scholarly journals Underwater Target Tracking Using Forward-Looking Sonar for Autonomous Underwater Vehicles

Sensors ◽  
2019 ◽  
Vol 20 (1) ◽  
pp. 102 ◽  
Author(s):  
Tiedong Zhang ◽  
Shuwei Liu ◽  
Xiao He ◽  
Hai Huang ◽  
Kangda Hao
Keyword(s):  
Target Tracking ◽  
Autonomous Underwater Vehicles ◽  
Region Growing ◽  
Underwater Vehicles ◽  
Generalized Regression Neural Network ◽  
Cluttered Environments ◽  
Online Processing ◽  
Underwater Target ◽  
Region Growing Segmentation ◽  
Forward Looking

In the scenario where autonomous underwater vehicles (AUVs) carry out tasks, it is necessary to reliably estimate underwater-moving-target positioning. While cameras often give low-precision visibility in a limited field of view, the forward-looking sonar is still an attractive method for underwater sensing, which is especially effective for long-range tracking. This paper describes an online processing framework based on forward-looking-sonar (FLS) images, and presents a novel tracking approach based on a Gaussian particle filter (GPF) to resolve persistent multiple-target tracking in cluttered environments. First, the character of acoustic-vision images is considered, and methods of median filtering and region-growing segmentation were modified to improve image-processing results. Second, a generalized regression neural network was adopted to evaluate multiple features of target regions, and a representation of feature subsets was created to improve tracking performance. Thus, an adaptive fusion strategy is introduced to integrate feature cues into the observation model, and the complete procedure of underwater target tracking based on GPF is displayed. Results obtained on a real acoustic-vision AUV platform during sea trials are shown and discussed. These showed that the proposed method is feasible and effective in tracking targets in complex underwater environments.

scholarly journals Clustering Cloud-Like Model-Based Targets Underwater Tracking for AUVs

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 370 ◽  
Author(s):  
Mingwei Sheng ◽  
Songqi Tang ◽  
Hongde Qin ◽  
Lei Wan
Keyword(s):  
Nearest Neighbor ◽  
Autonomous Underwater Vehicles ◽  
Data Association ◽  
Underwater Vehicles ◽  
Near Neighbor ◽  
Cluster Center ◽  
Model Data ◽  
Sea Trial ◽  
Underwater Target ◽  
Imaging Sonar

Autonomous underwater vehicles (AUVs) rely on a mechanically scanned imaging sonar that is fixedly mounted on AUVs for underwater target barrier-avoiding and tracking. When underwater targets cross or approach each other, AUVs sometimes fail to track, or follow the wrong target because of the incorrect association of the multi-target. Therefore, a tracking method adopting the cloud-like model data association algorithm is presented in order to track underwater multiple targets. The clustering cloud-like model (CCM) not only combines the fuzziness and randomness of the qualitative concept, but also achieves the conversion of the quantitative values. Additionally, the nearest neighbor algorithm is also involved in finding the cluster center paired to each target trajectory, and the hardware architecture of AUVs is proposed. A sea trial adopting a mechanically scanned imaging sonar fixedly mounted on an AUV is carried out in order to verify the effectiveness of the proposed algorithm. Experiment results demonstrate that compared with the joint probabilistic data association (JPDA) and near neighbor data association (NNDA) algorithms, the new algorithm has the characteristic of more accurate clustering.

Development of an ultra short baseline–aided buoy for underwater targets localization

2019 ◽  
Vol 233 (4) ◽  
pp. 1212-1225 ◽  
Author(s):  
Francesco Fanelli ◽  
Niccolò Monni ◽  
Nicola Palma ◽  
Alessandro Ridolfi
Keyword(s):  
Measurement Errors ◽  
Autonomous Underwater Vehicles ◽  
Dynamic Modelling ◽  
Experimental Tests ◽  
Underwater Vehicles ◽  
Short Baseline ◽  
Vehicle Localization ◽  
Positioning Systems ◽  
Fusion Methods ◽  
Underwater Target

Autonomous underwater vehicles localization and navigation are challenging due to the lack of Global Positioning System underwater: alternative techniques have then to be used in order to measure the position of the vehicle. To this aim, sensor fusion methods based on acoustic positioning systems are often exploited. This article faces the study and the improvement of the localization of an underwater target through an ultra short baseline–aided buoy built by the Mechatronics and Dynamic Modelling Laboratory of the University of Florence. Such a buoy relies on an ultra short baseline device for the localization and is aided by a proper sensor set in order to compensate variations in its pose. First, a study of the underwater localization based on the ultra short baseline technique is provided. The measurement errors entailed by the buoy motion are then analyzed and preliminarily compensated, exploiting linear least squares methods. Subsequently, filtering techniques are considered with the aim to further increase the accuracy of the ultra short baseline measurements. Due to the nonlinearities of the sensors characteristics, extended Kalman filter has been used, with different models for stationary and moving targets. The solutions proposed have been validated through experimental tests conducted with MArine Robotic Tool for Archaeology autonomous underwater vehicles built by the Mechatronics and Dynamic Modelling Laboratory. The results evidence an improved vehicle localization, suggesting interesting future developments concerning both mechanical and computational solutions.

scholarly journals Multiple Receptive Field Network (MRF-Net) for Autonomous Underwater Vehicle Fishing Net Detection Using Forward-Looking Sonar Images

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 1933
Author(s):  
Rixia Qin ◽  
Xiaohong Zhao ◽  
Wenbo Zhu ◽  
Qianqian Yang ◽  
Bo He ◽  
...  
Keyword(s):  
Receptive Field ◽  
Embedded System ◽  
Object Detection ◽  
Autonomous Underwater Vehicle ◽  
State Of The Art ◽  
Autonomous Underwater Vehicles ◽  
Underwater Vehicles ◽  
Field Network ◽  
Better Than ◽  
Forward Looking

Underwater fishing nets represent a danger faced by autonomous underwater vehicles (AUVs). To avoid irreparable damage to the AUV caused by fishing nets, the AUV needs to be able to identify and locate them autonomously and avoid them in advance. Whether the AUV can avoid fishing nets successfully depends on the accuracy and efficiency of detection. In this paper, we propose an object detection multiple receptive field network (MRF-Net), which is used to recognize and locate fishing nets using forward-looking sonar (FLS) images. The proposed architecture is a center-point-based detector, which uses a novel encoder-decoder structure to extract features and predict the center points and bounding box size. In addition, to reduce the interference of reverberation and speckle noises in the FLS image, we used a series of preprocessing operations to reduce the noises. We trained and tested the network with data collected in the sea using a Gemini 720i multi-beam forward-looking sonar and compared it with state-of-the-art networks for object detection. In order to further prove that our detector can be applied to the actual detection task, we also carried out the experiment of detecting and avoiding fishing nets in real-time in the sea with the embedded single board computer (SBC) module and the NVIDIA Jetson AGX Xavier embedded system of the AUV platform in our lab. The experimental results show that in terms of computational complexity, inference time, and prediction accuracy, MRF-Net is better than state-of-the-art networks. In addition, our fishing net avoidance experiment results indicate that the detection results of MRF-Net can support the accurate operation of the later obstacle avoidance algorithm.

scholarly journals Determination of Process Noise for Underwater Target Tracking with Forward Looking Sonar

2021 ◽  
Vol 13 (5) ◽  
pp. 1014
Author(s):  
Witold Kazimierski ◽  
Grzegorz Zaniewicz
Keyword(s):  
Theoretical Analysis ◽  
Target Tracking ◽  
Process Model ◽  
Specific Area ◽  
Measurement Model ◽  
Process Noise ◽  
Underwater Target ◽  
Definition Of ◽  
Empirical Experiment ◽  
Forward Looking

Target tracking is a process that provides information about targets in a specific area and is one of the key issues affecting the safety of any vehicle navigating in water. The main sensor used for underwater target tracking is sonar, with one of the most popular configurations being forward looking sonar (FLS). The target tracking state vector is usually estimated with the use of numerical filter algorithms, such as the Kalman filter (KF) and its modification, or the particle filter (PF). This requires the definition of a process model, including process noise, and a measurement model. This study focused on process noise definition. It is usually implemented as Gaussian noise, with a covariance matrix defined by the author. An analytical and empirical analysis was conducted, including a verification of the existing approaches and a survey of the published literature. Additionally, a theoretical analysis of the factors influencing process noise was conducted, which was followed by an empirical verification. The results were discussed, leading to the conclusions. The results of the theoretical analysis were confirmed by the empirical experiment and the results were compared with commonly used values of process noise in underwater target tracking processes.

Sign in / Sign up

Export Citation Format

Share Document