TY - GEN
T1 - SHREC 2020 track
T2 - 2020 Eurographics Workshop on 3D Object Retrieval, EG 3DOR 2020
AU - Giachetti, A.
AU - Biasotti, S.
AU - Thompson, E. Moscoso
AU - Fraccarollo, L.
AU - Nguyen, Q.
AU - Nguyen, H.
AU - Tran, M.
AU - Arvanitis, G.
AU - Romanelis, I.
AU - Fotis, V.
AU - Moustakas, K.
AU - Tortorici, C.
AU - Werghi, N.
AU - Berretti, S.
N1 - Funding Information:
Learned features and Neural Networks haven’t been proposed, due to the small size of the dataset. However, it is possible to simulate the creation of piles of gravel with different granulometry using physical engines and use the results to learn ad-hoc descriptors for our task. We are going to generate simulated data to create novel benchmarks with a larger number of samples and training data for learning-based descriptors. Synthetic datasets will also be useful to test algorithms that could estimate the distribution of sizes of generic gravel mixtures. A tool providing an estimate of this distribution is the real goal of the research for hydrologists. The bench-mark proposed here is intended as a first step toward this goal. Acknowledgements This work has been partially supported by project MIUR Excellence Departments 2018-2022 and by the italian PRIN project Enterprising (2017SEB7Z8). We thank Dr. Eng. Andrea Polo for his help in the Lab.
Publisher Copyright:
© 2020 The Author(s) Eurographics Proceedings © 2020 The Eurographics Association.
PY - 2020
Y1 - 2020
N2 - The quantitative analysis of the distribution of the different types of sands, gravels and cobbles shaping river beds is a very important task performed by hydrologists to derive useful information on fluvial dynamics and related processes (e.g., hydraulic resistance, sediment transport and erosion, habitat suitability. As the methods currently employed in the practice to perform this evaluation are expensive and time-consuming, the development of fast and accurate methods able to provide a reasonable estimate of the gravel distribution based on images or 3D scanning data would be extremely useful to support hydrologists in their work. To evaluate the suitability of state-of-the-art geometry processing tool to estimate the distribution from digital surface data, we created, therefore, a dataset including real captures of riverbed mockups, designed a retrieval task on it and proposed them as a challenge of the 3D Shape Retrieval Contest (SHREC) 2020. In this paper, we discuss the results obtained by the methods proposed by the groups participating in the contest and baseline methods provided by the organizers. Retrieval methods have been compared using the precision-recall curves, nearest neighbor, first tier, second tier, normalized discounted cumulated gain and average dynamic recall. Results show the feasibility of gravels characterization from captured surfaces and issues in the discrimination of mixture of gravels of different size.
AB - The quantitative analysis of the distribution of the different types of sands, gravels and cobbles shaping river beds is a very important task performed by hydrologists to derive useful information on fluvial dynamics and related processes (e.g., hydraulic resistance, sediment transport and erosion, habitat suitability. As the methods currently employed in the practice to perform this evaluation are expensive and time-consuming, the development of fast and accurate methods able to provide a reasonable estimate of the gravel distribution based on images or 3D scanning data would be extremely useful to support hydrologists in their work. To evaluate the suitability of state-of-the-art geometry processing tool to estimate the distribution from digital surface data, we created, therefore, a dataset including real captures of riverbed mockups, designed a retrieval task on it and proposed them as a challenge of the 3D Shape Retrieval Contest (SHREC) 2020. In this paper, we discuss the results obtained by the methods proposed by the groups participating in the contest and baseline methods provided by the organizers. Retrieval methods have been compared using the precision-recall curves, nearest neighbor, first tier, second tier, normalized discounted cumulated gain and average dynamic recall. Results show the feasibility of gravels characterization from captured surfaces and issues in the discrimination of mixture of gravels of different size.
UR - https://www.scopus.com/pages/publications/85108557776
U2 - 10.2312/3dor.20201162
DO - 10.2312/3dor.20201162
M3 - Conference contribution
AN - SCOPUS:85108557776
T3 - Eurographics Workshop on 3D Object Retrieval, EG 3DOR
SP - 27
EP - 35
BT - EG 3DOR 2020 - Eurographics Workshop on 3D Object Retrieval, Short Papers
A2 - Schreck, Tobias
A2 - Theoharis, Theoharis
A2 - Theoharis, Theoharis
A2 - Pratikakis, Ioannis
A2 - Spagnuolo, Michela
A2 - Veltkamp, Remco
A2 - Fellner, Dieter W.
A2 - Hansmann, Werner
A2 - Purgathofer, Werner
A2 - Sillion, Francois
Y2 - 4 September 2020 through 5 September 2020
ER -