Pasar al contenido principal

CADENA COMPLETA DE PROCESAMIENTO MULTI-IMAGEN Y VIDEO

TIN2017-85572-P

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de Fomento de la Investigación Científica y Técnica de Excelencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D (Excelencia / Generación de Conocimiento)
Año convocatoria 2017
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE LAS ISLAS BALEARES

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

Repositori Institucional UIB
Publicación Artículo científico (JournalArticle)

A Contrario Detection of Faces with a Short Cascade of Classifiers

  • Lisani, José-Luis
  • Ramis, Silvia
[eng] The a contrario framework has been successfully used for the detection of lines, contours and other meaningful structures in digital images. In this paper we describe the implementation of an algorithm for face detection published in 2017 by Lisani et al. which applies the a contrario approach to the computation of the detection thresholds of a classical cascade of classifiers. The result is a very short cascade which obtains similar detection rates than a classical (and longer) one at a much lower computational cost.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Jellytoring: Real-Time Jellyfish Monitoring Based on Deep Learning Object Detection

  • Martín-Abadal, Miguel
  • Ruiz-Frau, Ana
  • Hinz, Hilmar
  • González-Cid, Yolanda
During the past decades, the composition and distribution of marine species have changed due to multiple anthropogenic pressures. Monitoring these changes in a cost-effective manner is of high relevance to assess the environmental status and evaluate the effectiveness of management measures. In particular, recent studies point to a rise of jellyfish populations on a global scale, negatively affecting diverse marine sectors like commercial fishing or the tourism industry. Past monitoring efforts using underwater video observations tended to be time-consuming and costly due to human-based data processing. In this paper, we present Jellytoring, a system to automatically detect and quantify different species of jellyfish based on a deep object detection neural network, allowing us to automatically record jellyfish presence during long periods of time. Jellytoring demonstrates outstanding performance on the jellyfish detection task, reaching an F1 score of 95.2%; and also on the jellyfish quantification task, as it correctly quantifies the number and class of jellyfish on a real-time processed video sequence up to a 93.8% of its duration. The results of this study are encouraging and provide the means towards a efficient way to monitor jellyfish, which can be used for the development of a jellyfish early-warning system, providing highly valuable information for marine biologists and contributing to the reduction of jellyfish impacts on humans., Miguel Martin-Abadal was supported by Ministry of Economy and Competitiveness (AEI,FEDER,UE), under contract DPI2017-86372-C3-3-R. Ana Ruiz-Frau was supported by a Marie-Sklodowska-Curie Individual Fellowship (JellyPacts project number 655475). Hilmar Hinz was supported through a Ramón y Cajal Fellowship financed by the Ministerio de Economía y Competitividad de España and the Conselleria d’Educació, Cultura i Universitats Comunidad Autónoma de las Islas Baleares (RyC 2013 14729). Yolanda Gonzalez-Cid was supported by Ministry of Economy and Competitiveness (AEI,FEDER,UE), under contracts TIN2017-85572-P and DPI2017-86372-C3-1-R., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Image-based, unsupervised estimation of fish size from commercial landings using deep learning

  • Álvarez-Ellacuria, Amaya
  • Palmer, Miquel
  • Catalán, Ignacio Alberto
  • Lisani, José Luis
The dynamics of fish length distribution is a key input for understanding the fish population dynamics and taking informed management decisions on exploited stocks. Nevertheless, in most fisheries, the length of landed fish is still made by hand. As a result, length estimation is precise at fish level, but due to the inherent high costs of manual sampling, the sample size tends to be small. Accordingly, the precision of population-level estimates is often suboptimal and prone to bias when properly stratified sampling programmes are not affordable. Recent applications of artificial intelligence to fisheries science are opening a promising opportunity for the massive sampling of fish catches. Here, we present the results obtained using a deep convolutional network (Mask R-CNN) for unsupervised (i.e. fully automatic) European hake length estimation from images of fish boxes automatically collected at the auction centre. The estimated mean of fish lengths at the box level is accurate; for average lengths ranging 20–40 cm, the root-mean-square deviation was 1.9 cm, and maximum deviation between the estimated and the measured mean body length was 4.0 cm. We discuss the challenges and opportunities that arise with the use of this technology to improve data acquisition in fisheries., This work has been funded by the projects FOTOPEIX and FOTOPEX2 (2017/2279 and 2018/2002) from Fundación Biodiversidad, through the Pleamar Program. We specially thank OPMALLORCAMAR and Direcció General de Pesca del Govern de les Illes Balears for supporting these projects. The work of J-LL was partially supported by grants TIN2017-85572-P and DPI2017-86372-C3-3-R (MINECO/AEI/FEDERUE).
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Automatic 1d histogram segmentation and application to the computation of color palettes

  • Lisani, José Luis
  • Petro, Ana Belén
This article presents an implementation of the FTC (Fine-to-Coarse) algorithm for histogram segmentation, presented by Delon et al. in 2007. This algorithm uses a non-parametric a contrario approach to segment a 1D histogram into its meaningful modes. We describe also how the method may be applied to the hue, saturation and intensity histograms of color images in order to automatically extract their more representative colors, the so-called color palette. The algorithm for color palette extraction described in this paper is based on the one first published in 2007 by Delon et al., with an improvement that affects low-saturated colors. Several results illustrate the effectiveness of the algorithm., The authors acknowledge the Ministerio de Ciencia, Innovación y Universidades (MCIU), the Agencia Estatal de Investigación (AEI) and the European Regional Development Funds (ERDF) for its support to the project TIN2017-85572-P. This work has also been sponsored by the Comunitat Autonoma de les Illes Balears through the Direcció General de Política Universitària i Recerca with funds from the Tourist Stay Tax Law ITS 2017-006 (PRD2018/26).
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A Deep Learning-Based Workflow for Dendritic Spine Segmentation

  • Vidaurre-Gallart, I.
  • Fernaud-Espinosa, Isabel
  • Cosmin-Toader, N.
  • Talavera-Martínez, L
  • Martín-Abadal, Miguel
  • Benavides-Piccione, Ruth
  • González-Cid, Yolanda
  • Pastor, L.
  • DeFelipe, Javier
  • García-Lorenzo, M.
The morphological analysis of dendritic spines is an important challenge for the neuroscientific community. Most state-of-the-art techniques rely on user-supervised algorithms to segment the spine surface, especially those designed for light microscopy images. Therefore, processing large dendritic branches is costly and time-consuming. Although deep learning (DL) models have become one of the most commonly used tools in image segmentation, they have not yet been successfully applied to this problem. In this article, we study the feasibility of using DL models to automatize spine segmentation from confocal microscopy images. Supervised learning is the most frequently used method for training DL models. This approach requires large data sets of high-quality segmented images (ground truth). As mentioned above, the segmentation of microscopy images is time-consuming and, therefore, in most cases, neuroanatomists only reconstruct relevant branches of the stack. Additionally, some parts of the dendritic shaft and spines are not segmented due to dyeing problems. In the context of this research, we tested the most successful architectures in the DL biomedical segmentation field. To build the ground truth, we used a large and high-quality data set, according to standards in the field. Nevertheless, this data set is not sufficient to train convolutional neural networks for accurate reconstructions. Therefore, we implemented an automatic preprocessing step and several training strategies to deal with the problems mentioned above. As shown by our results, our system produces a high-quality segmentation in most cases. Finally, we integrated several postprocessing user-supervised algorithms in a graphical user interface application to correct any possible artifacts., The research leading to these results has received funding from the following entities: the Spanish Government under grants FPU18/05304, PRE2018-085403, TIN2017-83132-C2-1-R, PID2020-113013RB-C21, BES-2017-081264, TIN2017-85572-P, and DPI2017-86372-C3-3-R and the European Union's Horizon 2020 Framework under the Specific Grant Agreement No. 945539 (HBP SGA3).