An effective stereo SLAM with high-level primitives in underwater environment

Xu, Shuo; Ma, Teng; Li, Ye; Ding, Shuoshuo; Gao, Jingxuan; Xia, Jiahao; Qi, Haodong; Gu, Huanghe

doi:10.1088/1361-6501/ace645

Cited by 6 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xin et al [16] proposed an end-to-end network for SLAM preprocessing in an underwater low-light environment to achieve low-light image enhancement. Xu et al [17] integrated point features and object features to construct semantic landmarks. This proposed method can improve the performance of ORBSLAM2 in underwater scenarios.…”

Section: Vision-aided Navigationmentioning

confidence: 99%

A Low-Cost and High-Precision Underwater Integrated Navigation System

Liu,

Yu,

et al. 2024

JMSE

View full text Add to dashboard Cite

The traditional underwater integrated navigation system is based on an optical fiber gyroscope and Doppler Velocity Log, which is high-precision but also expensive, heavy, bulky and difficult to adapt to the development requirements of AUV swarm, intelligence and miniaturization. This paper proposes a low-cost, light-weight, small-volume and low-computation underwater integrated navigation system based on MEMS IMU/DVL/USBL. First, according to the motion formula of AUV, a five-dimensional state equation of the system was established, whose dimension was far less than that of the traditional. Second, the main source of error was considered. As the velocity observation value of the system, the velocity measured by DVL eliminated the scale error and lever arm error. As the position observation value of the system, the position measured by USBL eliminated the lever arm error. Third, to solve the issue of inconsistent observation frequencies between DVL and USBL, a sequential filter was proposed to update the extended Kalman filter. Finally, through selecting the sensor equipment and conducting two lake experiments with total voyages of 5.02 km and 3.2 km, respectively, the correctness and practicality of the system were confirmed by the results. By comparing the output of the integrated navigation system and the data of RTK GPS, the average position error was 4.12 m, the maximum position error was 8.53 m, the average velocity error was 0.027 m/s and the average yaw error was 1.41°, whose precision is as high as that of an optical fiber gyroscope and Doppler Velocity Log integrated navigation system, but the price is less than half of that. The experimental results show that the proposed underwater integrated navigation system could realize the high-precision and long-term navigation of AUV in the designated area, which had great potential for both military and civilian applications.

show abstract

Section: Vision-aided Navigationmentioning

confidence: 99%

A Low-Cost and High-Precision Underwater Integrated Navigation System

Liu,

Yu,

et al. 2024

JMSE

View full text Add to dashboard Cite

show abstract

“…Centers p 1 of the largest outer rectangles of hyperpixels are tracked by dense optical flow to obtain matching point pairs p 2 . Matched hyperpixels are identified based on p 2 coordinates, and depth residuals are calculated per hyperpixel with equation (12),…”

Section: Hyperpixel Segmentation and Fcm Clusteringmentioning

confidence: 99%

“…With the rapid development of artificial intelligence and robotics [1][2][3][4][5][6], simultaneous localization and mapping (SLAM) technology has become an important step toward intelligent and autonomous robot perception [7][8][9][10]. Currently, SLAM has been applied to many aspects of life, such as medical services, virtual/augmented reality, drones, and autonomous driving [11][12][13][14][15]. Among them, the sensors used in visual SLAM, which are relatively low-cost and have a wider range of applications, have received more and more attention in recent years, and a number of excellent visual SLAM (VSLAM) algorithms have appeared, such as ORB-SLAM2 [16], ORB-SLAM3 [17], DVO [18], etc, which have achieved excellent performance under laboratory conditions, among which ORB-SLAM 2 is able to achieve an absolute trajectory error (ATE) of about 0.015 m on the static RGB-D Technical University of Munich (TUM) dataset.…”

Section: Introductionmentioning

confidence: 99%

SFD-SLAM: a novel dynamic RGB-D SLAM based on saliency region detection

Gong,

Sun,

Zou

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

In dynamic environments, several SLAM systems effectively utilize optical flow fields to distinguish dynamic from static feature points. Commonly, these systems leverage the amplitude information within the optical flow field to develop adaptive thresholding segmentation models for identifying dynamic scene regions. Nevertheless, designing adaptive thresholding models typically necessitates meticulous planning and extensive experimentation. This study introduces a dynamic RGBD SLAM system, SFD-SLAM, which innovates by employing a saliency detection network for the direct extraction of dynamic regions via scene flow. This approach notably streamlines the design process associated with conventional adaptive thresholding models. Furthermore, SFD-SLAM incorporates a geometric module that merges depth residuals with hyperpixel segmentation to enhance the refinement of the dynamic mask. This is followed by integration with FCM clustering for the precise identification of moving objects. The efficacy of SFD-SLAM is assessed using the widely recognized TUM dynamic dataset. Experimental results demonstrate that the proposed system surpasses DGFlow-SLAM, which relies on an adaptive thresholding model for dynamic target segmentation, in terms of trajectory accuracy. It also achieves comparable localization accuracy to DynaSLAM. Moreover, SFD-SLAM maintains robust tracking capabilities, even in scenarios where DynaSLAM experiences tracking loss, thereby augmenting the robustness of RGBD-SLAM in dynamic settings.

show abstract

IFAL-SLAM: an approach to inertial-centered multi-sensor fusion, factor graph optimization, and adaptive Lagrangian method

Liu,

Qi,

Yuan

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

In response to the issues of low accuracy, perception degradation, and poor reliability of single-sensor SLAM technologies in complex environments, this study presents a novel IMU-centered multi-sensor fusion SLAM algorithm (IFAL-SLAM) integrating LiDAR, vision, and IMU, based on factor graph elimination optimization (\textbf{I}MU-centered multi-sensor \textbf{F}usion, \textbf{A}daptive \textbf{L}agrangian methods). The proposed system leverages a multi-factor graph model, centering on the IMU, and applies a covariance matrix to fuse visual-inertial and LiDAR-inertial odometries for bias correction, using loop closure factors for global adjustments. To minimize the optimization costs post-fusion, a sliding window mechanism is incorporated, coupled with a QR decomposition elimination method based on Householder transformation to convert the factor graph into a Bayesian network. Finally, an adaptive Lagrangian relaxation method is proposed, employing matrix-form penalty parameters and adaptive strategies to enhance convergence speed and robustness under high rotational dynamics.Experimental results indicate that the proposed algorithm achieves absolute trajectory errors of approximately 0.58 m and 0.24 m in large and small complex scenes, respectively, surpassing classic algorithms in terms of accuracy and reliability.

show abstract

An effective stereo SLAM with high-level primitives in underwater environment

Cited by 6 publications

References 45 publications

A Low-Cost and High-Precision Underwater Integrated Navigation System

A Low-Cost and High-Precision Underwater Integrated Navigation System

SFD-SLAM: a novel dynamic RGB-D SLAM based on saliency region detection

IFAL-SLAM: an approach to inertial-centered multi-sensor fusion, factor graph optimization, and adaptive Lagrangian method

Contact Info

Product

Resources

About