Stereo Vision System for Vision-Based Control of Inspection-Class ROVs

The inspection-class Remotely Operated Vehicles (ROVs) are crucial in underwater inspections. Their prime function is to allow the replacing of humans during risky subaquatic operations. These vehicles gather videos from underwater scenes that are sent online to a human operator who provides control. Furthermore, these videos are used for analysis. This demands an RGB camera operating at a close distance to the observed objects. Thus, to obtain a detailed depiction, the vehicle should move with a constant speed and a measured distance from the bottom. As very few inspection-class ROVs possess navigation systems that facilitate these requirements, this study had the objective of designing a vision-based control method to compensate for this limitation. To this end, a stereo vision system and image-feature matching and tracking techniques were employed. As these tasks are challenging in the underwater environment, we carried out analyses aimed at finding fast and reliable image-processing techniques. The analyses, through a sequence of experiments designed to test effectiveness, were carried out in a swimming pool using a VideoRay Pro 4 vehicle. The results indicate that the method under consideration enables automatic control of the vehicle, given that the image features are present in stereo-pair images as well as in consecutive frames captured by the left camera.

Download Full-text

FPGA-Based Stereo Vision System Using Gradient Feature Correspondence

Journal of Robotics and Mechatronics ◽

10.20965/jrm.2015.p0681 ◽

2015 ◽

Vol 27 (6) ◽

pp. 681-690 ◽

Cited By ~ 1

Author(s):

Hayato Hagiwara ◽

◽

Yasufumi Touma ◽

Kenichi Asami ◽

Mochimitsu Komori

Keyword(s):

Mobile Robot ◽

Stereo Vision ◽

Vision System ◽

Image Feature ◽

Interest Point ◽

Feature Correspondence ◽

Speeded Up Robust Features ◽

Stereo Vision System ◽

Simpler Algorithm ◽

Gradient Feature

<div class=""abs_img""><img src=""[disp_template_path]/JRM/abst-image/00270006/10.jpg"" width=""300"" /> Mobile robot with a stereo vision</div>This paper describes an autonomous mobile robot stereo vision system that uses gradient feature correspondence and local image feature computation on a field programmable gate array (FPGA). Among several studies on interest point detectors and descriptors for having a mobile robot navigate are the Harris operator and scale-invariant feature transform (SIFT). Most of these require heavy computation, however, and using them may burden some computers. Our purpose here is to present an interest point detector and a descriptor suitable for FPGA implementation. Results show that a detector using gradient variance inspection performs faster than SIFT or speeded-up robust features (SURF), and is more robust against illumination changes than any other method compared in this study. A descriptor with a hierarchical gradient structure has a simpler algorithm than SIFT and SURF descriptors, and the result of stereo matching achieves better performance than SIFT or SURF.

Download Full-text

Target Identification and Location Algorithm Based on SURF-BRISK Operator

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001416550168 ◽

2016 ◽

Vol 30 (06) ◽

pp. 1655016 ◽

Cited By ~ 3

Author(s):

Qiong Liu ◽

JiZhuang Hui ◽

Li Luo ◽

YanPu Yang

Keyword(s):

Stereo Vision ◽

Feature Matching ◽

Hamming Distance ◽

Target Identification ◽

Vision System ◽

Three Dimensional ◽

Image Feature ◽

Geometric Distortion ◽

Work Piece ◽

Target Image

Accurate and fast target image recognition is an important function of applications such as remote sensing imaging and medical imaging. However, an operator such as speeded up robust feature (SURF) cannot be accurately matched in the recognition process of a target image. This led us to propose the use of a method capable of matching identification, i.e. binary robust invariant scalable keypoints (BRISK) operators, in combination with SURF operators. The proposed algorithm combines the accuracy of SURF operators and the rapidity of BRISK operators to obtain a quick and accurate way of matching. The initial matching of image feature extraction for targets is performed using the SURF-BRISK algorithm, and similarity measurements of feature matching are performed for the feature points of initial matching using the Hamming distance. Then, secondary fine matching is performed using the M-estimator Sample and Consensus (MSAC) algorithm to eliminate mismatched point pairs in order to achieve recognition of target images. Then, the three-dimensional coordinates of the work piece are obtained by using a binocular stereo vision system to provide location coordinates for the robots to grasp the work pieces accurately. In the experiment, stereo vision matching is conducted for targets obtained using the SURF-BRISK algorithm, and the location coordinates of targets are passed to the robot controller. The experimental results show that if the special geometric distortion is neglected, this method can be adapted for accurate positioning of the target; hence, it can identify the target in complex environments, access the location coordinates of the target, and achieve accurate robotic grasping of the work piece in real time.

Download Full-text