Search

Underwater environment has a noisy medium and limited light source, so underwater vision has disadvantages of the limited detection range and the poor visibility. However it is still attractive in close range detections, especially for navigation. Thus, in this paper, vision-based object detection (template matching) and tracking (mean shift tracking) techniques for underwater robots using artificial objects have been studied. Also, we propose a novel weighted correlation coefficient using the feature-based and color-based approaches to enhance the performance of template matching in various illumination conditions. The average color information is incorporated into template matching using original and texturized images to robustly calculate correlation coefficients. And the objects are recognized using multiple template-based selection approach. Finally, the experiments in a test pool have been conducted to demonstrate the performance of the proposed techniques using an underwater robot platform yShark made by KORDI. [ABSTRACT FROM PUBLISHER]

This research describes a 3D reconstruction method of coral reefs using low-cost underwater cameras. We employed a multi-view camera system consisting of 3 identical waterproof cameras arrayed on a stereo-base, and collected footage of the seafloor in linear transects. To develop a 3D-representation of the seafloor image-pairs were first extracted from the video footage manually. Then corresponding points are automatically extracted from the stereo-pairs by the well known SIFT algorithm, which is invariant to scale, translation, and rotation. Based on the resultant x,y,z point cloud the 3D appearance of the coral reef is approximated by a Triangulation technique utilizing Delaunay Triangulation. The experimental result demonstrate robust 3D reconstruction with manual adjustment of camera A, B or C selection. [ABSTRACT FROM PUBLISHER]

The article discusses a study which analyzed the feasibility of a proposed technique of independently grasping a model-known object for an underwater vehicle-manipulator system (UVMS) through the use of a monocular vision. The other major techniques, like station keeping and grasping strategy, are also examined. It also presents the design of the vehicle controller and thrust allocation of the UVMS.

In this paper, we present a range sonar array based SLAM method for P-SURO AUV which is a test-bed for developing various underwater technologies. The vehicle's operating environment is a 12(L)x8(W)x6(D)m dimensional cuboid basin and its wall information is assumed to be known in priori. With this information, we propose an EKF (Extended Kalman Filter) SLAM method for the vehicle's operation in the basin. For range sonar, its measurement, in this paper, is modeled as a Gaussian distribution where the standard deviation is a function of sonar attack angle. Experimental studies are carried out to demonstrate the effectiveness of proposed SLAM method. [ABSTRACT FROM PUBLISHER]