As the global transition towards renewable energy sources accelerates, solar power becomes an increasingly important solution. Identifying and understanding the current distribution of solar panel installations is crucial for future planning and decision-making process. This paper introduces SolarDetector, a transformer-based neural network model, which we developed and fine-tuned for the accurate detection of solar panels. It achieves 91.0% mIoU for the task of masking solar panels on SWISSIMAGE dataset.

Maps provide various sources of information. An important example of such information is textual labels such as cities, neighborhoods, and street names. Although we treat this information as facts, and despite the massive effort done by providers to continuously improve their accuracy, this data is far from perfect. Discrepancies in textual labels rendered on the map are one of the major sources of inconsistencies across map providers. These discrepancies can have significant impacts on the reliability of the derived information and decision-making processes. Thus, it is important to validate the accuracy and consistency in such data. Most providers treat this data as their propriety data and it is not available to the public, thus we cannot compare the data directly. To address these challenges, we introduce a novel computer vision-based approach for automatically extracting and classifying labels based on the visual characteristics of the label, which indicates its category based on the format convention used by the specific map provider. Based on the extracted data, we detect the degree of discrepancies across map providers. We consider three map providers: Bing Maps, Google Maps, and OpenStreetMaps. The neural network we develop classifies the text labels with an accuracy up to 93% in all providers. We leverage our system to analyze randomly selected regions in different markets. The studied markets are USA, Germany, France, and Brazil. Experimental results and statistical analysis reveal the amount of discrepancies across map providers per region. We calculate the Jaccard distance between the extracted text sets for each pair of map providers, which represents the discrepancy percentage. Discrepancies percentages as high as 90% were found in some markets.

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 map providers including: (a) Bing Maps, (b) Google Maps, and (c) OpenStreetMap. MapsVision detects textual data discrepancies such as: (1) missing location labels (2) misspelled or different keywords, (3) shifted labels, and (4) level of significance manifested by text or label font-size and color. For a given location, our MapsVision framework compares textual labels based on a ground truth entered manually to those that exist in the three map providers. We then use the results of the textual extraction to determine the accuracy of textual data appearing on map providers. Our framework intelligently identifies the set of techniques for each map providers' that can maximize the overall detection accuracy. MapsVision is composed of three main building blocks including: (a) a capturing module that captures map tiles from map providers, (b) an analysis tool that uses computer vision and text-analytic techniques, and (c) a rich visualization interface for displaying statistical and real-time analytics. The objective of MapsVision is to help map editors improve the textual quality of their maps compared to other map providers.

Today, people's lives are enriched by the integration of electronic maps via smartphones. Electronic maps are required for a variety of commercial activities, such as catering, movie viewing, and tourism. Route planning and navigation are particularly intrinsically linked to electronic maps. As a result, it is critical that the roads on the electronic map are complete and accurate. At the present time, there are discrepancies between the map roads of various providers. This paper evaluates the roads on various map providers' maps. Due to the varied terrain depicted on the map, assessing the road properties can be challenging. Additionally, roads of varying thicknesses exist within a tile image, making it difficult to quantify the map's road lengths. This paper proposes a method for extracting road segments using an image binarization technique and employs edge erosion to assist in automatically computing the length of roads within maps. Throughout the paper, we provide comparison and statistical analysis on using our proposed road length detection model across map providers. Results show that our detection model can identify road length accurately and hence provide an overall measure of quality of maps.