|
|
Enric Marti, Jordi Vitria, & Alberto Sanfeliu. (1998). Reconocimiento de Formas y Análisis de Imágenes. AERFAI.
Abstract: Los sistemas actuales de reconocimiento automático del lenguaje oral se basan en dos etapas básicas de procesado: la parametrización, que extrae la evolución temporal de los parámetros que caracterizan la voz, y el reconocimiento propiamente dicho, que identifica la cadena de palabras de la elocución recibida con ayuda de los modelos que representan el conocimiento adquirido en la etapa de aprendizaje. Tomando como línea divisoria la palabra, dichos modelos son de tipo acústicofonético o gramatical. Los primeros caracterizan las palabras incluidas en el vocabulario de la aplicación o tarea a la que está orientado el sistema de reconocimiento, usando a menudo para ello modelos de unidades de habla de extensión inferior a la palabra, es decir, de unidades subléxicas. Por otro lado, la gramática incluye el conocimiento acerca de las combinaciones permitidas de palabras para formar las frases o su probabilidad. Queda fuera del esquema la denominada comprensión del habla, que utiliza adicionalmente el conocimiento semántico y pragmático para captar el significado de la elocución de entrada al sistema a partir de la cadena (o cadenas alternativas) de palabras que suministra el reconocedor.
|
|
|
|
Antonio Lopez, Ernest Valveny, & Juan J. Villanueva. (2005). Real-time quality control of surgical material packaging by artificial vision. Assembly Automation, 25(3).
|
|
|
|
O. Fors, A. Richichi, Xavier Otazu, & J. Nuñez. (2008). A new wavelet-based approach for the automated treatment of large sets of lunar occultation data. Astronomy and Astrohysics, 297–304.
|
|
|
|
A. Richichi, O. Fors, M.T. Merino, Xavier Otazu, J. Nuñez, A. Prades, et al. (2006). The Calar Alto lunar occultation program: update and new results. Astronomy and Astrophysics (Section ’Stellar structure and evolution’), 445:1081–1088.
|
|
|
|
Ariel Amato, Ivan Huerta, Mikhail Mozerov, Xavier Roca, & Jordi Gonzalez. (2014). Moving Cast Shadows Detection Methods for Video Surveillance Applications. In Augmented Vision and Reality (Vol. 6, pp. 23–47). Springer Berlin Heidelberg.
Abstract: Moving cast shadows are a major concern in today’s performance from broad range of many vision-based surveillance applications because they highly difficult the object classification task. Several shadow detection methods have been reported in the literature during the last years. They are mainly divided into two domains. One usually works with static images, whereas the second one uses image sequences, namely video content. In spite of the fact that both cases can be analogously analyzed, there is a difference in the application field. The first case, shadow detection methods can be exploited in order to obtain additional geometric and semantic cues about shape and position of its casting object (‘shape from shadows’) as well as the localization of the light source. While in the second one, the main purpose is usually change detection, scene matching or surveillance (usually in a background subtraction context). Shadows can in fact modify in a negative way the shape and color of the target object and therefore affect the performance of scene analysis and interpretation in many applications. This chapter wills mainly reviews shadow detection methods as well as their taxonomies related with the second case, thus aiming at those shadows which are associated with moving objects (moving shadows).
|
|
|
|
Isabelle Guyon, Lisheng Sun Hosoya, Marc Boulle, Hugo Jair Escalante, Sergio Escalera, Zhengying Liu, et al. (2019). Analysis of the AutoML Challenge Series 2015-2018. In Automated Machine Learning (pp. 177–219). SSCML. Springer.
Abstract: The ChaLearn AutoML Challenge (The authors are in alphabetical order of last name, except the first author who did most of the writing and the second author who produced most of the numerical analyses and plots.) (NIPS 2015 – ICML 2016) consisted of six rounds of a machine learning competition of progressive difficulty, subject to limited computational resources. It was followed bya one-round AutoML challenge (PAKDD 2018). The AutoML setting differs from former model selection/hyper-parameter selection challenges, such as the one we previously organized for NIPS 2006: the participants aim to develop fully automated and computationally efficient systems, capable of being trained and tested without human intervention, with code submission. This chapter analyzes the results of these competitions and provides details about the datasets, which were not revealed to the participants. The solutions of the winners are systematically benchmarked over all datasets of all rounds and compared with canonical machine learning algorithms available in scikit-learn. All materials discussed in this chapter (data and code) have been made publicly available at http://automl.chalearn.org/.
|
|
|
|
Maya Dimitrova, Ch. Roumenin, Petia Radeva, David Rotger, & Juan J. Villanueva. (2003). Multimodal Intelligent System for Cardiovascular Diagnosis.
|
|
|
|
Wenlong Deng, Yongli Mou, Takahiro Kashiwa, Sergio Escalera, Kohei Nagai, Kotaro Nakayama, et al. (2020). Vision based Pixel-level Bridge Structural Damage Detection Using a Link ASPP Network. AC - Automation in Construction, 110, 102973.
Abstract: Structural Health Monitoring (SHM) has greatly benefited from computer vision. Recently, deep learning approaches are widely used to accurately estimate the state of deterioration of infrastructure. In this work, we focus on the problem of bridge surface structural damage detection, such as delamination and rebar exposure. It is well known that the quality of a deep learning model is highly dependent on the quality of the training dataset. Bridge damage detection, our application domain, has the following main challenges: (i) labeling the damages requires knowledgeable civil engineering professionals, which makes it difficult to collect a large annotated dataset; (ii) the damage area could be very small, whereas the background area is large, which creates an unbalanced training environment; (iii) due to the difficulty to exactly determine the extension of the damage, there is often a variation among different labelers who perform pixel-wise labeling. In this paper, we propose a novel model for bridge structural damage detection to address the first two challenges. This paper follows the idea of an atrous spatial pyramid pooling (ASPP) module that is designed as a novel network for bridge damage detection. Further, we introduce the weight balanced Intersection over Union (IoU) loss function to achieve accurate segmentation on a highly unbalanced small dataset. The experimental results show that (i) the IoU loss function improves the overall performance of damage detection, as compared to cross entropy loss or focal loss, and (ii) the proposed model has a better ability to detect a minority class than other light segmentation networks.
Keywords: Semantic image segmentation; Deep learning
|
|
|
|
Joakim Bruslund Haurum, Meysam Madadi, Sergio Escalera, & Thomas B. Moeslund. (2022). Multi-scale hybrid vision transformer and Sinkhorn tokenizer for sewer defect classification. AC - Automation in Construction, 144, 104614.
Abstract: A crucial part of image classification consists of capturing non-local spatial semantics of image content. This paper describes the multi-scale hybrid vision transformer (MSHViT), an extension of the classical convolutional neural network (CNN) backbone, for multi-label sewer defect classification. To better model spatial semantics in the images, features are aggregated at different scales non-locally through the use of a lightweight vision transformer, and a smaller set of tokens was produced through a novel Sinkhorn clustering-based tokenizer using distinct cluster centers. The proposed MSHViT and Sinkhorn tokenizer were evaluated on the Sewer-ML multi-label sewer defect classification dataset, showing consistent performance improvements of up to 2.53 percentage points.
Keywords: Sewer Defect Classification; Vision Transformers; Sinkhorn-Knopp; Convolutional Neural Networks; Closed-Circuit Television; Sewer Inspection
|
|
|
|
Isabelle Guyon, Imad Chaabane, Hugo Jair Escalante, Sergio Escalera, Damir Jajetic, James Robert Lloyd, et al. (2016). A brief Review of the ChaLearn AutoML Challenge: Any-time Any-dataset Learning without Human Intervention. In AutoML Workshop (pp. 1–8).
Abstract: The ChaLearn AutoML Challenge team conducted a large scale evaluation of fully automatic, black-box learning machines for feature-based classification and regression problems. The test bed was composed of 30 data sets from a wide variety of application domains and ranged across different types of complexity. Over six rounds, participants succeeded in delivering AutoML software capable of being trained and tested without human intervention. Although improvements can still be made to close the gap between human-tweaked and AutoML models, this competition contributes to the development of fully automated environments by challenging practitioners to solve problems under specific constraints and sharing their approaches; the platform will remain available for post-challenge submissions at http://codalab.org/AutoML.
Keywords: AutoML Challenge; machine learning; model selection; meta-learning; repre- sentation learning; active learning
|
|
|
|
Arnau Ramisa, Adriana Tapus, David Aldavert, Ricardo Toledo, & Ramon Lopez de Mantaras. (2009). Robust Vision-Based Localization using Combinations of Local Feature Regions Detectors. AR - Autonomous Robots, 27(4), 373–385.
Abstract: This paper presents a vision-based approach for mobile robot localization. The model of the environment is topological. The new approach characterizes a place using a signature. This signature consists of a constellation of descriptors computed over different types of local affine covariant regions extracted from an omnidirectional image acquired rotating a standard camera with a pan-tilt unit. This type of representation permits a reliable and distinctive environment modelling. Our objectives were to validate the proposed method in indoor environments and, also, to find out if the combination of complementary local feature region detectors improves the localization versus using a single region detector. Our experimental results show that if false matches are effectively rejected, the combination of different covariant affine region detectors increases notably the performance of the approach by combining the different strengths of the individual detectors. In order to reduce the localization time, two strategies are evaluated: re-ranking the map nodes using a global similarity measure and using standard perspective view field of 45°.
In order to systematically test topological localization methods, another contribution proposed in this work is a novel method to see the degradation in localization performance as the robot moves away from the point where the original signature was acquired. This allows to know the robustness of the proposed signature. In order for this to be effective, it must be done in several, variated, environments that test all the possible situations in which the robot may have to perform localization.
|
|
|
|
David Masip, M. Bressan, & Jordi Vitria. (2004). Classifier Combination Applied to Real Time Face Detection and Classification.
|
|
|
|
Fernando Vilariño. (2019). 3D Scanning of Capitals at Library Living Lab.
|
|
|
|
Xavier Otazu, Olivier Penacchio, & Xim Cerda-Company. (2015). An excitatory-inhibitory firing rate model accounts for brightness induction, colour induction and visual discomfort. In Barcelona Computational, Cognitive and Systems Neuroscience.
|
|
|
|
Thierry Brouard, A. Delaplace, Muhammad Muzzamil Luqman, H. Cardot, & Jean-Yves Ramel. (2010). Design of Evolutionary Methods Applied to the Learning of Bayesian Nerwork Structures. In Ahmed Rebai (Ed.), Bayesian Network (pp. 13–37). Sciyo.
|
|
