Visual Discrimination and Large Area Mapping of Posidonia Oceanica Using a Lightweight AUV

Bonin‐Font, Francisco; Burguera, Antoni; Lisani, José Luis

doi:10.1109/access.2017.2764998

Cited by 40 publications

(30 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Both mosaics were built with the same key frames used in the SLAM processes and Binary descriptor-based Image Mosaicing (BIMOS) [50]. BIMOS-related references [50][51][52] already showed the good performance of this mosaic approach in terms of accuracy and execution time and of application in underwater environments with seagrass (see Bonin-Font et al [51]). Consequently, its assessment is out of the scope of this paper.…”

Section: Multi-session Slammentioning

confidence: 99%

A Trajectory-Based Approach to Multi-Session Underwater Visual SLAM Using Global Image Signatures

Burguera

Bonin‐Font

2019

JMSE

Self Cite

View full text Add to dashboard Cite

This paper presents a multi-session monocular Simultaneous Localization and Mapping (SLAM) approach focused on underwater environments. The system is composed of three main blocks: a visual odometer, a loop detector, and an optimizer. Single session loop closings are found by means of feature matching and Random Sample Consensus (RANSAC) within a search region. Multi-session loop closings are found by comparing hash-based global image signatures. The optimizer refines the trajectories and joins the different maps. Map joining preserves the trajectory structure by adding a single link between the joined sessions, making it possible to aggregate or disaggregate sessions whenever is necessary. All the optimization processes can be delayed until a certain number of loops has been found in order to reduce the computational cost. Experiments conducted in real subsea scenarios show the quality and robustness of this proposal.

show abstract

Section: Multi-session Slammentioning

confidence: 99%

A Trajectory-Based Approach to Multi-Session Underwater Visual SLAM Using Global Image Signatures

Burguera

Bonin‐Font

2019

JMSE

Self Cite

View full text Add to dashboard Cite

show abstract

“…3) Comparison: In this section we present a comparison of the VGG16-FCN8 architecture with the classification meth-ods mentioned in Section I, the Burguera et al method [9] (henceforth ML-SVM) and the Gonzalez et al method [10] (henceforth CNN), as well as to other state-ofthe-art semantic segmentation architectures such as the U-Net [27] and the SegNet [28]. The performance comparison is conducted using the evaluation metrics defined in Section III-C2, which are obtained from the classification of the images pertaining to three test sets.…”

Section: B Hyperparameters and Model Selection 1) Hyperparameters Sementioning

confidence: 99%

Deep Semantic Segmentation in an AUV for Online Posidonia Oceanica Meadows Identification

et al. 2018

Self Cite

View full text Add to dashboard Cite

Recent studies have shown evidence of a significant decline of the Posidonia oceanica (P.O.) meadows on a global scale. The monitoring and mapping of these meadows are fundamental tools for measuring their status. We present an approach based on a deep neural network to automatically perform a high-precision semantic segmentation of P.O. meadows in sea-floor images, offering several improvements over the state of the art techniques. Our network demonstrates outstanding performance over diverse test sets, reaching a precision of 96.57% and an accuracy of 96.81%, surpassing the reliability of labelling the images manually. Also, the network is implemented in an Autonomous Underwater Vehicle (AUV), performing an online P.O. segmentation, which will be used to generate real-time semantic coverage maps.Francisco Bonin-Font received the degree in telecommunications engineering from the Polytechnical University of Catalonia, Barcelona, in 1996, and the Ph.D. degree in computer engineering from the University of the Balearic Islands in 2012. He has been ten years with the industry of information technology services addressed to bank business, before he initiated his academic activities. He has participated as a Technician and a Researcher in nine projects

show abstract

“…Compared with other underwater vehicles that can be explored, such as manned ships, and float platforms, AUVs have numerous advantages such as underwater payload capacity, maneuverability, and depth of activity despite their high cost and short battery life. In a variety of marine technologies, autonomous underwater vehicles (AUVs) can be used for comprehensive surveys and studies in areas where the depth cannot be reached by general diving technology; their ability to accomplish various missions have brought marine development into a new era [2].…”

Section: Introductionmentioning

confidence: 99%

Path Planning Technologies for Autonomous Underwater Vehicles-A Review

Li¹,

Wang²,

Du³

2019

IEEE Access

138

View full text Add to dashboard Cite

An autonomous underwater vehicle (AUV) is an economical and safe tool that is well-suited for search, investigation, identification, and salvage operations on the sea floor. Path planning technology, which primarily includes modeling methods and path search algorithms, is an important technology for AUVs. In recent years, the AUV path planning technology has rapidly developed. Compared with land robots, AUVs must endure complex underwater environments and consider various factors, such as currents, water pressure, and topography. Challenges exist in terms of online obstacle avoidance, three-dimensional environment path planning, and the robustness of the algorithms. Adapting a complex environment and finding a suitable path planning method comprise the main problem that must be solved. In this paper, we summarize the principles, advantages, and disadvantages of modeling and path search technologies for AUVs. The most prominent feature of this paper is to summarize the improvement methods of various technical shortcomings and improve the original methods, such as dynamic obstacle avoidance, optimization path, coverage, and processing speed. In addition to summarizing the characteristics of each algorithm, this paper intuitively demonstrates the experimental environment, the real-time nature, the path planning range of the AUV, and so on. We also discuss the application scenarios of various modeling and path search technologies for AUVs. In addition, we discuss the challenges of AUVs and the direction of future research. INDEX TERMS AUV, path planning, model building, path search.

show abstract

Visual Discrimination and Large Area Mapping of Posidonia Oceanica Using a Lightweight AUV

Cited by 40 publications

References 26 publications

A Trajectory-Based Approach to Multi-Session Underwater Visual SLAM Using Global Image Signatures

A Trajectory-Based Approach to Multi-Session Underwater Visual SLAM Using Global Image Signatures

Deep Semantic Segmentation in an AUV for Online Posidonia Oceanica Meadows Identification

Path Planning Technologies for Autonomous Underwater Vehicles-A Review

Contact Info

Product

Resources

About