Pham Trung Dung

Dr. Pham Trung Dung


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
1 January 2020 in Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu
Verified
Journal Article
Closed access
CCCao Xuan Cuong
Cao Xuan Cuong
LCLe Van Canh
Le Van Canh
PCPham Van Chung
Pham Van Chung
LTLe Duc Tinh
Le Duc Tinh
PDPham Trung Dung
Pham Trung Dung
NCNgo Sy Cuong
Ngo Sy Cuong
Purpose. The main objective of this paper is to assess the quality of the 3D model of industrial buildings generated from Unmanned Aerial Vehicle (UAV) imagery datasets, including nadir (N), oblique (O), and Nadir and Oblique (N+O) UAV datasets. Methodology. The quality of a 3D model is defined by the accuracy and density of point clouds created from UAV images. For this purpose, the UAV was deployed to acquire images with both O and N flight modes over an industrial mining area containing a mine shaft tower, factory housing and office buildings. The quality assessment was conducted for the 3D point cloud model of three main objects such as roofs, facades, and ground surfaces using CheckPoints (CPs) and terrestrial laser scanning (TLS) point clouds as the reference datasets. The Root Mean Square Errors (RMSE) were calculated using CP coordinates, and cloud to cloud distances were computed using TLS point clouds, which were used for the accuracy assessment. Findings. The results showed that the point cloud model generated by the N flight mode was the most accurate but least dense, whereas that of the O mode was the least accurate but most detailed level in comparison with the others. Also, the combination of O and N datasets takes advantages of individual mode as the point clouds accuracy is higher than that of case O, and its density is much higher than that of case N. Therefore, it is optimal to build exceptional accurate and dense point clouds of buildings. Originality. The paper provides a comparative analysis in quality of point cloud of roofs and facades generated from UAV photogrammetry for mining industrial buildings. Practical value. Findings of the study can be used as references for both UAV survey practices and applications of UAV point cloud. The paper provides useful information for making UAV flight planning, or which UAV points should be integrated into TLS points to have the best point cloud.

15 April 2026 in Remote Sensing
Verified
Journal Article
Open access
PDF file
PDPham Trung Dung
Pham Trung Dung
TTThuong Tran
Thuong Tran
QNQuang-Minh Nguyen
Quang-Minh Nguyen
JLJinghan Li
Jinghan Li
Xuan ZhuXuan Zhu
Xuan Zhu
Automatic building extraction from high-resolution imagery remains constrained by limited training data and domain shifts across geographic regions and spatial resolutions. Although data augmentation is widely applied in semantic segmentation, its capacity to compensate for scarce labeled samples under varying domain conditions remains insufficiently quantified in remotely sensed data. Here, we present a controlled data-centric evaluation to quantify how explicit, label-preserving augmentation influences model generalization under varying domain shifts, rather than proposing a new augmentation algorithm. The experimental design integrates DeepLabV3+ (CNN) and SegFormer (transformer) architectures to assess whether augmentation effects persist across distinct feature-learning paradigms. Four scenarios are constructed, including two intra-domain settings, a resolution shift (0.3 m to 0.1 m), and a geographic shift across heterogeneous urban environments. Training subsets are progressively sampled from 20% to 100% to isolate the interaction between data volume and distributional variability. Geometric, radiometric, and occlusion-based transformations are evaluated individually and in combination. Under cross-domain and low-data regimes, augmentation substantially increases predictive performance. Combined transformations increase mIoU from 0.572 to 0.688 at 20% training data in the resolution shift scenario, while geometric augmentation improves mIoU from 0.444 to 0.533 under geographic transfer. Models trained on 20% augmented data exceed the performance of 100% non-augmented configurations under pronounced domain discrepancies, establishing an operational threshold of data efficiency. Computational analysis indicates negligible overhead (approximately 1 s per epoch) through asynchronous data pipelines. Augmentation functions as a regularization mechanism in intra-domain settings and transitions to a distribution bridging mechanism under cross-domain conditions. Geometric invariance and engineered data diversity partially substitute for manual annotation, enabling improved cross-domain building extraction performance.


1 September 2025 in Inżynieria Mineralna
Verified
Journal Article
Open access
PDF file
PDPham Trung Dung
Pham Trung Dung
NPNgoc Hung Pham
Ngoc Hung Pham
The building extraction from remote sensing (RS) images has been a significant area of research in the photogrammetric and remote sensing communities, especially with the development of deep learning for over a decade. With the availability of multi-source data from RS images, accurately identifying buildings with different spatial image resolutions has become a challenging task. In this study, we assessed how the unalignment of image resolution between the training and testing data sets affects the ability to extract buildings. Image resolution plays a crucial role in the performance of building extraction. Our experiments found that as the image resolution decreased from 10 cm to 50 cm, the efficiency of building segmentation reduced from 0.759 to 0.585 according to the IoU metric. Besides, the ability and accuracy of building segmentation significantly decreased when the difference in image resolution between the training and testing data sets increased. In the case study, we use the model trained on a 10 cm resolution dataset to predict for 50 cm resolution data, the IoU drops significantly to 0.299. This research offers important insights into building segmentation tasks using multi-source data from satellite, airborne, and UAV images.

8 October 2025 in Inżynieria Mineralna
Verified
Journal Article
Open access
PDF file
PDPham Trung Dung
Pham Trung Dung
NPNgoc Hung Pham
Ngoc Hung Pham
Automated building extraction using deep learning's semantic segmentation techniques on remote sensing imagery is increasingly important for mapping, urban planning, and environmental monitoring. However, this task presents considerable challenges, particularly when using Unmanned Aerial Vehicle (UAV) imagery from developing countries like Vietnam. The construction landscape in Vietnam is often characterized by non - homogeneous and non - standard building designs, as well as the coexistence of slums and modern urban areas. These real - world issues, combined with a lack of annotated data, frequently lead to model overfitting and reduced generalization. This study aims to fill a critical knowledge gap by systematically evaluating six widely used deep learning architectures: DeepLabV3+, U net, U net++, Feature Pyramid Network (FPN), Pyramid Attention Network (PAN), and SegFormer, specifically for building extraction tasks. We utilize Intersection over Union (IoU) scores and analyze overfitting behavior to compare the performance of these models on a benchmark WHU Building Dataset and a challenging proprietary Vietnamese UAV Building Dataset. Our thorough analysis quantifies the individual and combined effects of transfer learning and data augmentation on model performance. Our findings indicate that both transfer learning and data augmentation are essential, consistently resulting in higher IoU scores improving by 10 - 15% with transfer learning — and significantly reducing overfitting (from as much as 30% down to 3 - 7% on the Vietnamese dataset). Furthermore, architectural efficiency is more critical than the raw parameter count. Models like DeepLabV3+ and SegFormer achieved top - tier performance, with IoU scores of 0.858 and 0.855, respectively, on the Vietnamese dataset while maintaining a moderate parameter count of 11 - 12 million. The Vietnamese dataset proved to be inherently more challenging than the WHU benchmark, highlighting the need for robust training strategies for effective generalization in complex, real - world environments. This research provides recommendations for selecting appropriate model architectures and training strategies to ensure accurate and reliable building extraction under difficult conditions.