Gou Koutaki

Urban road extraction based on hough transform and region growing

In the paper, we present an approach of road extraction in urban area by combining the Hough transform and region growing. In this case, we use Digital Surface Mode (DSM) data, which is based on the elevation of land surface, building, and so on to overcome the disadvantage of aerial photo image. The main problem in extracting the road in urban area from an aerial photo is the shadow cast by the buildings. The shadow will lead to an inappropriate road segment. Another benefit of using the DSM data in urban area is the significant different of the elevation between the road and the building elevation. A simple thresholding of this data could extract some of the road. To improve the result, we use Hough transform to detect and recognize the road as a line and use this information to make a better threshold. Furthermore, we use the seeding region growing method to expand the road network. The seeds for region growing are obtained from the perimeter of the threshold segmentation resulted by hough lines. Finally, the post processing is required to remove a false road by employing the morphology image operator. The experiment result shows that the proposed method improves the quality result with a very good performance.

Automatic urban road extraction on DSM data based on fuzzy ART, region growing, morphological operations and radon transform

In recent years, an automatic urban road extraction, as part of Intelligent Transportation research, has attracted the researchers due to the important role for the next modern transportation where urban area plays the main role within the transportation system. In this work, we propose a new combination of fuzzy ART clustering, Region growing, Morphological Operations and Radon transform (ARMOR) for automatic extraction of urban road networks from the digital surface model (DSM). The DSM data, which is based-on the elevation of surface, overcome a serious buildings shadow problem as in the aerial photo image. Due to the different elevation between the road and the buildings, the thresholding technique yields a fast initial road extraction. The threshold values are obtained from Fuzzy ART clustering of the geometrical points in the histogram. The initial road is then expanded using region growing. Though most of the road regions are extracted, it contains a lot of non-road areas and the edge is still rough. A fast way to smoothing the region is by employing the morphology closing operation. Furthermore, we perform the road line filter by opening operation with a line shape structuring element, where the line orientation is obtained from the Radon Transform. Finally, the road network is constructed based-on B-Spline from the extracted road skeleton. The experimental result shows that the proposed method running faster and increases the quality and the accuracy about 10% higher than the highest result of the compared method.

Urban Road Network Extraction Based on Zebra Crossing Detection from a Very High Resolution RGB Aerial Image and DSM Data

Recently, road network extraction in urban areas using high resolution data, has attracted many researchers because it is very challenging and important work in order to provide an intelligent spatial processing. In this work, we use two types of data: an extremely high-resolution image in which the signature of the road, such as zebra crossing, road lines, cars, and the like, can be seen in detail, and DSM data, which is based on the elevation of the surface. We propose a road extraction based on zebra crossings detection where there is a simple peculiar pattern to recognise. In this task, we employ a circle mask template matching and Speeded Up Robust Features (SURF) method in order to detect and evaluate the zebra crossing location in an RGB aerial image. These locations of zebra crossings represent the starting point of the road and we associate it to the corresponding DSM data to obtain the elevation information. In the DSM data, the elevation of the road and the building differ significantly, therefore, we expand the starting point based on a local thresholding and seeded region growing to create an initial road region quickly. Furthermore, we utilise morphological opening operation with a line shape structural element to produce the road line and remove the false alarms. The experimental result shows that the proposed method is run quick enough with good accuracy.

Urban road extraction based on shadow removal and road clues detection from high resolution RGB aerial image

In urban areas, the shadow cast by buildings, trees along the road, abundant objects and complex image texture make the extraction of the road on very high Resolution RGB aerial image very difficult and challenging. We propose a method of road extraction from RGB aerial image in the followings steps: Shadow removal, enhanced sobel transform, keypoints extraction based on Maximally Stable Extremal Regions (MSER), feature extraction based on Speeded Up Robust Features (SURF) and road construction based on multi-resolution segmentation. The experimental results show that the proposed method achieves a good result.

Urban Road Network Extraction Based on Fuzzy ART, Radon Transform and Morphological Operations on DSM Data

In urban areas, the main disadvantage of an aerial photo for road extraction is the shadow cast by buildings and the complexity of the road network. For this case, we used Digital Surface Model (DSM) data, which are based on the elevation of land surfaces. However, one of the problems associated with DSM data is the non-road area with the same road elevations, like parking places, parks, empty ground and so on. In this paper, we propose the Mixed ART clustering on histogram followed by region growing to extract the initial road and perform the road filter by opening operation with a line shape structuring element, where the line orientation is obtained from the Radon Transform. Finally, the road networks are constructed based on B-Spline curve from the skeleton of the extracted road. The experimental result shows that the proposed method improved the quality and the accuracy average within an acceptable time.

Grid seeded region growing with Mixed ART for road extraction on DSM data

Region Growing with Mixed ART is one of the methods for road extraction based on segmentation processing. The method is based on Region Growing method but using ART approach as homogeneity measurement. However, a drawback of this method is time consuming. For road extraction problem, it is unnecessary to separate all the regions as in general segmentation approach. We only need some of the road data and then grow it to obtain the road network. In this paper, we proposed a grid seeded region growing with Mixed ART. Since the road will cross the grid, we can obtain the road network based on growing from these seed points. The experimental result shows that the proposed method performs faster up to four times than the conventional seed point with the similar quality. The accuracy of extracted road and non-road are 74% and 77% respectively.