between images, the matching success rate between multimodal images decreases even further. (It is worth noting that experiments have shown the impact of scale to be relatively small; therefore, this discussion focuses only on the influence of resolution differences on multimodal image matching.) To tackle these challenges, we’ve enhanced the feature point extraction, description, and association processes in image matching. This has resulted in a robust multimodal image matching framework that is invariant to rotation and resolution, with a high success rate. Specifically, inspired by the concept of image pyramids, we designed a strategy for extracting feature points in multiple resolution dimensions. This enables assigning resolution dimension information to feature points and expanding the set of points to be matched. Building upon feature point extraction, we enhanced the Log-Gabor filter and designed a novel feature descriptor. This descriptor can work robustly in scenarios with modal differences and rotational variances ranging from 0 °to 360 °. Applying this descriptor to the matching framework helps to eliminate the influence of angle differences on feature point associations between images. Furthermore, to further improve the matching success rate, we adopted a resolution dimension traversal retrieval strategy for the association of feature points. Based on this strategy, the number of correct matching points can be increased under the condition of the same feature points, thereby increasing the inlier rate of the matching results and enhancing the success rate of the matching results. To evaluate the performance of this matching framework, we created a test dataset containing 42, 496 pairs of images using publicly available datasets. These images cover six categories including optical, SAR, DEM, infrared, map, and nighttime light, with three types of transformations between images: translation, rotation, and scaling. We conducted comparative experiments using the MIRRIFT method against five advanced multimodal feature matching methods with publicly available source code, namely RIFT, LNIFT, HAPCG, HOWP, and LGHD. The results demonstrate that the MIRRIFT method proposed in this paper exhibits robustness to rotational, resolution, and modal differences in images. Specifically, it achieved an average success rate improvement of 59%, an increase in average correct matching points by 12%, and an average matching accuracy of 1.97. The executable program and sample data will be made available at https://github.com/Geng-Zemin/MIRRIFT.
- 25 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-16
MIRRIFT: Multimodal Image Rotation and Resolution Invariant Feature Transformation
Multimodal image matching success rates are often low due to non-linear radiation differences. Furthermore, when geometric transformations such as rotation and resolution exist between images, the matching success rate between multimodal images decreases even further. (It is worth noting that experiments have shown the impact of scale to be relatively small; therefore, this discussion focuses only on the influence of resolution differences on multimodal image matching.) To tackle these challenges, we’ve enhanced the feature point extraction, description, and association processes in image matching. This has resulted in a robust multimodal image matching framework that is invariant to rotation and resolution, with a high success rate. Specifically, inspired by the concept of image pyramids, we designed a strategy for extracting feature points in multiple resolution dimensions. This enables assigning resolution dimension information to feature points and expanding the set of points to be matched. Building upon feature point extraction, we enhanced the Log-Gabor filter and designed a novel feature descriptor. This descriptor can work robustly in scenarios with modal differences and rotational variances ranging from 0 °to 360 °. Applying this descriptor to the matching framework helps to eliminate the influence of angle differences on feature point associations between images. Furthermore, to further improve the matching success rate, we adopted a resolution dimension traversal retrieval strategy for the association of feature points. Based on this strategy, the number of correct matching points can be increased under the condition of the same feature points, thereby increasing the inlier rate of the matching results and enhancing the success rate of the matching results. To evaluate the performance of this matching framework, we created a test dataset containing 42, 496 pairs of images using publicly available datasets. These images cover six categories including optical, SAR, DEM, infrared, map, and nighttime light, with three types of transformations between images: translation, rotation, and scaling. We conducted comparative experiments using the MIRRIFT method against five advanced multimodal feature matching methods with publicly available source code, namely RIFT, LNIFT, HAPCG, HOWP, and LGHD. The results demonstrate that the MIRRIFT method proposed in this paper exhibits robustness to rotational, resolution, and modal differences in images. Specifically, it achieved an average success rate improvement of 59%, an increase in average correct matching points by 12%, and an average matching accuracy of 1.97. The executable program and sample data will be made available at https://github.com/Geng-Zemin/MIRRIFT.