Image and Signal Processing Methods

Assessing the transferability of a hybrid Taguchi-objective function method to optimize image segmentation for detecting and counting cave roosting birds using terrestrial laser scanning data

[+] Author Affiliations
Mohammed Oludare Idrees, Biswajeet Pradhan, Helmi Zulhaidi Mohd Shafri

University Putra Malaysia, Geospatial Information Science Research Center, Faculty of Engineering, Department of Civil Engineering, 43400 UPM Serdang, Selangor, Malaysia

Manfred F. Buchroithner

Dresden University of Technology, Institute of Cartography, Helmholtzstraße 10, 01062 Dresden, Germany

Siti Khairunniza Bejo

University Putra Malaysia, Faculty of Engineering, Department of Biological and Agricultural Engineering, 43400 UPM Serdang, Selangor, Malaysia

J. Appl. Remote Sens. 10(3), 035023 (Sep 16, 2016). doi:10.1117/1.JRS.10.035023
History: Received June 15, 2016; Accepted August 23, 2016
Text Size: A A A

Abstract.  As far back as early 15th century during the reign of the Ming Dynasty (1368 to 1634 AD), Gomantong cave in Sabah (Malaysia) has been known as one of the largest roosting sites for wrinkle-lipped bats (Chaerephon plicata) and swiftlet birds (Aerodramus maximus and Aerodramus fuciphagus) in very large colonies. Until recently, no study has been done to quantify or estimate the colony sizes of these inhabitants in spite of the grave danger posed to this avifauna by human activities and potential habitat loss to postspeleogenetic processes. This paper evaluates the transferability of a hybrid optimization image analysis-based method developed to detect and count cave roosting birds. The method utilizes high-resolution terrestrial laser scanning intensity image. First, segmentation parameters were optimized by integrating objective function and the statistical Taguchi methods. Thereafter, the optimized parameters were used as input into the segmentation and classification processes using two images selected from Simud Hitam (lower cave) and Simud Putih (upper cave) of the Gomantong cave. The result shows that the method is capable of detecting birds (and bats) from the image for accurate population censusing. A total number of 9998 swiftlet birds were counted from the first image while 1132 comprising of both bats and birds were obtained from the second image. Furthermore, the transferability evaluation yielded overall accuracies of 0.93 and 0.94 (area under receiver operating characteristic curve) for the first and second image, respectively, with p value of <0.0001 at 95% confidence level. The findings indicate that the method is not only efficient for the detection and counting cave birds for which it was developed for but also useful for counting bats; thus, it can be adopted in any cave.

Figures in this Article
© 2016 Society of Photo-Optical Instrumentation Engineers

Citation

Mohammed Oludare Idrees ; Biswajeet Pradhan ; Manfred F. Buchroithner ; Helmi Zulhaidi Mohd Shafri and Siti Khairunniza Bejo
"Assessing the transferability of a hybrid Taguchi-objective function method to optimize image segmentation for detecting and counting cave roosting birds using terrestrial laser scanning data", J. Appl. Remote Sens. 10(3), 035023 (Sep 16, 2016). ; http://dx.doi.org/10.1117/1.JRS.10.035023


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.