Sea Turtle Detection Using Faster R-CNN for Conservation Purpose

  • Mohamed Badawy
  • Cem DirekogluEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1095)


Automatically monitoring see turtles over extensive coastlines is an important task for environmental research and conservation nowadays. Unfortunately, some of the sea turtle species have become endangered today and this is why there is a need for search-and-rescue. Computer vision algorithms can be used for sea turtle detection and monitoring. Recently, due to the powerful Convolutional Neural Networks (CNNs), computer vision crucial applications came to reality. Although such algorithms are computationally expensive, they have proved promising results where real-time applications can be feasibly implemented given high-capability GPUs. In this paper, we present a system of sea turtles detection using a Faster R-CNN algorithm. This system performs the sea turtles’ detection on a cloud (off-board). Our detection algorithm can be performed using a static camera, or a moving camera that is mounted on UAVs for surveillance, search-and-rescue purposes.


Computer vision Object detection Sea turtles Faster R-CNN 



This work is sponsored by Cyprus Wildlife Research Institute (CWRI). Our project team would like to acknowledge CWRI for supporting us to buy the hardware components required in the project. We also would like to thank Chantal Kohl and Stefanie Kramer from Humboldt University for supplying us some sea turtle images and videos for experimentation in our project. This project has been implemented on a server which belongs to Hossam Ahmed and Mohamed Badawy, we would like to thank them as well.


  1. 1.
    Erhan, D., Szegedy, C., Toshev, A., Anguelov, D.: Scalable object detection using deep neural networks. In: CVPR14 Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2155–2162 (2014)Google Scholar
  2. 2.
    Girshick, R.: Fast R-CNN. (2015)
  3. 3. ImageNet Tree View. Accessed 11 June 2019
  4. 4.
    Lee, J., Wang, J., Crandall, D.J., Sabanovic, S., Fox, G.C.: Real-time, cloud-based object detection for unmanned aerial vehicles. In: 2017 First IEEE International Conference on Robotic Computing (IRC), pp. 36–43 (2017)Google Scholar
  5. 5.
    Abadi, M., Agarwal, A., et al.: Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv:1603.04467 (2016)
  6. 6.
    Gao, H.: Faster R-CNN explained. Accessed 3 Jan 2019
  7. 7.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. (2016)
  8. 8.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. (2016)
  9. 9.
    Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. (2014)
  10. 10.
    Szegedy, C., Reed, S., Erhan, D., Anguelov, D.: Scalable, high-quality object detection. (2015)
  11. 11.
    Tzutalin LabelImg: Git code. (2015)
  12. 12.
    Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S.: SSD single shot multibox detector. (2016)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Center for Sustainability, Department of Electrical and Electronics EngineeringMiddle East Technical University - Northern Cyprus CampusKalkanli, GuzelyurtTurkey

Personalised recommendations