Large-Scale Habitat Mapping Using Vision-Based AUVs: Experiences, Challenges &amp; Vehicle Design

Dunbabin, Matthew; Allen, Simon

doi:10.1109/oceanse.2007.4302309

Cited by 9 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inspection package includes a video camera (Inspector, zoom 12:1) mounted on a pan and tilt unit (Imenco) and 600 W of light sources (DSP&L). The navigation package includes a Doppler Velocity Log (Argonaut/Sontek), an Inertial Unit (HG1700 /Honeywell), a Digital Compass (TCM2/PNI) and acoustic beacons (20)(21)(22)(23)(24)(25)(26)(27)(28)(29)(30).…”

Section: Resultsmentioning

confidence: 99%

“…At this speed, Isurus is capable of operating for about 12 hours. The maximum operating depth is 200 m. For navigation, Isurus uses a PNI TCM2 digital compass and Long BaseLine (LBL) acoustic beacons (20)(21)(22)(23)(24)(25)(26)(27)(28)(29)(30). In the standard configuration, Isurus is equipped with an Ocean Sensors 200 CTD sensor, a Wet Labs optical backscatter sensor, a Marine Sonics side scan sonar and an Imagenex altimeter.…”

Section: Resultsmentioning

confidence: 99%

“…There are many examples of surveying problems [47,20]. Surveys with adaptive sampling are described in [30] and algorithms for uses such as bathymetry are shown in [48].…”

Section: 1mentioning

confidence: 99%

See 2 more Smart Citations

Sensor systems on networked vehicles

Sousa¹,

Maciel²,

Pereira³

2009

Networks &Amp; Heterogeneous Media

View full text Add to dashboard Cite

The future role of networked unmanned vehicles in advanced field studies is discussed in light of the recent technological advances and trends. Visions for systems which could have not been designed before are contrasted to the legal, technological and societal challenges facing the deployment of these systems. The discussion is illustrated with examples of developments from the Underwater Systems and Technologies Laboratory (LSTS) from Porto University.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Sensor systems on networked vehicles

Sousa¹,

Maciel²,

Pereira³

2009

Networks &Amp; Heterogeneous Media

View full text Add to dashboard Cite

show abstract

“…To initiate the search, the AUV travels to the expected target location using the mission primitives and navigation strategies described in Dunbabin and Allen (2007). Once within a prespecified radius of the expected target location (typically 1.5-m GPS error), it begins a search routine as described above to locate the SSL target using the proposed method.…”

Section: Field Experimentsmentioning

confidence: 99%

Robust vision‐based underwater homing using self‐similar landmarks

Nègre

Pradalier

Dunbabin

2008

Journal of Field Robotics

View full text Add to dashboard Cite

Next-generation autonomous underwater vehicles (AUVs) will be required to robustly identify underwater targets for tasks such as inspection, localization, and docking. Given their often unstructured operating environments, vision offers enormous potential in underwater navigation over more traditional methods; however, reliable target segmentation often plagues these systems. This paper addresses robust vision-based target recognition by presenting a novel scale and rotationally invariant target design and recognition routine based on self-similar landmarks that enables robust target pose estimation with respect to a single camera. These algorithms are applied to an AUV with controllers developed for vision-based docking with the target. Experimental results show that the system performs exceptionally on limited processing power and demonstrates how the combined vision and controller system enables robust target identification and docking in a variety of operating conditions. C 2008 Wiley Periodicals, Inc.

show abstract

“…They can obtain three dimensional environments. Therefore they can derive sensor attitudes relative to the terrains if any types of seafloor maps are acquired in advance using a shape matching as in [1], which is similar to video image based methods as in [2] and [3]. If the attitudes derived from the imaging sonars show enough accuracies to utilize for a vehicle control and other services, it can be said that they have the potential to serve for attitude sensors.…”

Section: Introductionmentioning

confidence: 99%

Rotation estimation from noisy sonar images and distortion corrections for nonlinearities

Shiba

2009

Oceans 2009-Europe

View full text Add to dashboard Cite

In the previous conference a new vehicle attitude estimation method was proposed using imaging sonars with Hough transformation for noisy sonar images. The method estimates onboard sonar attitude parameters from the location of the reference plane in the sonar image. In this paper a new rotation parameter estimation is introduced using these attitude parameter time variations. It does not require the Hough transformation, hence it is useful for smaller and lighter ocean observing platforms. After summarizing the attitude estimation based on the Hough transformation, the new procedure is explained referring its coordinate system which is one of the most significant features of the method. Moreover three distortions found in the attitude estimation are discussed and suppression procedures are presented.

show abstract

Large-Scale Habitat Mapping Using Vision-Based AUVs: Experiences, Challenges & Vehicle Design

Cited by 9 publications

References 12 publications

Sensor systems on networked vehicles

Sensor systems on networked vehicles

Robust vision‐based underwater homing using self‐similar landmarks

Rotation estimation from noisy sonar images and distortion corrections for nonlinearities

Contact Info

Product

Resources

About