A5035493173- Data Management and Algorithms
- Geographic Information Systems Studies
- Advanced Image and Video Retrieval Techniques
- Automated Road and Building Extraction
- Image Retrieval and Classification Techniques
- Solar Radiation and Photovoltaics
- Currency Recognition and Detection
- Advanced Neural Network Applications
- Remote Sensing and LiDAR Applications
University of Washington Tacoma
2022-2023
University of Washington
2023
As the global transition towards renewable energy sources accelerates, solar power becomes an increasingly important solution. Identifying and understanding current distribution of panel installations is crucial for future planning decision-making process. This paper introduces SolarDetector, a transformer-based neural network model, which we developed fine-tuned accurate detection panels. It achieves 91.0% mIoU task masking panels on SWISSIMAGE dataset.
Today, people's lives are enriched by the integration of electronic maps via smartphones. Electronic required for a variety commercial activities, such as catering, movie viewing, and tourism. Route planning navigation particularly intrinsically linked to maps. As result, it is critical that roads on map complete accurate. At present time, there discrepancies between various providers. This paper evaluates providers' Due varied terrain depicted map, assessing road properties can be...
We demonstrate MapsVision, a computer vision-based framework capable of identifying discrepancies across different map providers for similar geographical locations. In this study, we primarily focus on three including: (a) Bing Maps, (b) Google and (c) OpenStreetMap. MapsVision detects textual data such as: (1) missing location labels (2) misspelled or keywords, (3) shifted labels, (4) level significance manifested by text label font-size color. For given location, our compares based ground...
Maps provide various sources of information. An important example such information is textual labels as cities, neighborhoods, and street names. Although we treat this facts, despite the massive effort done by providers to continuously improve their accuracy, data far from perfect. Discrepancies in rendered on map are one major inconsistencies across providers. These discrepancies can have significant impacts reliability derived decision-making processes. Thus, it validate accuracy...
With the increasing availability of smart devices, billions users are currently relying on map services for many fundamental daily tasks such as obtaining directions and getting routes. It is becoming more important to verify quality consistency route data presented by different providers. However, verifying this manually a very time-consuming task. To address problem, in paper we introduce novel geospatial analysis system that based road directionality. We investigate our Road...