An Integrated Visual Odometry System With Stereo Camera for Unmanned Underwater Vehicles

Xu, Zhizun; Haroutunian, Maryam; Murphy, Alan J.; Neasham, Jeffrey; Norman, Rosemary

doi:10.1109/access.2022.3187032

Cited by 9 publications

(1 citation statement)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A fusion of acoustic DVL measurements and stereo imaging is offered in [14] for Simultaneous Localization And Mapping (SLAM) by formulating a joint utility function that also incorporates observations from a gyroscope and a depth sensor. In [15], a visual odometry system is proposes for underwater unmanned vehicles. The method filters out unreliable points from the 3D reconstruction of a scene provided by stereo cameras augmented by depth information from a single-beam sonar.…”

Section: State Of the Artmentioning

confidence: 99%

A Statistical Evaluation of the Connection between Underwater Optical and Acoustic Images

Chinicz,

Diamant

2024

Remote Sensing

View full text Add to dashboard Cite

The use of Synthetic Aperture Sonar (SAS) in autonomous underwater vehicle (AUV) surveys has found applications in archaeological searches, underwater mine detection and wildlife monitoring. However, the easy confusability of natural objects with the target object leads to high false positive rates. To improve detection, the combination of SAS and optical images has recently attracted attention. While SAS data provides a large-scale survey, optical information can help contextualize it. This combination creates the need to match multimodal, optical–acoustic image pairs. The two images are not aligned, and are taken from different angles of view and at different times. As a result, challenges such as the different resolution, scaling and posture of the two sensors need to be overcome. In this research, motivated by the information gain when using both modalities, we turn to statistical exploration for feature analysis to investigate the relationship between the two modalities. In particular, we propose an entropic method for recognizing matching multimodal images of the same object and investigate the probabilistic dependency between the images of the two modalities based on their conditional probabilities. The results on a real dataset of SAS and optical images of the same and different objects on the seafloor confirm our assumption that the conditional probability of SAS images is different from the marginal probability given an optical image, and show a favorable trade-off between detection and false alarm rate that is higher than current benchmarks. For reproducibility, we share our database.

show abstract

Section: State Of the Artmentioning

confidence: 99%