Automatic Road Extraction from Remote Sensing Images Based on Fuzzy Connectedness

With the rapid development of space technology, space remote sensing activities get a full extension and application. Remote sensing information has become an essential part of geographic information data source. As a very important kind of geographic information in remote sensing information, road information has a wide range of applications in the field of traffic navigation, urban planning, and military reconnaissance. To acquire road information accurately and rapidly is the only way to meet the needs of practical application. But due to the high complexity of remote sensing information of the road, and the modern computer automation has not yet reached the level of the corresponding demand, so far there is still not a mature and reliable automatic road extraction method, so the automatic road extraction technology has become a research hotspot in remote sensing information processing. This paper presents an automatic algorithm based on fuzzy connectedness which can extract road information from the remote sensing images. The algorithm detects the edge of the image with Canny operator and connected domain elimination. Then extend the road with the fuzzy connectedness to form a road image. After using fuzzy connectedness expansion algorithm, the automatic identification of the road can be achieved. In many trials of treating remote sensing images as objects, the performance of this extraction algorithm has high accuracy and greater versatility. The results of the experiment are in line with basic human identification results. Road information is critical to the public when disaster comes, having a full knowledge of the road information may help reducing the casualties. As a result, road extraction is vital to the safety of our citizens as well as our government's emergency warning, preparedness and planning. Road extraction has great significance in the earthquake relief and forest fire escape, thus plays an important role in emergency rescue and relief work.