ARTÍCULO
TITULO

Recognition and Tracking of an Underwater Pipeline from Stereo Images during AUV-Based Inspection

Valery Bobkov    
Antonina Shupikova and Alexander Inzartsev    

Resumen

The inspection of condition of underwater pipelines (UPs) based on autonomous underwater vehicles (AUVs) requires high accuracy of positioning while the AUV is moving along to the object being examined. Currently, acoustic, magnetometric, and visual means are used to detect and track UPs with AUVs. Compared to other methods, visual navigation can provide higher accuracy for local maneuvering at short distances to the object. According to the authors of the present article, the potential of video information for these purposes is not yet fully utilized, and, therefore, the study focused on the more efficient use of stereo images taken with an AUV?s video camera. For this, a new method has been developed to address inspection challenges, which consists in the highlighting of visible boundaries and the calculation of the UP centerline using algorithms for combined processing of 2D and 3D video data. Three techniques for initial recognition of the direction of UP upon its detection were analyzed: on the basis of a stereo-pair of images using point features of the surface; using tangent planes to the UP in one of the stereo-pair; and using the UP median planes in both images of the stereo-pair. Approaches for determining the parameters of the relative positions of the AUV and the UP during the subsequent tracking are also considered. The technology proposed can be of practical use in the development of navigation systems to be applied for UP inspection without deploying additional expensive equipment, either separately or in combination with measurements from other sensors.

 Artículos similares

       
 
Shuai Yang, Zhihui Zou, Yingchao Li, Haodong Shi and Qiang Fu    
To address the issue of poor tracking accuracy and the low recognition rate for multiple small targets in infrared images caused by uneven image intensity, this paper proposes an accurate tracking algorithm based on optical flow estimation. The algorithm... ver más
Revista: Applied Sciences

 
Xiao Xu, Xuehan Zhang, Zhongxu Bao, Xiaojie Yu, Yuqing Yin, Xu Yang and Qiang Niu    
Hand gesture recognition is an essential Human?Computer Interaction (HCI) mechanism for users to control smart devices. While traditional device-based methods support acceptable recognition performance, the recent advance in wireless sensing could enable... ver más
Revista: Applied Sciences

 
Jong-Shin Chen, Chun-Ming Kuo and Ruo-Wei Hung    
Many highly contagious infectious diseases, such as COVID-19, monkeypox, chickenpox, influenza, etc., have seriously affected or currently are seriously affecting human health, economic activities, education, sports, and leisure. Many people will be infe... ver más
Revista: Algorithms

 
Shijing Liu, Cheng Qian, Xueying Tu, Haojun Zheng, Lin Zhu, Huang Liu and Jun Chen    
Variable-condition fish recognition is a type of cross-scene and cross-camera fish re-identification (re-ID) technology. Due to the difference in the domain distribution of fish images collected under different culture conditions, the available training ... ver más

 
Junyi Yang, Yutong Yao and Donghe Yang    
Due to the complexity of the underwater environment, tracking underwater targets via traditional particle filters is a challenging task. To resolve the problem that the tracking accuracy of a traditional particle filter is low due to the sample impoveris... ver más