International Journal of

Automation and Smart Technology

Jayson Piquero1*, Edwin Sybingco1, Alvin Chua2, Marc Say1, Clarisse Crespo1, Reginald Rivera1, Ma. Antonette Roque1, and Leonard Ambata1


 

1De La Salle University. Department of Electronics and Communications Engineering
2De La Salle University. Department of Mechanical Engineering

Download Citation: |
Download PDF


ABSTRACT


This paper introduces an approach to tree detection using mapped aerial images from drones. Tree detection is achieved by training a Faster Region-Based Convolutional Neural Network using Tensorflow Object Detection API. A Color-Based tree detector is also added to further filter out undesired detections such as tree shadows. Aerial images obtained from drones are mapped using Web Open Drone Map, an open-source drone mapping software. This paper aims to achieve a low-cost approach to disaster assessment using tree detection and drone images. The implemented system is able to detect trees and yielded an average detection rate accuracy of 85.63% and 95.14% for stitched maps and unstitched images respectively.


Keywords: drone, mapping, webodm, faster r-cnn


Share this article with your colleagues

 


REFERENCES


  1. [1] M. Mohan, C. Silva, C. Klauberg, P. Jat, G. Catts, A. Cardil, A. Hudak, and M. Dia, "Individual Tree Detection from Unmanned Aerial Vehicle (UAV) Derived Canopy Height Model in an Open Canopy Mixed Conifer Forest", 2017. https://doi.org/10.3390/f8090340

  2. [2] L. Ambata, A. Chavez, N. Devnani, J. Ingeniero, A. Paggabao, "LEAD: A LiDAR-based Three-Dimensional Mapping System for Environment and Object Detection on an Unmanned Aerial Vehicle", B.S. thesis, De La Salle University, Manila, Philippines, 2019. https://doi.org/10.1109/HNICEM48295.2019.9072891

  3. [3] W. Metzler, D. Pinson, A. Hendrickson, R. Xu, and J. Henriques, "Low-Cost Drone System for Analyzing Elevation", 2018. https://doi.org/10.1109/SIEDS.2018.8374732

  4. [4] J. Barnetson, S. Phinn, and P. Scarth, "Mapping woody vegetation cover across Australia's arid rangelands: Utilising a machine-learning classification and low- cost Remotely Piloted Aircraft System", 2019. https://doi.org/10.1016/j.jag.2019.101909

  5. [5] J. Cuevas, A. Chua, E. Sybingco, and E. Bakar, "Identification of River Hydromorphological Features Using Histograms of Oriented Gradients Cascaded to the Viola-Jones Algorithm", International Journal of Mechanical Engineering and Robotics Research Vol. 8, No. 2, March 2019. https://doi.org/10.18178/ijmerr

  6. [6] J. Cuevas, A. Chua, E. Sybingco, and E. Bakar, "Identification of river hydromorphological features using Viola-Jones Algorithm", 2016 IEEE Region 10 Conference (TENCON), 2016. https://doi.org/10.1109/TENCON.2016.7848439

  7. [7] E. Belyaev and S. Forchhammer, "Drone HDR Infrared Video Coding via Aerial Map Prediction", 2018. https://doi.org/10.1109/ICIP.2018.8451554

  8. [8] V. Delica, A. Orquia, J. Piquero, E. Reynaldo, J. Ilao, E. Sybingco, M. Roque, A. Chua, J. Katupitya, and H. Jayakody, "A New Sliding Mode Controller Implementation on an Autonomous Quadcopter System", International Journal of Automation and Smart Technology, vol. 9, no. 2, 2019. https://doi.org/10.5875/ausmt.v9i2.1876

  9. [9] I. Gue and A. Chua, "Development of a Fuzzy GS-PID Controlled Quadrotor for Payload Drop Missions", Journal of Telecommunication, Electronic and Computer Engineering, vol. 10, Issue 1-5, pp. 55-58, 2018.

  10. [10] C. Dim, F. Nabor, G. Santos, M. Schoeler, and A. Chua, "Novel Experiment Design for Unmanned Aerial Vehicle Controller Performance Testing", IOP Conference Series: Materials Science and Engineering, vol. 533, no. 1, 2019. https://doi.org/10.1088/1757-899X/533/1/012026

  11. [11] A. Asares, P. Ko, J. Minlay, B. Sarmiento, and A. Chua, "Design of an Unmanned Aerial Vehicle Blimp for Indoor Applications", International Journal of Mechanical Engineering and Robotics Research, vol. 8, no. 1, 2019, Pages 157-161. https://doi.org/10.18178/ijmerr.8.1.157-161

  12. [12] S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks", 2016. https://doi.org/10.1109/TPAMI.2016.2577031

  13. [13] J.R.R. Uijlings, K.E.A. van de Sande, T. Gevers, and A.W.M. Smeulders, "Selective Search for Object Recognition", 2012. https://doi.org/10.1007/s11263-013-0620-5

  14. [14] R. Girshick, "Fast R-CNN", 2015. https://doi.org/10.1109/ICCV.2015.169

  15. [15] E. Barbe, Aerial view of palm trees on a caribbean island with a white sand beach and turquoise water- Sint-Vincent and the Grenadines, n.d. [Online]. Available: https://stock.adobe.com/ca/images/aerial-view-of- palm-trees-on-a-caribbean-island-with-a-white- sand-beach-and-turquoise-water-sint-vincent-and-the-grenadines/208681208. [Accessed: 19-Aug-2019]

  16. [16] Altizure, Altizure android app quick start guide, 2016 [Online]. Available: https://www.youtube.com/watch?v=3IZ7DJYLxXc. [Accessed: 19-Aug-2019]

  17. [17] Drones Made Easy, Map Pilot for DJI, n.d. [Online]. Available: https://www.dronesmadeeasy.com/Articles.asp?ID=254. [Accessed: 19-Aug-2019]

  18. [18] Foxtech, How to make mapping waypoints in Mission Planner for Nimbus Mapping VTOL, 2018 [Online]. Available: https://www.youtube.com/watch?v=eMJbNZennM8. [Accessed: 19-Aug-2019]

  19. [19] C. Crespo, J. Paredes, J. Villamin, E. Sybingco, C. Llorente, A. Abad, M. Cabatuan, "Computer-based surveying system capable of human detection and head count with picture and location transfer from autonomous quadrotor", B.S. thesis, De La Salle University, Manila, Philippines, 2016.


ARTICLE INFORMATION


Received: 2019-08-23

Accepted: 2020-05-17
Available Online: 2021-07-01


Cite this article:

Jayson. P., Edwin. S., Alvin. C., Marc. S., Clarisse. C., Reginald. R., Ma. A.R. and Leonard. A. (2021) A Novel Automated Tree Detection System using Faster R-CNN. Int. j. autom. smart technol. https://doi.org/10.5875/ausmt.v11i1.2224

  Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.