A5069488868- Automated Road and Building Extraction
- Remote Sensing and LiDAR Applications
- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Remote Sensing in Agriculture
- Wildlife-Road Interactions and Conservation
- Service-Oriented Architecture and Web Services
- Data Management and Algorithms
- Land Use and Ecosystem Services
- Grey System Theory Applications
- Advanced Neural Network Applications
- Colorectal Cancer Screening and Detection
- Gallbladder and Bile Duct Disorders
- Green IT and Sustainability
- Advanced Computational Techniques and Applications
- Geoscience and Mining Technology
- Social Work Education and Practice
- IoT-based Smart Home Systems
- Smart Agriculture and AI
- Geographic Information Systems Studies
- Advanced Image Fusion Techniques
- Interactive and Immersive Displays
- Advanced Decision-Making Techniques
- Multi-Criteria Decision Making
- IoT and Edge/Fog Computing
Hangzhou Dianzi University
2025
State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing
2020-2024
Wuhan University
2020-2024
National Yang Ming Chiao Tung University
2010
Anqing Normal University
2008
Building extraction based on high-resolution remote sensing imagery has been widely used in automatic surveying and mapping. However, few methods have developed for building instance extraction, i.e., extracting each building's footprint separately, which is required a number of applications, such as the smallest unit cadastral database. In there are two challenges: 1) buildings with various scales exist 2) precise footprints difficult to extract due blurry boundaries. this article, solve...
Road extraction from very high-resolution (VHR) remote sensing imagery remains a huge challenge, due to the shadows and occlusions of trees buildings. Such complex backgrounds result in deep networks often producing fragmented roads with poor connectivity. has three typical tasks: road surface segmentation (SS), centerline (CE), edge detection (ED), which are conducted wide range real applications. Also, tasks have symbiotic relationship, i.e., SS determines location edges, CE ED can allow...
With rapid development of service-oriented architecture and cloud computing, web services have been widely adopted for developing various kinds applications. A set non-functional requirements such as QoS has become important criteria service selection. The nature based selection can be treated a multiple group decision making (MCDM) problem. This article presents an evaluation method on the technique Order Preference by Similarity to Ideal Solution (TOPSIS) help consumers providers analyze...
Abstract Background The study aimed to construct an intelligent difficulty scoring and assistance system (DSAS) for endoscopic retrograde cholangiopancreatography (ERCP) treatment of common bile duct (CBD) stones. Methods 1954 cholangiograms were collected from three hospitals training testing the DSAS. D-LinkNet34 U-Net adopted segment CBD, stones, duodenoscope. Based on segmentation results, stone size, distal CBD diameter, arm, angulation estimated. performance estimation was assessed by...
Accurate mapping of global urban man-made objects such as buildings and roads is critical for monitoring urbanization. Remote sensing imagery provides a cost-effective way these objects, but the challenge "knowledge forgetting" arises due to diversity continuous growth samples. Although existing knowledge distillation approaches can transfer from larger teacher model smaller student by distilling learned reliable labels, they fail work global-scale mapping, which lies in two aspects:...
Climate change is one of the driving forces behind a new wave energy management systems. Most currently available systems in domestic environment are concerned with real-time consumption monitoring, and display statistical real time data consumption. Although these play crucial role providing detailed picture home contribute towards influencing behavior household, they all leave it to households take appropriate measures reduce their Some do provide general saving tips but not consider...
Aircraft recognition is crucial in both civil and military fields, high-spatial resolution remote sensing has emerged as a practical approach. However, existing data-driven methods fail to locate discriminative regions for effective feature extraction due limited training data, leading poor performance. To address this issue, we propose knowledge-driven deep learning method called the explicable aircraft framework based on part parsing prior (APPEAR). APPEAR explicitly models aircraft's...
There is a growing interest in designing an interoperable smart home environment which involves heterogeneous appliance systems, as it aims to increase the system flexibility. With rapid growth numbers of appliances, devices, and services, task for integrating systems become difficult. In addition, diversity these technologies involved poses tremendous challenges implementation development. The emergence Service Component Architecture (SCA) also generates large interests, they can exploit...
Greenhouses are densely distributed across the cultivated land in high-resolution remote sensing imagery, resulting problem of dense object extraction. On one hand, objects tend to be wrongly merged into since connected; on other existed random sampling scheme does not make good use distribution density improve training effect. To meet demand for greenhouse extraction, this paper proposes a novel deep learning-based extraction algorithm. solve that merged, dual-task learning module, which...
Accurate and timely road mapping that describes the network geometry topology is key element of intelligent transport systems smart city management. However, current global maps like OpenStreetMap (OSM) are typically outdated spatially incomplete with uneven accuracies. Although development remote sensing satellite technology advance computer vision have made it possible to quickly extract networks from massive very-high-resolution (VHR) imagery, existing extraction methods limited by...
Recent advancements in satellite remote sensing technology and computer vision have enabled rapid extraction of road networks from massive, Very High-Resolution (VHR) imagery. However, current methods face the following limitations: 1) Insufficient availability accurate diverse training datasets for global-scale extraction; 2) Costly time-consuming manual labeling millions samples; 3) Limited generalization ability deep learning models across global contexts, resulting better performance...
Urban road vectorization mapping can reflect the urban development of cities, which consists two separate tasks: extraction and vectorization. Most current methods focus on yet ignoring importance vectorization, facing problem connectivity. In this work, to implement in a unified way, novel framework is proposed. The proposed node proposal network (NPN) module connectivity based refinement module. NPN module, head adopted, improves mask by providing supervision nodes, are actually part mask....
Building extraction based on high-resolution remote sensing imagery has been widely used in automatic surveying and mapping. Recently, the instance segmentation algorithm introduced to building extraction, which can calculate number area of buildings simultaneously. However, there are some challenges: 1) multi-scale buildings; 2) occlusion by other adjacent buildings. In this paper, solve these problems, we propose a framework feature pyramid object-aware convolution neural network (CNN)....