RipGAN: A GAN-Based Rip Current Data Augmentation Method

Rip currents are a major hazard on beaches worldwide, and their strong, offshore-directed currents can place even experienced beachgoers at risk of drowning. While it is intuitive to consider developing an automated rip current detection system to assist lifeguards in protecting beachgoers, rip current detection is in its infancy due to the lack of high-quality large-scale annotated rip current datasets. Also, the collection and annotation of rip current images require expert knowledge, which makes it more difficult to build datasets. So, this paper proposes a GAN-based rip current data augmentation method, RipGAN, to improve the performance of rip current detectors by increasing representative training data. To create new training images, RipGAN, has two branches. One is a texture generator that enriches the pattern and texture details of waves, making the image more realistic. The other is a rip generator based on FFFM-Unet. FFFM (Fast Fourier Fusion Module) uses Fast Fourier convolution to fuse the features from the low and the high layers, so as to further optimise the generated image. Furthermore, we trained Yolov8, YOLOv10, DINO and RT-DETR as rip current detectors to prove the effectiveness of RipGAN. The detectors' rnAP 50: 95 improved by 2. 67% on the test set and AP 50 by 4. 93% on real-scene videos, outperforming other data augmentation methods. Besides, abundant ablation studies have been conducted to further evaluate each component of RipGAN.

Authors

• Shenyang Qian
• Mitchell Harley
• Imran Razzak
• Yang Song 0001

Keywords

• Training
• Image resolution
• Convolution
• Training data
• Detectors
• Data augmentation
• Generators
• Hazards
• Robotics and automation
• Videos
• Data Augmentation Methods
• Fast Fourier
• Detection Performance
• Training Images
• Wave Pattern
• Image Annotation
• Fast Modulation
• Training Set
• Fast Fourier Transform
• Public Datasets
• Object Detection
• Image Object
• Intersection Over Union
• Bounding Box
• Kullback-Leibler
• Generative Adversarial Networks
• Synthetic Images
• Latent Code
• Synthetic Training Data
• Random Code
• Sobel Operator
• Conditional Generative Adversarial Network
• Realistic Images
• Intersection Over Union Threshold
• Average Precision
• Google Earth