Auv/rov Pose and Shape Estimation of Tethered Targets without Fiducials
نویسندگان
چکیده
This paper presents an algorithm (SPEAR) for visually estimating the pose and shape of an underwater target without fiducials. The goal is to enable AUV/ROV stationkeeping with respect to targets about which nothing is known a priori. It will also enable relative positioning with respect to any face on the 3-D body. It uses a particle filter to simultaneously track the pose and reconstruct a 3-D point cloud model of the target, based on concepts from the SLAM community (in particular, the FastSLAM algorithm [1], [2]). The algorithm for target estimation is explained and applied to the case of monocular sensing. Results are given showing successful estimation of an underwater target’s pose along with the 3-D locations of features on the body, based on experiments conducted in Monterey Bay, California with the ROV Ventana and a tethered underwater target.
منابع مشابه
Remotely Operated Vehicles and Autonomous Surface Vehicles in Auv Operations
Transferring data between the ocean surface and an operating Autonomous Underwater Vehicle (AUV) is a difficult and slow process. Current methods of un-tethered submersible communication have either a very limited data transfer rate or a prohibitively short range. In this paper, students of the University of Florida propose a new data transfer method that will supply the high data rates of a te...
متن کاملComparison of Different Targets Used in Augmented Reality Applications in Ubiquitous GIS
Drilling requires accurate information about locations of underground infrastructures or it can cause serious damages. Augmented Reality (AR) as a technology in Ubiquitous GIS (UBIGIS) can be used to visualize underground infrastructures on smartphones. Since smartphone’s sensors do not provide such accuracy, another approaches should be applied. Vision based computer vision systems are well kn...
متن کاملRelative Pose Estimation and Fusion of Omnidirectional and Lidar Cameras
This paper presents a novel approach for the extrinsic parameter estimation of omnidirectional cameras with respect to a 3D Lidar coordinate frame. The method works without specific setup and calibration targets, using only a pair of 2D-3D data. Pose estimation is formulated as a 2D-3D nonlinear shape registration task which is solved without point correspondences or complex similarity metrics....
متن کاملHybrid Camera Pose Estimation Combining Square Fiducials Localization Technique and Orthogonal Iteration Algorithm
متن کامل
Hybrid camera pose estimation combining square fiducials localisation technique and orthogonal iteration algorithm
Camera pose estimation from video images is a fundamental problem in machine vision and Augmented Reality (AR) systems. Most developed solutions are either linear for both n points and n lines, or iterative depending on nonlinear optimization of some geometric constraints. In this paper, we first survey several existing methods and compare their performances in an AR context. Then, we present a...
متن کامل