Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Kongwen (Frank) Zhang has a total of 35 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    UAV Panoramic Filming for Rapid Indirect Optical Estimation of Leaf Area Index (LAI)

    by Jingwei Gao, Ruiqiang Guo, Kongwen Zhang

    Leaf Area Index (LAI) is a fundamental structural metric for characterizing terrestrial ecosystems, quantifying carbon sequestration, and understanding canopy physiological processes. The LAI-2200C Plant Canopy Analyzer provides established multi-angular gap-fraction measurements for indirect optical LAI estimation; however, its ground-based operation can be constrained by terrain accessibility, limited spatial coverage, and sky illumination conditions. This study presents an Unmanned Aerial Vehicle (UAV)-based approach that uses the upward-facing 180° fisheye camera of a DJI Avata 360 platform to approximate the hemispherical viewing geometry and multi-angular sampling of the LAI-2200C. The circular fisheye imagery is processed directly by identifying the image centre and calibrating its projection geometry to convert pixel positions into zenith angles. Five concentric angular masks corresponding to the LAI-2200C’s viewing rings are then applied to extract canopy gap fractions from classified sky and vegetation pixels. The resulting multi-angular gap-fraction measurements are used to estimate effective LAI through the Miller integral approach, providing an image-based alternative to conventional optical measurements. Comparisons with ground-based LAI-2200C observations across on-site plots demonstrate strong agreement, while the UAV platform substantially increases sampling efficiency and spatial coverage. In particular, the first-person-view (FPV) flight capability offers considerable flexibility for collecting canopy observations in steep terrain, dense vegetation, and otherwise inaccessible locations where conventional ground-based measurements are difficult or impractical. This approach provides a rapid, flexible, and potentially scalable alternative for LAI assessment.

  • Open Access

    Monitoring agricultural drought mitigation using MODIS data: a spatiotemporal study of Henan province, 2001–2022

    by Yue Li, Junjie Zhu, Kongwen Zhang, Chenyu Lv

    Agricultural drought represents one of the most persistent and damaging natural hazards in Henan province, posing a severe threat to regional food security and socio-economic stability. Monitoring the shifting center of gravity of drought-prone areas is essential for proactive mitigation, and vegetation-based remote sensing indices offer an efficient means to capture these dynamics. This study evaluates the efficacy of four satellite-borne remote sensing drought indices, namely, the Crop Water Stress Index (CWSI), Vegetation Supply Water Index (VSWI), Normalized Difference Drought Index (NDDI), and Temperature Vegetation Dryness Index (TVDI), against the meteorological and physical measurement-based Self-Calibrating Palmer Drought Severity Index (SC-PDSI) to determine their applicability across the province’s diverse landscapes. Correlation analysis shows that CWSI is most consistent with a moderate but statistically significant SC-PDSI value ( r = − 0.47 , p < 0.001 ) , particularly in regions with complex terrain. This is particularly evident in regions with complex terrain, suggesting CWSI is the most applicable index for drought monitoring in this region. Spatiotemporal analysis based on the CWSI indicates a significant decline in agricultural drought intensity from 2001 to 2022, with a decadal decline rate of − 0.052 / 10 a . Spatially, drought severity follows a “northwest-heavy, southeast-light” gradient. Chronic drought conditions were primarily concentrated within the central agricultural plains and the Loess hilly regions of the northwest, whereas the high-altitude forested regions in the west remained largely unaffected. Notably, the total drought-affected area has contracted significantly, with moderate drought coverage decreasing by 25%, suggesting multiple interacting factors contribute to an overall recovery in regional moisture conditions. Analysis of the drought center of gravity (defined by CWSI > 0.75 ) reveals a consistent northeastward migration at an average velocity of 2.97 km/year. These findings highlight the significant contributions of vegetation dynamics and human intervention in reshaping drought landscapes and provide an essential scientific basis for drought mitigation and sustainable water resource management in transitional climate zones.

  • Open Access

    Simulating the Future: A Digital Twin Framework for Rapidly Developing Mid-Size Canadian Cities: The Abbotsford Public Transit Case Study

    by Kongwen (Frank) Zhang, Katherine Hilal, Wei Li, Amy Keryluik Casey

    Rapidly developing, mid-sized Canadian municipalities often suffer from a deficit in dedicated modernization capacity, leaving public infrastructure lagging behind growth and reliant on historically “grandfathered” legacy solutions. To overcome the lack of empirical, data-backed planning in these regions, this paper proposes an agile, data-driven smart city framework centered around a localized digital twin (DT) environment. The framework is evaluated through a case study of a proposed new public transit route in Abbotsford, British Columbia, a rapidly expanding city grappling with decentralized commercial zones and low-density sprawl. Our approach synthesizes heterogeneous, multi-source spatial data, including regional commuter trajectories, real-time Abbotsford International Airport (YXX) flight schedules, and points of interest (POI) business densities, to map high-resolution hourly temporal variations in traffic conditions. These streams feed into a virtual simulation framework that evaluates operational cost–benefit trade-offs for proposed transit routes. Crucially, this framework serves as a living, continuously updated system that enables resource-constrained cities to dynamically simulate transit networks as commercial footprints and transit volumes evolve. Finally, we discuss the roadmap for this framework, detailing how integrating predictive AI models and gamified interfaces can democratize urban planning, enabling municipal stakeholders and non-technical operators to interactively co-design public transit systems.

  • Open Access

    Evaluating the Influence of Pseudo Tree Crown (PTC) Input Alternatives for Machine Learning and Deep Learning Models on Individual Tree Classification Performance

    by Tong Yan, Kongwen Zhang, Wuxue Cheng, Jane Liu

    Individual tree classification has a long history of diverse development, with recent trends focusing on the adoption of machine learning and deep learning approaches. It is a simple and powerful approach that allows the model to auto-pilot while reducing the need for physical characteristic understanding. Over more than a decade of research, we have focused on establishing a direct representation of individual trees that bridges 2D top-down imagery and true 3D models. In this study, we investigated the fundamental question of the influence of the input data on these ML/DL models. In 2024, we introduced a novel data transformation method, the Pseudo Tree Crown (PTC), which provides a pseudo-3D pixel-value perspective that enhances the informational richness of images and significantly improves classification performance. Our original implementation was successfully tested on urban and deciduous trees in 2024 and was later extended to Canadian natural conifer species under snow conditions in 2025. However, the original PTC relied on the green band, limiting its applicability to green-leaf species. In this study, we analyzed and compared the performance of different data variations and transformations, such as the Green–Red Vegetation Index (GRVI) and principal component analysis (PCA), as direct input and used their PTC forms. Classifications were conducted using Random Forest (RF), ResNet50, YOLOv10 and Segment Anything (SA). The results confirmed the effectiveness of the PTC, which consistently improves the classification accuracy by at least 5% without introducing additional computational time or complexity. Furthermore, PTC exhibits robust, consistent behavior across all data forms, demonstrating its strong resilience and reliability.

  • Open Access

    Evaluating the Influence of Pseudo Tree Crown (PTC) Input Alternatives for Machine Learning and Deep Learning Models on Individual Tree Classification Performance

    by Yan Tong, Kongwen (Frank) Zhang, Wuxue Cheng, Jane Liu

    Individual tree classification has a long history of diverse development, with recent trends focusing on the adoption of machine learning and deep learning approaches. A simple and powerful approach that lets the model auto-pilot, but weakens the need for physical characteristic understanding. Over more than a decade of our research, we have focused on establishing a direct representation of individual trees that bridges 2D top-down imagery and true 3D models. In this study, we investigated the fundamental question of the influence of the input data on these ML/DL models. In 2024, we introduced a novel data transformation method, the Pseudo Tree Crown (PTC), which provides a pseudo-3D pixel-value perspective that enhances the informational richness of images and significantly improves classification performance. Our original implementation was successfully tested on urban and deciduous trees in 2024 and was later extended to Canadian natural conifer species under snow conditions in 2025. However, the original PTC relied on the green band, limiting its applicability to green-leaf species. In this study, we analyzed and compared the performance of different data variations and transformations, such as the Green–Red Vegetation Index (GRVI) and Principal Component Analysis (PCA), as direct input and used their PTC forms. Classifications were conducted using Random Forest, ResNet50, and YOLOv10. The results confirmed the effectiveness of the PTC, which consistently improves classification accuracy by at least 7% without introducing additional computational time or complexity. Furthermore, PTC exhibits robust, consistent behaviour across all data forms, demonstrating its strong resilience and reliability.

  • Open Access

    Bridging Nadir Observations and Three-Dimensional Tree Structure through Species-dependent Generative Modeling

    by Raghav Sharma, Kongwen (Frank) Zhang, Jane Liu, Baoxin Hu

    Reconstructing three-dimensional (3D), species-dependent tree structure from widely available two-dimensional (2D) nadir-view remote sensing data represents a critical yet unresolved challenge in forest monitoring and ecological analysis. While decades of airborne and satellite imagery provide rich spatial and temporal coverage, their inherent top-down perspective limits direct access to lateral crown structure, constraining the characterization of individual trees and canopy dynamics. In this study, we propose a novel 2D-to-3D inference framework that synthesizes realistic lateral (fac¸ade) views of individual tree crowns from single nadir-view LiDAR data as proxy, establishing an important intermediate step toward optical 3D forest modeling. Using a conditional diffusion framework, we demonstrate that integrating ancillary biological attributes, specifically tree species and height, resolves the inherent ambiguity in mapping nadir observations to lateral structure. The model learns species-dependent structural priors that enable the generation of physically plausible fac¸ade views, effectively transmuting 2D observations to infer missing 3D characteristics. Our quantitative evaluation demonstrates high pixel-wise fidelity between generated and measured ground-truth LiDAR data, achieving a Mean Absolute Error (MAE) of 0.077. Currently, nadir data alone are reported as insufficient to recover meaningful fac¸ade geometry, whereas conditioning on species identity and tree height enables robust reconstruction of characteristic crown shapes and vertical profiles. This study highlights the role of attribute-conditioned generative modeling as a scalable mechanism for transforming 2D remote sensing archives into enriched 3D structural representations. By bridging the gap between nadir imagery and species-dependent 3D tree models, the proposed approach lays the groundwork for future reconstruction of individual tree structure from historical 2D imagery, supporting long-term analyses of tree growth, canopy evolution, and ecosystem dynamics at landscape scales.


  • Open Access

    Indoor Pathfinding with the A* Algorithm: A Cross-Platform Mobile Implementation Case

    by Kongwen Zhang, Boris Massesa, Jingwen Gao

    This study presents the development of a fully integrated mobile module that enables indoor pathfinding functionality from the front end to the back end. The module is implemented using the A* algorithm for route optimization and a NestJS framework with PostgreSQL and PostGIS for spatial data management. Designed as part of the University of the Fraser Valley (UFV) Campus App project, this cross-platform mobile application is built with React Native to ensure seamless usability across devices. Core functionalities include intelligent room search, interactive floor plan visualization, and real-time, turn-by-turn navigation powered by WebSocket communication. The system demonstrates the feasibility of combining spatial databases, efficient routing algorithms, and real-time communication technologies to enhance campus navigation and user experience.

  • Open Access

    Low-Cost CCTV Repurposing for Sustainable Parking Management: A Non-AI Computer Vision Case Stud

    by Namya Kamboj, Kongwen Zhang

    Urban parking inefficiency results in fuel waste and emissions, yet the current monitoring systems rely on resource-intensive AI or sensor-based approaches. Aligning with a focus on sustainable technology, this project demonstrates how deterministic computer-vision techniques (using adaptive thresholding and polygon masking) can transform the existing CCTV camera framework into parking occupancy detectors without AI. This system deploys an open-source pipeline, combining OpenCV and PyQt5, on UFV’s infrastructure, which requires zero hardware costs and consumes 95% less power than other GPU-based solutions. Testing with 18,000+ frames of simulated CCTV footage, the system achieved approximately 99% accuracy. This case study presents a replicable solution for institutions in resource-constrained environments, demonstrating that an economical IoT-CV integration can optimize urban resources while minimizing AI’s carbon footprint.


  • Open Access

    Individual Tree Species Classification Using Pseudo Tree Crown (PTC) on Coniferous Forests

    by Kongwen (Frank) Zhang, Tianning Zhang, Jane Liu

    Coniferous forests in Canada play a vital role in carbon sequestration, wildlife conservation, climate change mitigation, and long-term sustainability. Traditional methods for classifying and segmenting coniferous trees have primarily relied on the direct use of spectral or LiDAR-based data. In 2024, we introduced a novel data representation method, pseudo tree crown (PTC), which provides a pseudo-3D pixel-value view that enhances the informational richness of images and significantly improves classification performance. While our original implementation was successfully tested on urban and deciduous trees, this study extends the application of PTC to Canadian conifer species, including jack pine, Douglas fir, spruce, and aspen. We address key challenges such as snow-covered backgrounds and evaluate the impact of training dataset size on classification results. Classification was performed using Random Forest, PyTorch (ResNet50), and YOLO versions v10, v11, and v12. The results demonstrate that PTC can substantially improve individual tree classification accuracy by up to 13%, reaching the high 90% range.


  • Open Access

    Submarine Topography Classification Using ConDenseNet with Label Smoothing Regularization

    by Jingyan Zhang, Kongwen Zhang, Jiangtao Liu

    The classification of submarine topography and geomorphology is essential for marine resource exploitation and ocean engineering, with wide-ranging implications in marine geology, disaster assessment, resource exploration, and autonomous underwater navigation. Submarine landscapes are highly complex and diverse. Traditional visual interpretation methods are not only inefficient and subjective but also lack the precision required for high-accuracy classification. While many machine learning and deep learning models have achieved promising results in image classification, limited work has been performed on integrating backscatter and bathymetric data for multi-source processing. Existing approaches often suffer from high computational costs and excessive hyperparameter demands. In this study, we propose a novel approach that integrates pruning-enhanced ConDenseNet with label smoothing regularization to reduce misclassification, strengthen the cross-entropy loss function, and significantly lower model complexity. Our method improves classification accuracy by 2% to 10%, reduces the number of hyperparameters by 50% to 96%, and cuts computation time by 50% to 85.5% compared to state-of-the-art models, including AlexNet, VGG, ResNet, and Vision Transformer. These results demonstrate the effectiveness and efficiency of our model for multi-source submarine topography classification.