Junhua Kang

Accurate detection of soybean seedlings using unmanned aerial vehicles (UAVs) in complex field environments is crucial for yield estimation and agricultura

As the primary contributor to the error budget in microwave-dependent geodetic techniques, tropospheric delay has emerged as a bottleneck in achieving precise positioning of global navigation satellite systems (GNSSs). Due to the dynamic nature of water vapor, effective global zenith total delay (ZTD) modeling is essential yet challenging, underscoring the need for robust solutions. Artificial intelligence methods provide an effective approach for capturing the spatiotemporal characteristics of ZTD for modeling. In this contribution, we employ stacking ensemble learning to develop a machine-learning-based global ZTD (MGZTD) model, which integrates four decision tree models and artificial neural networks, leveraging the global forecast system to implement real-time nonlinear compensation for the empirical ZTD model. Validation against ERA5-derived ZTD shows that the model’s optimization achieves a 73.2% accuracy improvement over the baseline without correction. When benchmarked against GNSS post-processed ZTD, the stacking algorithm outperforms base learner schemes, particularly in tropical coastal environments. Furthermore, the MGZTD model achieves a global mean root mean square (RMS) error of 18.9 mm, yielding improvements of 52.5%, 51.3%, and 51.6% over the state-of-the-art GPT3, PVoxel, and IGPZWD models, respectively. The proposed model can effectively simulate the subtle random time-varying and spatially complex distribution of ZTD, delivering accurate and stable prediction information for users. These indicate the promising potential of the MGZTD model in enhancing real-time GNSS wide-area positioning services and water vapor remote sensing.

Modeling real-time zenith total delay (ZTD) remains a challenge owing to the rapidly changing water vapor conditions influenced by geography and climate. In this contribution, we propose Trop_XS, an innovative architecture that integrates the extreme gradient boosting (XGBoost) and spherical cap harmonic analysis (SCHA) algorithms with multi-source heterogeneous data, to support real-time wide-area tropospheric augmentation services. XGBoost enables rapid fusion of epoch-wise features, generating ZTD corrections at predefined grid points with a mean RMS below 11 mm. Building on the empirical ZTD model, the enhanced SCHA-E solution is employed to model the ZTD corrections from reference sites and regular grids, achieving a favorable trade-off between accuracy and communication burden. Validated against 6-month post-processing ZTD from 31 external test stations, Trop_XS-derived ZTD achieves a mean RMS of 13.4 mm, outperforming MOFC, VMF3_SCHA, and GNSS_interp solutions by 25.3%, 10.5%, and 11.4%, respectively. Furthermore, the proposed model demonstrates superior spatiotemporal applicability in areas characterized by complex terrain and limited station density, as well as during periods with active water vapor. Statistical results of the real-time precise point positioning (PPP) demonstrate that incorporating Trop_XS ZTD constraints effectively weakens the vertical error and accelerates initialization, shortening vertical convergence times by 36.4% in winter and 32.3% in summer, respectively. Given its scalability, the Trop_XS solution holds potential in other challenging regions, enhancing GNSS satellite-based PPP services and numerical weather forecasting capabilities.

Monocular depth estimation (MDE) is a critical computer vision task that enhances environmental perception in fields such as autonomous driving and robot navigation. In recent years, deep learning-based MDE methods have achieved notable progress in these fields. However, achieving robust monocular depth estimation in low-altitude forest environments remains challenging, particularly in scenes with dense and cluttered foliage, which complicates applications in environmental monitoring, agriculture, and search and rescue operations. This paper presents a comprehensive evaluation of state-of-the-art deep learning-based MDE methods on low-altitude forest datasets. The evaluated models include both self-supervised and supervised approaches, employing different network structures such as convolutional neural networks (CNNs) and Vision Transformers (ViTs). We assessed the generalization of these approaches across diverse low-altitude scenarios, specifically focusing on forested environments. A systematic set of evaluation criteria is employed, comprising traditional image-based global statistical metrics as well as geometry-aware metrics, to provide a more comprehensive evaluation of depth estimation performance. The results indicate that most Transformer-based models, such as DepthAnything and Metric3D, outperform traditional CNN-based models in complex forest environments by capturing detailed tree structures and depth discontinuities. Conversely, CNN-based models like MiDas and Adabins struggle with handling depth discontinuities and complex occlusions, yielding less detailed predictions. On the Mid-Air dataset, the Transformer-based DepthAnything demonstrates a 54.2% improvement in RMSE for the global error metric compared to the CNN-based Adabins. On the LOBDM dataset, the CNN-based MiDas has the depth edge completeness error of 93.361, while the Transformer-based Metric3D demonstrates the significantly lower error of only 5.494. These findings highlight the potential of Transformer-based approaches for monocular depth estimation in low-altitude forest environments, with implications for high-throughput plant phenotyping, environmental monitoring, and other forest-specific applications.

Recent developments in deep learning technology have boosted the performance of dense stereo reconstruction. However, the state-of-the-art deep learning-based stereo matching methods are mainly trained using close-range synthetic images. Consequently, the application of these methods in aerial photogrammetry and remote sensing is currently far from straightforward. In this paper, we propose a new disparity estimation network for stereo matching and investigate its generalization abilities in regard to aerial images. First, we propose an end-to-end deep learning network for stereo matching, regularized by disparity gradients, which includes a residual cost volume and a reconstruction error volume in a refinement module, and multiple losses. In order to investigate the influence of the multiple losses, a comprehensive analysis is presented. Second, based on this network trained with synthetic close-range data, we propose a new pipeline for matching high-resolution aerial imagery. The experimental results show that the proposed network improves the disparity accuracy by up to 40% in terms of errors larger than 1 px compared to results when not including the refinement network, especially in areas containing detailed small objects. In addition, in qualitative and quantitative experiments, we are able to show that our model, pre-trained on a synthetic stereo dataset, achieves very competitive sub-pixel geometric accuracy on aerial images. These results confirm that the domain gap between synthetic close-range and real aerial images can be satisfactorily bridged using the proposed new deep learning method for dense image matching.

The utilization of unmanned aerial vehicle (UAV) for soybean seedling detection is an effective way to estimate soybean yield, which plays a crucial role in agricultural planning and decision-making. However, the soybean seedlings objects in the UAV image are small, in clusters, and occluded each other, which makes it very challenging to achieve accurate object detection and counting. To address these issues, we optimize the YOLOv8 model and propose a GAS-YOLOv8 network, aiming to enhance the detection accuracy for the task of soybean seedling detection based on UAV images. Firstly, a global attention mechanism (GAM) is incorporated into the neck module of YOLOv8, which reallocates weights and prioritizes global information to more effectively extract soybean seedling features. Secondly, the CIOU loss function is replaced with the SIOU loss, which includes an angle loss term to guide the regression of bounding boxes. Experimental results show that, on the soybean seedling dataset, the proposed GAS-YOLOv8 model achieves a 1.3% improvement in mAP@0.5 and a 6% enhancement in detection performance in dense seedling areas, when compared to the baseline model YOLOv8s.When compared to other object detection models (YOLOv5, Faster R-CNN, etc.), the GAS-YOLOv8 model similarly achieved the best detection performance. These results demonstrate the effectiveness of the GAS-YOLOv8 in detecting dense soybean seedlings, providing more accurate theoretical support for subsequent yield estimation.