A review on the wavelet methods for sonar image segmentation

Abstract

The sonar image segmentation is needed such as in underwater object orientation and recognition, in collision prevention and navigation of underwater robots, in underwater investigation and rescue, in seafloor object seeking, in seafloor salvage, and in marine military affairs like torpedo detection. The wavelet-based methods have the ability of multiscale and multiresolution, and they are apt at edge detection and feature extraction of images. The applications of these methods to the sonar image segmentation are increasingly raised. The contents of the article are to classify the sonar image segmentation methods with wavelets and to describe main ideas, advantages, disadvantages, and conditions of use of every method. In the methods for sonar image region (or texture) segmentation, the thought of multiscale (or multiresolution) analysis of the wavelet transform is usually combined with other theories or methods such as the clustering algorithms, the Markov random field, co-occurrence matrix, Bayesian theory, and support vector machine. In the methods for sonar image edge detection, the space–frequency local characteristics of the wavelet transform are usually utilized. The wavelet packet-based and beyond wavelet-based methods can usually reach more precise segmentation. The article also gives 12 directions (or development trends predicted) of the sonar image segmentation methods with wavelets which should be researched deeply in the future. The aim of writing this review is to make the researchers engaged in sonar image segmentation learn about the research works in the field in a short time. Up to now, the similar reviews in this field have not been found.

Sonar image intelligent processing in seabed pipeline detection: review and application

“…In the field of investigation and detection of seabed pipelines, Tian et al proposed a high-resolution image texture segmentation algorithm based on wavelet transform and predicted twelve development trends in the image segmentation in the future [119]. Jiang and Zhou also introduced a back-propagation neural network to supervise the hidden details of the acoustic properties of seabed pipelines [120].…”

Malaria cell image classification by explainable artificial intelligence

“…Wang et al proposed an improved iris recognition method using wavelet packet and achieved remarkable results [24]. Tian et al showed the use of wavelet packets by segmenting sonar images [25]. Further, the use of wavelet packets can be found in deepfake image detection proposed by Wolter et al [26].…”

Advanced Autonomy for Uuv-Based Sas

“…Algorithms that perform this process, referred to as automated object recognition (AOR), encompass state-of-the-art techniques that include decluttering, denoising, object identification, advanced image processing, and more recently deep learning artificial neural networks (ANNs) (7)(8)(9)(10). Systems utilizing AOR have been shown to reduce operator workload while retaining accuracy, allowing for expedited mission completion and the potential to improve mission quality.…”