A Real-Time Framework for Detection of Long Linear Infrastructural Objects in Aerial Imagery

  • Hrishikesh SharmaEmail author
  • Tanima Dutta
  • V. Adithya
  • P. Balamuralidhar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9164)


In any nation, many long linear infrastructures exist, which need to be periodically inspected for faults and subsequent maintenance. These include power grid, pipelines, railway corridor etc. Most of these infrastructures support critical utilities, and hence operated 24 x 7 throughout the year. The length of these infrastructures can be in tens of kilometers. Hence maintenance inspections via acquisition of aerial imagery is gaining popularity. Since such video can have thousands of frames, it is imperative that its analysis be automated. Such infrastructure detection is against a background that is quite heterogeneous and complex. In this paper, we propose an algorithmic framework that can be used for automatic, real-time detection of different linear infrastructural objects in outdoor aerial images. The five-stage algorithm focuses on minimization of false positives. The algorithm was tested against video data captured for two different power grids in outskirts of Bangalore. The results show seldom false positives, and false negatives in certain frames occur sparsely enough that we are able to do a continuous video tracking. We believe that this framework will be useful in real deployments as well.


Power Line Power Grid Linear Feature Seed Point Aerial Image 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



We thank Prof. Omkar and his research group from Dept. of Aerospace, Indian Institute of Science, Bangalore for collaborating and providing us with video data to test our algorithm.


  1. 1.
    Ceron, A., Mondragon, B., Prieto, F.: Power line detection using a circle based search with UAV images. In: International Conference on Unmanned Aircraft Systems, pp. 632–639 (2014)Google Scholar
  2. 2.
    Dutta, T., Sharma, H., Adithya, V., Balamurali, P.: Image analysis-based automatic detection of transmission towers using aerial imagery. In: 7th Iberian Conference on Pattern Recognition and Image Analysis. Springer Verlag (2015)Google Scholar
  3. 3.
    Ercal, F.: Image Processing Algorithms. Lecture Notes.
  4. 4.
    Lagerstrom, R., Sun, C., Pascal, V.: Boundary extraction of linear features using dual paths through gradient profiles. Elsevier J. Pat. Rec. Lett. 29(12), 1753–1757 (2008)CrossRefGoogle Scholar
  5. 5.
    Lebourgeois, F., Drira, F., Gaceb, D., Duong, J.: Fast Integral MeanShift: Application to Color Segmentation of Document Images. In: International Conference on Document Analysis and Recognition, pp. 52–56, August 2013Google Scholar
  6. 6.
    Li, Z., Liu, Y., Hayward, R., Zhang, J., Cai, J.: Knowledge-based power line detection for uav surveillance and inspection systems. In: IEEE International Conference on Image and Vision Computing (2008)Google Scholar
  7. 7.
    Luo, X., Zhang, J., Cao, X., Yan, P., Li, X.: Object-aware power line detection using color and near-infrared images. IEEE Trans. Aerosp. Electron. Syst. 50(2), 1374–1389 (2014)CrossRefGoogle Scholar
  8. 8.
    Mu, C., Yu, J., Feng, Y., Cai, J.: Power lines extraction from aerial images based on gabor filter. In: International Symposium on Spatial Analysis, Spatial-temporal Data Modeling, and Data Mining (2009)Google Scholar
  9. 9.
    Sargin, M., Altinok, A., Manjunath, B., Rose, K.: Variable length open contour tracking using a deformable trellis. IEEE Trans. Image Process. 20(4), 1023–1035 (2011)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Shao, Y., Guo, B., Hu, X., Di, L.: Application of a fast linear feature detector to road extraction from remotely sensed imagery. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 4(3), 626–631 (2011)CrossRefGoogle Scholar
  11. 11.
    Sharma, H., Bhujade, R., Adithya, V., Balamurali, P.: Vision-based Detection of Power Distribution Lines in Complex Remote Surroundings. In: National Conference on Communications, pp. 1–6 (February 2014)Google Scholar
  12. 12.
    Sonka, M., Winniford, M., Collins, S.M.: Robust simultaneous detection of coronary borders in complex images. IEEE Trans. Med. Imaging 14(1), 151–161 (1995)CrossRefGoogle Scholar
  13. 13.
    Sonka, M., Hlavac, V., Boyle, R.: Image Processing, Analysis, and Machine Vision. Thomson-Engineering, Birchmount Road, Toranto, Ontario, CA (2007)Google Scholar
  14. 14.
    Sun, C., Vallotton, P.: Fast linear feature detection using multiple directional non-maximum suppression. In: IEEE International Conference on Pattern Recognition, pp. 288–291 (2006)Google Scholar
  15. 15.
    Unnikrishnan, R., Pantofaru, C., Hebert, M.: Toward objective evaluation of image segmentation algorithms. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 929–944 (2007)CrossRefGoogle Scholar
  16. 16.
    Yan, G., Li, C., Zhou, G., Zhang, W., Li, X.: Automatic extraction of power lines from aerial images. IEEE Geosci. Remote Sens. Lett. 4(3), 387–391 (2007)CrossRefGoogle Scholar
  17. 17.
    Yang, T.W., Yin, H., Ruan, Q.Q., Han, J.D., Qi, J.T., Yong, Q., Wang, Z.T., Sun, Z.Q.: Overhead power line detection from uav video images. In: IEEE International Conference on Mechatronics and Machine Vision in Practice, pp. 74–79 (2012)Google Scholar
  18. 18.
    Zhang, J., Liu, L., Wang, B., Chen, X., Wang, Q., Zheng, T.: High speed automatic power line detection and tracking for a UAV-based inspection. In: IEEE International Conference on Industrial Control and Electronics Engineering, pp. 266–269 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Hrishikesh Sharma
    • 1
    Email author
  • Tanima Dutta
    • 2
  • V. Adithya
    • 1
  • P. Balamuralidhar
    • 1
  1. 1.TCS Innovation LabsBangaloreIndia
  2. 2.Department of Computer ScienceIIT IndoreIndoreIndia

Personalised recommendations