Bingyu Sun

Dr. Bingyu Sun


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2013 in Remote Sensing
Verified
Journal Article
Open access
PDF file
WLWenbo Li
Wenbo Li
ZDZhiqiang Du
Zhiqiang Du
Feng LingFeng Ling
Feng Ling
DZDongbo Zhou
Dongbo Zhou
HWHailei Wang
Hailei Wang
XZXiaoming Zhang
Xiaoming Zhang
Remote sensing has more advantages than the traditional methods of land surface water (LSW) mapping because it is a low-cost, reliable information source that is capable of making high-frequency and repeatable observations. The normalized difference water indexes (NDWIs), calculated from various band combinations (green, near-infrared (NIR), or shortwave-infrared (SWIR)), have been successfully applied to LSW mapping. In fact, new NDWIs will become available when Advanced Land Imager (ALI) data are used as the ALI sensor provides one green band (Band 4), two NIR bands (Bands 6 and 7), and three SWIR bands (Bands 8, 9, and 10). Thus, selecting the optimal band or combination of bands is critical when ALI data are employed to map LSW using NDWI. The purpose of this paper is to find the best performing NDWI model of the ALI data in LSW map. In this study, eleven NDWI models based on ALI, Thematic Mapper (TM), and Enhanced Thematic Mapper Plus (ETM+) data were compared to assess the performance of ALI data in LSW mapping, at three different study sites in the Yangtze River Basin, China. The contrast method, Otsu method, and confusion matrix were calculated to evaluate the accuracies of the LSW maps. The accuracies of LSW maps derived from eleven NDWI models showed that five NDWI models of the ALI sensor have more than an overall accuracy of 91% with a Kappa coefficient of 0.78 of LSW maps at three test sites. In addition, the NDWI model, calculated from the green (Band 4: 0.525–0.605 μm) and SWIR (Band 9: 1.550–1.750 μm) bands of the ALI sensor, namely NDWIA4,9, was shown to have the highest LSW mapping accuracy, more than the other NDWI models. Therefore, the NDWIA4,9 is the best indicator for LSW mapping of the ALI sensor. It can be used for mapping LSW with high accuracy.

17 February 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JPJian Peng
Jian Peng
XMXiaoming Mei
Xiaoming Mei
WLWenbo Li
Wenbo Li
LHLiang Hong
Liang Hong
BSBingyu Sun
Bingyu Sun
Haifeng LiHaifeng Li
Haifeng Li
Scene understanding of remote sensing images is of great significance in various applications. Its fundamental problem is how to construct representative features. Various convolutional neural network architectures have been proposed for automatically learning features from images. However, is the current way of configuring the same architecture to learn all the data while ignoring the differences between images the right one? It seems to be contrary to our intuition: it is clear that some images are easier to recognize, and some are harder to recognize. This problem is the gap between the characteristics of the images and the learning features corresponding to specific network structures. Unfortunately, the literature so far lacks an analysis of the two. In this paper, we explore this problem from three aspects: we first build a visual-based evaluation pipeline of scene complexity to characterize the intrinsic differences between images; then, we analyze the relationship between semantic concepts and feature representations, i.e., the scalability and hierarchy of features which the essential elements in CNNs of different architectures, for remote sensing scenes of different complexity; thirdly, we introduce CAM, a visualization method that explains feature learning within neural networks, to analyze the relationship between scenes with different complexity and semantic feature representations. The experimental results show that a complex scene would need deeper and multi-scale features, whereas a simpler scene would need lower and single-scale features. Besides, the complex scene concept is more dependent on the joint semantic representation of multiple objects. Furthermore, we propose the framework of scene complexity prediction for an image and utilize it to design a depth and scale-adaptive model. It achieves higher performance but with fewer parameters than the original model, demonstrating the potential significance of scene complexity.

21 June 2024 in Measurement Science and Technology
Verified
Journal Article
Closed access
XMXinyu Meng
Xinyu Meng
XCXi Chen
Xi Chen
SCShaofeng Chen
Shaofeng Chen
YFYongfeng Fang
Yongfeng Fang
HFHao Fan
Hao Fan
BSBingyu Sun
Bingyu Sun
Simultaneous localization and mapping (SLAM) is the process of estimating the trajectory of a mobile sensor carrier and creating a representation of its surroundings. Traditional SLAM algorithms are based on ‘static world assumption’ and simplify the problem by filtering out moving objects or tracking them separately in complex dynamic environments. However, this strong assumption restricts the application of SLAM algorithms on highly dynamic and unstructured environments. In order to resolve above problem, this paper propose an improved object-aware dynamic SLAM system by integrating image information, i.e. semantic and velocity information. Firstly, we adopt deep learning method to detect both the 2D and 3D bounding boxes of objects in the environment. This information is then used to perform multi-view, multi-dimensional bundle optimization to jointly refine the poses of camera, object, and point. Secondly, 2D detection results from image and 3D detection results from lidar are integrated by the joint probabilistic data association data association algorithm to facilitate object-level data association. We also calculate 2D and 3D motion velocity and this information is used to constraint the motion of the object. Finally, we perform comprehensive experiments on different datasets, including NCLT, M2DGR, and KITTI to prove the performance of the proposed method.

9 March 2026 in Frontiers in Robotics and AI
Verified
Journal Article
Open access
PDF file
XCXi Chen
Xi Chen
BSBingyu Sun
Bingyu Sun
Introduction: LiDAR–camera fusion systems are widely used in robotic localization and perception, where accurate extrinsic calibration is crucial for multi-sensor fusion. During long-term operation, extrinsic parameters can drift due to vibration and other disturbances, while target-based recalibration is inconvenient in the field and targetless approaches often suffer from highly non-convex objectives and limited robustness in challenging outdoor scenes. Methods: We propose a targetless LiDAR–camera extrinsic calibration method by minimizing a semantic distribution consistency risk on SE(3). We align semantic probability distributions from the two sensing modalities in the image domain and freeze the pixel sampling measure at an anchor pose, so that pixel weighting no longer depends on the current extrinsic estimate and the objective landscape remains stable during optimization. On top of this anchor-fixed measure, we introduce a direction-aware weighting strategy that emphasizes pixels sensitive to yaw perturbations, improving the conditioning of rotation estimation. We further use a globally balanced Jensen–Shannon divergence to mitigate semantic class imbalance and enhance robustness. Results: Experiments on the KITTI Odometry dataset show that the proposed method reliably converges from substantial initial perturbations and yields stable extrinsic estimates. Discussion: The results indicate that the method is promising for maintaining long-term LiDAR–camera calibration in real-world robotic systems.

13 March 2026 in Sensors
Verified
Journal Article
Open access
PDF file
Ruyang ZhangRuyang Zhang
Ruyang Zhang
BSBingyu Sun
Bingyu Sun
Environments with sparse or repetitive geometric structures, such as long corridors and narrow stairwells, remain challenging for LiDAR–inertial simultaneous localization and mapping (LiDAR–IMU SLAM) due to insufficient geometric observability and unreliable data associations. To address these issues, we propose VINA-SLAM, a novel LiDAR–IMU SLAM framework that constructs a unified global voxel map to explicitly exploit structural consistency. VINA-SLAM continuously tracks surface normals stored in the global voxel map using a normal-guided correspondence strategy, enabling stable scan-to-map alignment in degenerate scenes. Furthermore, a tangent-space metric is introduced to supplement missing rotational constraints around planar regions, providing reliable initial pose estimates for local optimization. A tightly coupled sliding-window bundle adjustment is then formulated by jointly incorporating IMU factors, voxel normal consistency factors, and planar regularization terms. In particular, the minimum eigenvalue of each voxel’s covariance is used as a statistically principled planar constraint, improving the Hessian conditioning and cross-view geometric consistency. The proposed system directly aligns raw LiDAR scans to the voxelized map without explicit feature extraction or loop closure. Experiments on 25 sequences from the HILTI and MARS-LVIG datasets show that VINA-SLAM reduces ATE by 25–40% on average while maintaining real-time performance at 10 Hz in the evaluated geometrically degenerate environments.
1

22 June 2026 in Agriculture
Verified
Journal Article
Open access
PDF file
HFHao Fan
Hao Fan
JXJintao Xi
Jintao Xi
XCXi Chen
Xi Chen
BSBingyu Sun
Bingyu Sun
Object detection in unstructured agricultural environments remains challenging due to large scale variations, complex backgrounds, irregular obstacle shapes, and limited computational resources. To address these challenges, this paper proposes Agri-DETR, an efficient end-to-end detection framework based on the Real-Time Detection Transformer (RT-DETR), with coordinated improvements in feature perception, multi-scale representation, spatial reconstruction, and bounding box regression. Specifically, a lightweight backbone with a high-resolution feature branch is introduced to enhance the representation of small and fine-grained targets. A large selective feature fusion module is designed to strengthen multi-scale contextual modeling and improve feature discrimination under complex backgrounds. In addition, an attention-enhanced dynamic upsampling module refines high-resolution feature reconstruction, while a scale–shape–geometry-aware Intersection over Union (SSGIoU) loss improves localization stability for irregular and elongated objects. Experimental results show that Agri-DETR achieves 66.0% Average Precision (AP) on the self-constructed Agricultural Obstacle Dataset (AO-Dataset), outperforming representative detectors while reducing the parameter count by approximately 25% compared with RT-DETR-R18 baseline. In particular, small-object AP increases by 1.4%, demonstrating improved detection capability for small obstacles. Cross-dataset evaluation on COCO2017 further shows that Agri-DETR achieves 48.3% AP, demonstrating favorable generalization capability beyond the agricultural domain. These results indicate that Agri-DETR achieves an effective balance among detection accuracy, model complexity, and practical efficiency, making it a promising solution for real-world agricultural obstacle detection.