Jun 21, 2016 - In today's world of growing population, the need for urban planning is very high. A robust and efficient method for extraction of roads from a ...
Higher Institute for Applied Sciences and Technology Communications Department 4th year, Mini Project Multimedia
Robust and Efficient Method to Extract Roads From Satellite Images
Submitted by:
Aya Alkhateeb
Scientific Supervisor:
Dr. Nizar Zarka Eng. Bassel Shanwarr
June 21th, 2016
[Type text]
Page ii
[Type text]
Page iii
Robust and Efficient Method to Extract Roads from Satellite Images
Contents List of Figures ................................................................................Error! Bookmark not defined. Abstract ........................................................................................................................................... ii Introduction ..................................................................................................................................... 3 The algorithm steps ......................................................................................................................... 4 Practical results ............................................................................................................................... 6 The algorithm results on different images ...................................................................................... 7 Conclusion .................................................................................................................................... 10 References ..................................................................................................................................... 11
Aya Alkhateeb, Eng. Bassel Shanwar, Dr. Nizar Zarka
Page | i
Robust and Efficient Method to Extract Roads from Satellite Images
Abstract In today’s world of growing population, the need for urban planning is very high. A robust and efficient method for extraction of roads from a given set of database is explained. Roads play a vital role and important role in urban planning thus, its extraction can be of great help. The other applications of road extraction are: identification of isolated buildings that need to be detected and updating of GIS database according to the requirements of the human expertise. In this method, roads are extracted solely based on their color. The steps in the algorithm are easy to follow and implement. It is also less time consuming and an automatic method.
Aya Alkhateeb, Eng. Bassel Shanwar, Dr. Nizar Zarka
Page | ii
Robust and Efficient Method to Extract Roads from Satellite Images
Introduction Road extraction plays one of the major roles in many applications regarding the betterment of present human lives. Thus, the need for road extraction using a robust and efficient method is also high. Currently, there are many ways to extract roads manually and automatically. Road extraction explained in this report depends only on the color of the road. The advantage of this method is that road images from any type of satellite can be used provided it has more than 0.5m resolution. Here, the images considered are multispectral images. Multispectral images are those images that consist of three or more spectral bands. Any type of roads can be extracted based on their color. The algorithm is implemented using MATLAB.
Aya Alkhateeb, Eng. Bassel Shanwar, Dr. Nizar Zarka
Page | 3
Robust and Efficient Method to Extract Roads from Satellite Images
The algorithm steps The first step in this method is the creation of a database. The database should contain multispectral road images whose road intensity values are within a particular range. By considering different intensity ranges, any type of roads can be extracted. So in the beginning we should conversion of a vector image to a scalar image using spectral angle, but I do not do this step because all pictures which I obtain are scalar image.
The second step in this algorithm is scalar image is filtered using a median filter to remove noises that affects satellite images. When considering different types of filters, median filter is the most apt one to reduce noise in satellite image. That we do as this code:
filter1=medfilt2 (myimage1_1, [3 3]);
The third step in this algorithm is conversion the scalar image into a binary image for facilitation, easy, fast processing and some image enhancement operation need binary type to implement. The threshold for binary Conversion is 0.07. That we do as this code:
myimage1_2=im2bw (filter1);
The fourth step is using one of morphological operations to remove unwanted object which still in. The importance of morphological Operations can be more clearly understood by referring to [1]. Since the operations are done on the binary image, the MATLAB function used is „bwmorph‟. That we do as this code:
se1=strel ('square', 2); myimage1_3=imopen (myimage1_2, se1);
Aya Alkhateeb, Eng. Bassel Shanwar, Dr. Nizar Zarka
Page | 4
Robust and Efficient Method to Extract Roads from Satellite Images
The fifth step is edges detection for clear identification of the roads. Gradient filter is used for the edge detection and the type of operator used for the detection is „sobel‟. But I use canny operator because the edges are extracted with greater accuracy. That we do as this code:
myimage2_71=edge(myimage2_3,'canny',[0.36 0.9]);
The final step is to overlay the extracted road onto the scalar image of the original image. Overlaying of the result helps to illustrate the accuracy of the road extraction. In the final image, the thin lines indicate the paths of roads in the image. That we do as this code:
My_over1 = myimage1_1; [i2 j2]=size (myimage1_71); for i3 = 1:i2 for j3=1:j2 if myimage1_71 (i3, j3) == 1 My_over1 (i3, j3) = 1; end end end figure Imshow(My_over1);
Aya Alkhateeb, Eng. Bassel Shanwar, Dr. Nizar Zarka
Page | 5
Robust and Efficient Method to Extract Roads from Satellite Images
Practical results To show the results of our algorithm, I allocate the outcome of each step in the same picture:
Aya Alkhateeb, Eng. Bassel Shanwar, Dr. Nizar Zarka
Page | 6
Robust and Efficient Method to Extract Roads from Satellite Images
The algorithm results on different images We apply the previous algorithm on different images and we obtain: The first image:
Aya Alkhateeb, Eng. Bassel Shanwar, Dr. Nizar Zarka
Page | 7
Robust and Efficient Method to Extract Roads from Satellite Images
The second image:
Aya Alkhateeb, Eng. Bassel Shanwar, Dr. Nizar Zarka
Page | 8
Robust and Efficient Method to Extract Roads from Satellite Images
The third image:
Aya Alkhateeb, Eng. Bassel Shanwar, Dr. Nizar Zarka
Page | 9
Robust and Efficient Method to Extract Roads from Satellite Images
Conclusion Finally we can considered our algorithm fast, robust and easy to understand and implement, also different types of roads can be extracted. But this algorithm depend on the color of roads in the database that led to some of the barren lands and small areas of parking lots are also being extracted. This is because the locations also have the same pixel intensity values as that of roads. Different other techniques such as usage of Digital Elevation Models (DEM), active contours and artificial intelligence methods could be included to remove the unwanted objects that are being extracted.
Aya Alkhateeb, Eng. Bassel Shanwar, Dr. Nizar Zarka
Page | 10
Robust and Efficient Method to Extract Roads from Satellite Images
References [1] D. Chaudhuri, N. K. Kushwaha, and A. Samal, “Semi-Automated Road Detection From High Resolution
[2]
Satellite Images by Directional Morphological Enhancement and Segmentation Techniques” IEEE Journal Of Selected Topics In Applied Earth Observations And Remote Sensing, Vol. 5, No. 5, October 2012. J. Mena, “State of the art on automatic road extraction for GIS update: a novel classification,” Pattern Recognition Letters, vol. 24, pp. 3037 3058, 2003.
Aya Alkhateeb, Eng. Bassel Shanwar, Dr. Nizar Zarka
Page | 11
