Search

Accurate underwater target detection is crucial for the operation of autonomous underwater vehicles (AUVs), enhancing their environmental awareness and target search and rescue capabilities. Current deep learning-based detection models are typically large, requiring substantial storage and computational resources. However, the limited space on AUVs poses significant challenges for deploying these models on the embedded processors. Therefore, research on model compression is of great practical importance, aiming to reduce model parameters and computational load without significantly sacrificing accuracy. To address the challenge of deploying large detection models, this paper introduces an automated pruning method based on dependency graphs and successfully implements efficient pruning on the YOLOv7 model. To mitigate the accuracy degradation caused by extensive pruning, we design a hybrid distillation method that combines output-based and feature-based distillation techniques, thereby improving the detection accuracy of the pruned model. Finally, we deploy the compressed model on an embedded processor within an AUV to evaluate its performance. Multiple experiments confirm the effectiveness of our proposed method in practical applications. [ABSTRACT FROM AUTHOR]

Underwater target detection technology plays a crucial role in the autonomous exploration of underwater vehicles. In recent years, significant progress has been made in the field of target detection through the application of artificial intelligence technology. Effectively applying AI techniques to underwater target detection is a highly promising area of research. However, the difficulty and high cost of underwater acoustic data collection have led to a severe lack of data, greatly restricting the development of deep-learning-based target detection methods. The present study is the first to utilize diffusion models for generating underwater acoustic data, thereby effectively addressing the issue of poor detection performance arising from the scarcity of underwater acoustic data. Firstly, we place iron cylinders and cones underwater (simulating small preset targets such as mines). Subsequently, we employ an autonomous underwater vehicle (AUV) equipped with side-scan sonar (SSS) to obtain underwater target data. The collected target data are augmented using the denoising diffusion probabilistic model (DDPM). Finally, the augmented data are used to train an improved YOLOv7 model, and its detection performance is evaluated on a test set. The results demonstrate the effectiveness of the proposed method in generating similar data and overcoming the challenge of limited training sample data. Compared to models trained solely on the original data, the model trained with augmented data shows a mean average precision (mAP) improvement of approximately 30% across various mainstream detection networks. Additionally, compared to the original model, the improved YOLOv7 model proposed in this study exhibits a 2% increase in mAP on the underwater dataset. [ABSTRACT FROM AUTHOR]

Autonomous underwater vehicles (AUVs) are extensively utilized in various autonomous underwater missions, encompassing ocean environment monitoring, underwater searching, and geological exploration. Owing to their profound underwater capabilities and robust autonomy, AUVs have emerged as indispensable instruments. Nevertheless, AUVs encounter several constraints in the domain of underwater navigation, primarily stemming from the cost-intensive nature of inertial navigation devices and Doppler velocity logs, which impede the acquisition of navigation data. Underwater simultaneous localization and mapping (SLAM) techniques, along with other navigation approaches reliant on perceptual sensors like vision and sonar, are employed to augment the precision of self-positioning. Particularly within the realm of machine learning, the utilization of extensive datasets for training purposes plays a pivotal role in enhancing algorithmic performance. However, it is common for data obtained exclusively from inertial sensors, a Doppler Velocity Log (DVL), and depth sensors in underwater environments to not be publicly accessible. This research paper introduces an underwater navigation dataset derived from a controllable AUV that is equipped with high-precision fiber-optic inertial sensors, a DVL, and depth sensors. The dataset underwent rigorous testing through numerical calculations and optimization-based algorithms, with the evaluation of various algorithms being based on both the actual surfacing position and the calculated position. [ABSTRACT FROM AUTHOR]

Underwater sensing and detection still rely heavily on acoustic equipment, known as sonar. As an imaging sonar, side-scan sonar can present a specific underwater situation in images, so the application scenario is comprehensive. However, the definition of side scan sonar is low; many objects are in the picture, and the scale is enormous. Therefore, the traditional image segmentation method is not practical. In addition, data acquisition is challenging, and the sample size is insufficient. To solve these problems, we design a semantic segmentation model of side-scan sonar images based on a convolutional neural network, which is used to realize the semantic segmentation of side-scan sonar images with few training samples. The model uses a large convolution kernel to extract large-scale features, adds a parallel channel using a small convolution kernel to obtain multi-scale features, and uses SE-block to focus on the weight of different channels. Finally, we verify the effect of the model on the self-collected side-scan sonar dataset. Experimental results show that, compared with the traditional lightweight semantic segmentation network, the model's performance is improved, and the number of parameters is relatively small, which is easy to transplant to AUV. [ABSTRACT FROM AUTHOR]

SLAM (Simultaneous Localization And Mapping) plays a vital role in navigation tasks of AUV (Autonomous Underwater Vehicle). However, due to a vast amount of image sonar data and some acoustic equipment's inherent high latency, it is a considerable challenge to implement real-time underwater SLAM on a small AUV. This paper presents a filter based methodology for SLAM algorithms in underwater environments. First, a multi-beam forward looking sonar (MFLS) is utilized to extract environmental features. The acquired sonar image is then converted to sparse point cloud format through threshold segmentation and distance-constrained filtering to solve the calculation explosion issue caused by a large amount of original data. Second, based on the proposed method, the DVL, IMU, and sonar data are fused, the Rao-Blackwellized particle filter (RBPF)-based SLAM method is used to estimate AUV pose and generate an occupancy grid map. To verify the proposed algorithm, the underwater vehicle is equipped as an experimental platform to conduct field tasks in both the experimental pool and wild lake, respectively. Experiments illustrate that the proposed approach achieves better performance in both state estimation and suppressing divergence. [ABSTRACT FROM AUTHOR]