Bathymetric-Based Band Selection Method for Hyperspectral Underwater Target Detection

Band selection has imposed great impacts on hyperspectral image processing in recent years. Unfortunately, few existing methods are proposed for hyperspectral underwater target detection (HUTD). In this paper, a novel unsupervised band selection method is proposed for HUTD by embedding the bathymetric model into the band selection process. Considering the dependence between targets and background, a bathymetric latent spectral representation learning scheme is designed to investigate a physically meaningful subspace where the desired targets are the most distinguishable from the background. This calculated subspace is exploited as a reference to select out desired bands based on the spectral distance metric. Then, we propose an iteration-based band subset generation strategy for the sake of promoting the diversity of the band selection results and taking full advantage of the ample spectral information. Moreover, a representative band selection approach based on sparse representation is also conducted to eliminate the redundant information among adjacent bands. The band selection result is eventually achievable by connecting the representative bands of all the band subsets. Qualitative and quantitative evaluations demonstrate the effectiveness and efficiency of the proposed method in comparison with state-of-the-art band selection methods.

A Self-Improving Framework for Joint Depth Estimation and Underwater Target Detection from Hyperspectral Imagery

Underwater target detection (UTD) is one of the most attractive research topics in hyperspectral imagery (HSI) processing. Most of the existing methods are presented to predict the signatures of desired targets in an underwater context but ignore the depth information which is position-sensitive and contributes significantly to distinguishing the background and target pixels. So as to take full advantage of the depth information, in this paper a self-improving framework is proposed to perform joint depth estimation and underwater target detection, which exploits the depth information and detection results to alternately boost the final detection performance. However, it is difficult to calculate depth information under the interference of a water environment. To address this dilemma, the proposed framework, named self-improving underwater target detection framework (SUTDF), employs the spectral and spatial contextual information to pick out target-associated pixels as the guidance dataset for depth estimation work. Considering the incompleteness of the guidance dataset, an expectation-maximum liked updating scheme has also been developed to iteratively excavate the statistical and structural information from input HSI for further improving the diversity of the guidance dataset. During each updating epoch, the calculated depth information is used to yield a more diversified dataset for the target detection network, leading to a more accurate detection result. Meanwhile, the detection result will in turn contribute in detecting more target-associated pixels as the supplement for the guidance dataset, eventually promoting the capacity of the depth estimation network. With this specific self-improving framework, we can provide a more precise detection result for a hyperspectral UTD task. Qualitative and quantitative illustrations verify the effectiveness and efficiency of SUTDF in comparison with state-of-the-art underwater target detection methods.

Fuzzy target detection algorithm based on improved SSD and transfer learning

Fuzzy target detection as an important task to reflect the detection ability of underwater robot, the artificial target recognition based on the image taken by underwater robot has been widely concerned. However, there is no open standard fuzzy underwater image data set, and in the harsh deep-water fuzzy environment, it is difficult to collect large-scale marked underwater fuzzy optical images. At the same time, it is also hoped that the detection model has the ability to learn quickly from small samples in the case of as few samples as possible. Therefore, combining depth learning and transfer learning, a new method based on improved SSD and transfer learning is proposed. Firstly, we design a more accurate SSD network (underwater SSD) which is suitable for fuzzy underwater target detection. The features extracted from the detection network are highly representative. Secondly, we use the Transfer learning method to train the underwater SSD network, which can only use the tags in the air to identify fuzzy underwater objects, and have strong robustness in both the air and fuzzy underwater imaging modes. Finally, soft NMS is used to detect the target. The experimental results of the simulation data show that the algorithm not only overcomes the difficulties of the known data set of underwater target, but also effectively improves the accuracy of underwater target detection compared with the traditional deep learning method, reaching 82.31%, showing better detection performance.