Abstract
Acoustic seabed classification (ASC) is a fast and large-scale seabed sediment survey method. In particular, combining it with an automated classifier can theoretically achieve fast automatic seabed sediment classification. However, owing to the cost of sampling, a lack of labeled data for sediment classification based on seabed acoustic images impedes the training and deployment of classifiers. Herein, we use shallow-water, side-scan sonar images collected from the Pearl River Estuary combined with deep learning to study sediment classification and optimization methods for a small dataset of seabed acoustic images. In this paper, we applied different and deeper convolutional neural networks (CNNs) and used grayscale CIFAR-10 for pretraining to achieve large-span parameter migration and improve model performance. The best result in the experiment is a 3.459% error rate achieved by ResNet after fine tuning, verifying the improvement brought by our fine tuning strategy and the deeper models used in such tasks. The results of data enhancement based on generative adversarial networks (GANs) indicated that this method can improve the accuracy of sediment classification; however, the effects of GANs are limited and they are computationally expensive. Overall, our findings resolve, to an extent, the dilemma of using small datasets of seabed acoustic images for sediment classification and provide a framework for future studies on sediment classification, which has a certain significance in helping people better understand the seabed.
Highlights
Inspired by the great success of deep learning (DL) in computer vision and related fields, research on the applications of DL to underwater imaging has begun
The results of our experiments can be divided into two parts, based upon the goals: (1) optimization of convolutional neural networks (CNNs); (2) data enhancement based on DL
The configuration of the workstation we used in the experiments was as follows: the central processing unit (CPU) was an Intel Core-i9-9820X with a C422 motherboard (Intel Corp., USA), the memory was 32 GB, and the graphics processing unit (GPU) was a single GeForce RTX2080Ti (Nvidia Corp., USA)
Summary
Inspired by the great success of deep learning (DL) in computer vision and related fields, research on the applications of DL to underwater imaging has begun. There are two main types of underwater images—optical photographic images and acoustic images—which typically include underwater targets, seafloor topography, and seafloor sediments, among others. Seabed sediment classification is used to investigate the type and distribution of seabed sediments, which is of great significance to marine geology and related research. The traditional seabed sampling method is timeconsuming and expensive, and it is difficult to cover a large seabed area. An effective-cost method for seabed sediment classification is necessary.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have