It is common for these solutions to exploit spectral and spatial features for image target identification. This problem is being easily dominated by Object-Based Image Analysis (OBIA) of high-resolution optical images. This topic covering the mapping of urban settlements based on remote sensing images has a rich history and supporting literature. Some of the latest work on this topic is Refs. The best way forward is to have an automated, intelligent, image-based solution. Manually classifying objects taken from low altitudes and via Unmanned Aerial Vehicle imaging technology is also severely extensive despite some advantages over field surveys.
#Spacenet buildinglabels example update#
Consequently, it is a perfect method to update databases if employed wisely. Remote sensing provides a less easy, less costly, and more accurate alternative to field surveys that allow larger coverage. This field survey requires high manpower and expenses because of the increasing complexity and number of urban villages.
#Spacenet buildinglabels example manual#
Traditional methods of cartography of unplanned construction in urban settlements require field visits, extensive measurement of constructions of interest, and manual digitalization of data. Urban villages are the most common outcomes of the discussed urban sprawling worldwide and require immediate attention. To devise a strategic policy, it is important to understand every component that prepares the area and every construction that characterizes the slum. These situations require efficient management, reconstruction, and big leap improvement of unplanned habitats. Moreover, the public safety sector has been majorly compromised. While these unplanned settlements do provide housing for low-income personals, they have become to the root causes of unequal and unsatisfactory living conditions and standards. This demand has led to the settlement of many unplanned areas, which are highly packed with small buildings. There is a rapidly increasing demand for housing facilities for the low-income population.
The statistics for this problem can be known by the mapping of the settlements for nearly 564 million rural population in China. Less-developed countries, especially in Asia and Africa, often witness new unplanned settlements like slums, urban villages, and shantytowns as the urban sprawls continue to cater to the increasing population. It has been determined that building mapping can be achieved with high-resolution antenna images with high accuracy achieved. This study demonstrated the potential of automatic building extraction with the help of artificial intelligence in high-density residential areas. A successful image segmentation was achieved with 90% accuracy. A high result was obtained with an F1 score of 0.9. In line with the work done, 82.2% IoU accuracy was achieved in building segmentation. In the U-net architecture, image segmentation is performed with different encoders and the results are compared. It was aimed to remove buildings in the high-density city of Boston. The Massachusetts building dataset includes residential buildings of the city of Boston.
The open-source Massachusetts building dataset was used as the dataset. This study proposes the differentiation of buildings by image segmentation on high-resolution satellite images with U-net architecture. Artificial intelligence technology, which has increased significantly today, has the potential to provide building extraction on high-resolution satellite images. The main reason for the problem is that manual building extraction is very difficult and takes a lot of time. Building extraction on satellite images poses another problem. Unplanned urban settlements are quite common, especially in low-income countries. Recently, settlement planning and replanning process are becoming the main problem in rapidly growing cities.
0 kommentar(er)
