Description of field of research:

Rip Currents are contributing around 25 fatal drownings each year in Australia. Previous research has indicated that most of beachgoers cannot correctly identify a rip current, leaving them at risk of experiencing a drowning incident. Automated detection of rip currents could help to reduce drownings and assist lifeguards in supervision planning; however,  varying beach conditions have made this challenging. This work will develop an efficient, lightweight few-shot learning framework via contrastive proposal encoding. Due to the transformation invariant nature of the proposed approach, it may help to boost the rip detection for rare images.


Computer Science and Engineering

Research areas

Computer Vision, Object Detection

The main contact will be the supervisor (Imran Razzak), but day-to-day supervision will also be provided by Ph.D. students. Students are expected to skillful in Deep Learning, Object Detection. 

  • Shallow Rip Currents Detection Framework for efficient  rip current detection. 
  • Research Publication
  • Earlier study for ARC Linkage application
  • de Silva, A., Mori, I., Dusek, G., Davis, J. and Pang, A., 2021. Automated rip current detection with region based convolutional neural networks. Coastal Engineering, 166, p.103859.
  • Rashid, Ashraf Haroon, Imran Razzak, Muhammad Tanveer, and Antonio Robles-Kelly. ""Ripnet: A lightweight one-class deep neural network for the identification of rip currents."" In International Conference on Neural Information Processing, pp. 172-179. Springer, Cham, 2020.
  • Sun, B., Li, B., Cai, S., Yuan, Y. and Zhang, C., 2021. Fsce: Few-shot object detection via contrastive proposal encoding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7352-7362).
  • Rashid, A.H., Razzak, I., Tanveer, M. and Robles-Kelly, A., 2021, July. RipDet: A Fast and Lightweight Deep Neural Network for Rip Currents Detection. In 2021 International Joint Conference on Neural Networks (IJCNN) (pp. 1-6). IEEE.
  • Sšez, Francisco J., Patricio A. Catalan, and Carlos Valle. ""Wave-by-wave nearshore wave breaking identification using U-Net."" Coastal Engineering 170 (2021): 104021.