Real-time panoramic system for underwater cleaning robot

Jiang, Ping; Wei, Qianxiao; Chen, Yanhu; Yang, Canjun; Fan, Jinchang; Shou, Zhicheng; Huang, Zhengming

doi:10.1109/icmimt.2018.8340440

Cited by 2 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic panorama stitching based on SIFT image stitching [22][23][24]. This method has the advantage of using invariant features in the image to match the panoramic image sequence while the input image has uncertainties (e.g., rotation, scaling, and brightness changes).…”

Section: Feature-based Panoramic Image Stitchingmentioning

confidence: 99%

Artificial Intelligence Based Object Detection and Tracking for a Small Underwater Robot

Lee

Chen

2023

Processes

View full text Add to dashboard Cite

Object recognition and tracking is a challenge for underwater vehicles. Traditional algorithm requires a clear feature definition, which suffers from uncertainty as the variation of occlusion, illumination, season and viewpoints. A deep learning approach requires a large amount of training data, which suffers from the computation. The proposed method is to avoid the above drawbacks. The Siamese Region Proposal Network tracking algorithm using two weights sharing is applied to track the target in motion. The key point to overcome is the one-shot detection task when the object is unidentified. Various complex and uncertain environment scenarios are applied to evaluate the proposed system via the deep learning model’s predictions metrics (accuracy, precision, recall, P-R curve, F1 score). The tracking rate based on Siamese Region Proposal Network Algorithm is up to 180 FPS.

show abstract

Section: Feature-based Panoramic Image Stitchingmentioning

confidence: 99%

Artificial Intelligence Based Object Detection and Tracking for a Small Underwater Robot

Lee

Chen

2023

Processes

View full text Add to dashboard Cite

show abstract

“…The domestic research carried out in the field of cleaning marine steel piles started relatively late. At press, some universities have carried out relevant research, for example, CNOOC Energy Development Co. Ltd. And Yang Canjun's team [22][23][24] at Zhejiang University developed a cleaning robot called "HOME". HOME is composed of a four-wheel permanent magnet adsorption module and passive roll joint, which ensures the self-adaptive adjustment function.…”

Section: Introductionmentioning

confidence: 99%

Application of Multi-Cylinder Synchronous Control for Telescopic Mechanism of Marine Steel Pile Cleaning Equipment

Li¹,

Nan

et al. 2023

JMSE

View full text Add to dashboard Cite

In order to clean up marine fouling attached to marine steel pile, this paper proposed an innovative configuration scheme of the marine steel pile cleaning equipment by the scraping method and its telescopic mechanism by applying a multi-cylinder synchronous control strategy to the cleaning equipment, and produced a test prototype of the cleaning equipment that could solve the problem of cleaning equipment eccentricity and tilt in the field of ocean engineering. Based on the MATLAB Simulink module, a simulation model of the operation process of the telescopic mechanism of the marine steel pile cleaning equipment was established to complete the evaluation of the multi-cylinder synchronous control performance under multiple working conditions. Through the test, the synchronous working performance of the telescopic mechanism of the cleaning equipment under the no-load condition was preliminarily verified. The test results showed that under the no-load condition, the relative errors between the three cylinders and the target displacement were 0.8%, 0.4%, and 0.2%, respectively, and the cleaning equipment could reach the specified working position at the given working speed. The displacement synchronization error between each cylinder was 0.7 mm, 0.7 mm, and 0.6 mm, respectively, and the displacement synchronization error was controlled within 1 mm. The telescopic mechanism had good synchronization, which can ensure the stability and prevent the eccentricity and tilt during the cleaning equipment operation as well as provide a valuable reference for the manufacturing of cleaning equipment.

show abstract

Real-time panoramic system for underwater cleaning robot

Cited by 2 publications

References 24 publications

Artificial Intelligence Based Object Detection and Tracking for a Small Underwater Robot

Artificial Intelligence Based Object Detection and Tracking for a Small Underwater Robot

Application of Multi-Cylinder Synchronous Control for Telescopic Mechanism of Marine Steel Pile Cleaning Equipment

Contact Info

Product

Resources

About