Browsing by Keyword "Localization"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item Deep learning to find colorectal polyps in colonoscopy: A systematic literature review: A systematic literature review(2020-08) Sánchez-Peralta, Luisa F.; Bote-Curiel, Luis; Picón, Artzai; Sánchez-Margallo, Francisco M.; Pagador, J. Blas; COMPUTER_VISIONColorectal cancer has a great incidence rate worldwide, but its early detection significantly increases the survival rate. Colonoscopy is the gold standard procedure for diagnosis and removal of colorectal lesions with potential to evolve into cancer and computer-aided detection systems can help gastroenterologists to increase the adenoma detection rate, one of the main indicators for colonoscopy quality and predictor for colorectal cancer prevention. The recent success of deep learning approaches in computer vision has also reached this field and has boosted the number of proposed methods for polyp detection, localization and segmentation. Through a systematic search, 35 works have been retrieved. The current systematic review provides an analysis of these methods, stating advantages and disadvantages for the different categories used; comments seven publicly available datasets of colonoscopy images; analyses the metrics used for reporting and identifies future challenges and recommendations. Convolutional neural networks are the most used architecture together with an important presence of data augmentation strategies, mainly based on image transformations and the use of patches. End-to-end methods are preferred over hybrid methods, with a rising tendency. As for detection and localization tasks, the most used metric for reporting is the recall, while Intersection over Union is highly used in segmentation. One of the major concerns is the difficulty for a fair comparison and reproducibility of methods. Even despite the organization of challenges, there is still a need for a common validation framework based on a large, annotated and publicly available database, which also includes the most convenient metrics to report results. Finally, it is also important to highlight that efforts should be focused in the future on proving the clinical value of the deep learning based methods, by increasing the adenoma detection rate.Item Experimental evaluation of autonomous driving based on visual memory and image-based visual servoing(2011-09) Diosi, Albert; Šegvić, Siniša; Remazeilles, Anthony; Chaumette, François; Medical TechnologiesIn this paper, the performance of a topological-metric visual-path- following framework is investigated in different environments. The framework relies on a monocular camera as the only sensing modality. The path is represented as a series of reference images such that each neighboring pair contains a number of common landmarks. Local 3-D geometries are reconstructed between the neighboring reference images to achieve fast feature prediction. This condition allows recovery from tracking failures. During navigation, the robot is controlled using image-based visual servoing. The focus of this paper is on the results from a number of experiments that were conducted in different environments, lighting conditions, and seasons. The experiments with a robot car show that the framework is robust to moving objects and moderate illumination changes. It is also shown that the system is capable of online path learning.Item On the design of a novel two-objective harmony search approach for distance- and connectivity-based localization in wireless sensor networks(2013-02) Manjarres, Diana; Del Ser, Javier; Gil-Lopez, Sergio; Vecchio, Massimo; Landa-Torres, Itziar; Salcedo-Sanz, Sancho; Lopez-Valcarce, Roberto; IA; Tecnalia Research & InnovationIn several wireless sensor network applications the availability of accurate nodes' location information is essential to make collected data meaningful. In this context, estimating the positions of all unknown-located nodes of the network based on noisy distance-related measurements (usually referred to as localization) generally embodies a non-convex optimization problem, which is further exacerbated by the fact that the network may not be uniquely localizable, especially when its connectivity degree is not sufficiently high. In order to efficiently tackle this problem, we propose a novel two-objective localization approach based on the combination of the harmony search (HS) algorithm and a local search procedure. Moreover, some connectivity-based geometrical constraints are defined and exploited to limit the areas in which sensor nodes can be located. The proposed method is tested with different network configurations and compared, in terms of normalized localization error and three multi-objective quality indicators, with a state-of-the-art metaheuristic localization scheme based on the Pareto archived evolution strategy (PAES). The results show that the proposed approach achieves considerable accuracies and, in the majority of the scenarios, outperforms PAES.Item Remote monitoring for safety of workers in industrial plants: Learned lessons beyond technical issues(Elsevier, 2018-01-01) Lopez, Jose María Cabero; Tecnalia Research & InnovationMost tasks during a turnaround in a refinery imply rush, works in crowded risky zones and dangerous confined spaces. Current safety protocols are mostly based on tasks schedules, human supervision all along the refinery and Personal Protection Equipment (PPE). These protocols, although very costly and usually exhaustive, are prone to human errors and infractions that can become fatal. Localization techniques and communication technologies are two excellent means to help minimize latent risks for worker’s safety. This work describes a set of lessons learned in real initiatives for remote monitoring of workers’ activities in refineries. It focuses especially on aspects beyond technical issues usually treated in the literature, i.e., deployment, logistics, and sociological issues.Item UWB MAC and network solutions for low data rate with location and tracking applications(2005) Giancola, Guerino; Blazevic, Ljubica; Bucaille, Isabelle; De Nardis, Luca; Di Benedetto, Maria Gabriella; Durand, Yves; Froc, Gwillerm; Cuezva, Begoña Molinete; Pierrot, Jean Benoît; Pirinen, Pekka; Rinaldi, Nils; Tecnalia Research & InnovationThe object of this paper is to present the main results achieved during the first fifteen months of the 6th framework European Union integrated research project PULSERS [1], regarding Ultra Wide Band (UWB) Medium Access Control (MAC) and network layer issues for low data rate with location and tracking (LDR-LT) applications. Various intended UWB system architectures and their key requirements and parameters are introduced. For such systems, potential MAC schemes and network solutions are illustrated and discussed. New ideas about wireless UWB access, synchronization, resource allocation, and topology management are also presented.