Redirigiendo al acceso original de articulo en 18 segundos...
ARTÍCULO
TITULO

On-Line Multi-Class Segmentation of Side-Scan Sonar Imagery Using an Autonomous Underwater Vehicle

Antoni Burguera and Francisco Bonin-Font    

Resumen

This paper proposes a method to perform on-line multi-class segmentation of Side-Scan Sonar acoustic images, thus being able to build a semantic map of the sea bottom usable to search loop candidates in a SLAM context. The proposal follows three main steps. First, the sonar data is pre-processed by means of acoustics based models. Second, the data is segmented thanks to a lightweight Convolutional Neural Network which is fed with acoustic swaths gathered within a temporal window. Third, the segmented swaths are fused into a consistent segmented image. The experiments, performed with real data gathered in coastal areas of Mallorca (Spain), explore all the possible configurations and show the validity of our proposal both in terms of segmentation quality, with per-class precisions and recalls surpassing the 90%, and in terms of computational speed, requiring less than a 7% of CPU time on a standard laptop computer. The fully documented source code, and some trained models and datasets are provided as part of this study.

 Artículos similares

       
 
Moli Chen, Xunkai Wei, Hao Wang and Zhenhe Jiang    
Compared to maximum state parameters, such as maximum altitude and Mach, the number of hovers and S turns can be used as process parameters representing the complexity of military aircraft maneuvers when classifying big flight mission data to compile fli... ver más
Revista: Applied Sciences

 
Pinyang Zhang and Changzheng Chen    
In the operation and maintenance of planetary gearboxes, the growth of monitoring data is often faster than its analysis and classification. Careful data analysis is generally considered to require more expertise. Rendering the machine learning algorithm... ver más
Revista: Applied Sciences

 
Robert ?upan, Adam Vinkovic, Rexhep Nikçi and Bernarda Pinjatela    
This research is primarily focused on utilizing available airborne LiDAR data and spatial data from the OpenStreetMap (OSM) database to generate 3D models of buildings for a large-scale urban area. The city center of Ljubljana, Slovenia, was selected for... ver más
Revista: Information

 
Jeong-Hyun Yoon, Dong-Ham Kim, Sang-Woong Yun, Hye-Jin Kim and Sewon Kim    
Container terminals are at the center of global logistics, and are highly dependent on the schedule of vessels arriving. Conventional ETA records from ships, utilized for terminal berth planning, lack sufficient accuracy for effective plan implementation... ver más

 
Rongsheng Zhu, Wenhao Shi, Gongchang Gan, Huairui Li, Dawei Yang, Yuchen Duan and Qiang Fu    
To investigate the transient characteristics of high-speed axial flow water-jet pumps during start-up and emergency acceleration as well as to analyze how different accelerations affect the performance of internal flow, the k?? turbulence model of the SS... ver más