Your SlideShare is downloading. ×
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Miniproject final group 14
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×
Saving this for later? Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime – even offline.
Text the download link to your phone
Standard text messaging rates apply

Miniproject final group 14

973

Published on

Published in: Education
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
973
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
0
Comments
0
Likes
0
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide

Transcript

  • 1. SIKKIM MANIPAL INSTITUTE OF TECHNOLOGY .
    • DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
    • AUTOMATIC EXTRACTION & VECTORIZATION OF CONTOUR LINES FROM TOPOGRAPHICAL MAP
    • PROJECT GUIDE:
    • Mrs . Ratika Pradhan (Reader)
    • TEAM MEMBERS:
    • Ruchika Agarwal (200611088)
    • Shikhar Kumar (200613050)
    • Sameer Gupta (200611092)
  • 2. PROBLEM STATEMENT
    • Given a topographic sheet, we need to process the images to detect the contours with their exact coordinate and altitude information and store it in a database.
  • 3. PROBLEM ANALYSIS
    • Very high resolution images require greater memory space hence increased processing time.
    • Biggest challenge is to identify the brown contour lines from other similar colored noises in the extracted result.
    • Slight error encountered during extraction results in broken contour lines or intersecting contour lines.
    • The Moore’s tracing algorithm gives undesirable result for multi-pixel lines hence thinning is required to be performed before implementation of the algorithm.
    • The Moore’s tracing algorithm is the most efficient algorithm for tracing a region’s boundary.
  • 4.
    • The process involves following steps
    • Extracting contours based on color from a topographical sheet.
    • Thinning of contours to single pixel contours.
    • Reconstruction of the broken contour lines.
    • Tracing the contours.
    • Extracting altitude attribute from the map for each contour.
    • Maintaining a database of the extracted contours.
    PROBLEM ANALYSIS
  • 5. LITERATURE SURVEY
    • Survey was conducted on different ways in which these methods have already been implemented.
    • Dongjun et.al [7] has suggested a method based on Generalized Gradient Vector Flow (GGVF) snake model to extract contour lines.
    • Zhou and Zhen [6] have proposed deformable model and field flow orientation method for extracting contour lines.
    • Leberl and Olson [1] have suggested a method that involves the entire four tasks mentioned above for automatic vectorization of clean contour lines.
    • Soille and Arrighi [3] have suggested image based approach using mathematical morphology operator to reconstruct contour lines.
  • 6.
    • Frischknecht [4] have used hierarchical template matching algorithm for extracting text but fails to extract contour lines.
    • Greenle [2] have made an attempt to extract elevation contour lines from topographic maps.
    • Zhang has proposed an efficient thinning algorithm which is widely used by many researchers in this area.
    • There exists many contour tracing algorithms - Square tracing, Moore neighbor, Radial sweep, Theo Pavlidis’ tracing algorithms.
    • Moore algorithm by far, provides the best method for tracing region boundaries.
    LITERATURE SURVEY – (CONTD…)
  • 7. EXTRACTION
    • Our primary aim is to scan a topographic sheet to produce a digital image.
    • We then extract contour lines from the topographic sheet.
    • Contour extraction from colored topographic sheets is done by extracting specific color values from the map.
    • In our case we scan individual RED, GREEN and BLUE components of an image. RGB components lying within a specific range are extracted and put on an blank image of same size.
  • 8. THINNING
    • Thinning is a process used in image processing to reduce multiple pixel width into single pixel width.
    • This process involves deletion of extra pixels in the neighborhood of the pixel without introducing any discontinuity in the connected components.
    • The thinning method used thins both the contour lines and the characters to their central lines with high speed.
    • This method is rotation invariant and preserves the topology of the contour lines and symbols.
    • It checks for the 8-neighborhood of the pixel into consideration and assigns the weight value to it.
    • The method maintains the connectivity of the contour lines.
  • 9. ALGORITHM Modified Moore’s neighbor algorithm Input : A square tessellation T containing a connected component P of black cells. Output : A sequence B(b 1 , b 2 , …, b k ) of boundary pixels i.e. the contour line. We define M(p) to be the Moore neighborhood of pixel p , c denotes the current pixel under consideration i.e. c is in M(p) . Begin Set B to be empty. From bottom to top and left to right scan the cells of T until a black pixel, s, of P is found. Insert s in B. Set the current boundary point, p, to s i.e. p = s. Set c to be the next clockwise pixel in M(p). While c is not in B do If c is black Insert c in B. Set p=c. End if Advance c to the next clockwise pixel in M(p). End while Set p=s. Set c to the next anticlockwise pixel in M(p). Repeat previous step with an anticlockwise scan each time in M(p). End.
  • 10. DESIGN METHODOLOGY
    • SOFTWARE REQUIREMENTS :
    • Language : MATLAB 7 or above
    • Platform : Windows XP/Vista
    •   HARDWARE REQUIREMENTS:
    • P-IV and above
    • 512 MB RAM
    • 120 GB HDD
  • 11. RESULT / OUTPUT Sample Topographic Sheet Contour Extraction from Sample Image
  • 12. Input image (before thinning) Output image (after thinning) THINNING
  • 13. Contour Tracing Method
  • 14. Contour Tracing Input Output From Contour Tracing
  • 15. DATABASE
  • 16.
    • The extraction of contour lines also includes many noise pixels which has been improved greatly.
    • Errors in extraction will lead to broken and intersecting lines.
    • The reconnection process of lines still has to be done manually.
    • Thinning was performed successfully to obtain single pixel width
    • lines with no errors.
    • The tracing of contours was performed successfully with
    • significant success.
    • The coordinate and altitude information were stored
    • successfully in the database.
    CONCLUSION
  • 17. REFERENCES
    • REFERENCES
    • [1] F. Leberl, D. Olson, “Raster scanning for operatioal digitizing of graphical data”, Photogrammetric Engineering and Remote Sensing, 48(4), pp. 615-627,1982.
    • [2] D. Greenle, “Raster and Vector Processing for Scanned line work”, Photogrammetric and Remote Sensing, 53(10), pp. 1383-1387, 1987.
    • [3] P. Soille, P Arrighi, “From Scanned Topographic Maps to Digital Elevation Models”, Proc. of Geovision, International Symposium on Imaging Appications in Geology, pp.1-4,1999.
    • [4] S. Frischknecht, E. Kanani, “Automatic Interpretation of Scanned Topographic Maps: A Raster – Based Approach”, Proc.Second International Workshop, GREC, pp.207-220, 1997.
    • [5] S. Salvatore, P. Guitton, “Contour Lines Recognition from Scanned Topographic Maps”, Journal of WSCG, pp. 1-3, 2004.
    • [6] X. Z. Zhou, H. L. Zhen, “Automatic vectorization of coNtour lines based on Deformable model and Field Flow Orirntation”, Chiense Journal of Computers,vol 8, pp. 1056-1063, 2004.
    • [7] Dongjum Xin, X. Z. Zhou, H.L.Zhen, “Contour Line Extraction from Paper- based Topographic Maps.
    • [8] G. Toussaint, Course Notes: Grids, connectivity and contour Tracing <http://jeff.cs.mcgill.ca/~godfried/teaching/pr-notes/contour.ps>.
    • [9] R.C.Gonzalez and R.E.Woods, Digital Image Processing. Prentice Hall, 2002.
    • [10] Bernd Jahne, Horst HauBecker, Computer Vision and Applications, 2000 by Academic Press.

×