Patricia L. Suarez, Angel D. Sappa, & Boris X. Vintimilla. (2018). Cross-spectral image dehaze through a dense stacked conditional GAN based approach. In 14th IEEE International Conference on Signal Image Technology & Internet based Systems (SITIS 2018) (pp. 358–364).
Abstract: This paper proposes a novel approach to remove haze from RGB images using a near infrared images based on a dense stacked conditional Generative Adversarial Network (CGAN). The architecture of the deep network implemented receives, besides the images with haze, its corresponding image in the near infrared spectrum, which serve to accelerate the learning process of the details of the characteristics of the images. The model uses a triplet layer that allows the independence learning of each channel of the visible spectrum image to remove the haze on each color channel separately. A multiple loss function scheme is proposed, which ensures balanced learning between the colors and the structure of the images. Experimental results have shown that the proposed method effectively removes the haze from the images. Additionally, the proposed approach is compared with a state of the art approach showing better results.
|
Dennis G. Romero, A. F. Neto, T. F. Bastos, & Boris X. Vintimilla. (2012). RWE patterns extraction for on-line human action recognition through window-based analysis of invariant moments. In 5th Workshop in applied Robotics and Automation (RoboControl).
Abstract: This paper presents a method for on-line human action recognition on video sequences. An analysis based on Mahalanobis distance is performed to identify the “idle” state, which defines the beginning and end of the person movement, for posterior patterns extraction based on Relative Wavelet Energy from sequences of invariant moments.
|
Dennis G. Romero, A. F. Neto, T. F. Bastos, & Boris X. Vintimilla. (2012). An approach to automatic assistance in physiotherapy based on on-line movement identification. In VI Andean Region International Conference – ANDESCON 2012. Andean Region International Conference (ANDESCON), 2012 VI: IEEE.
Abstract: This paper describes a method for on-line movement identification, oriented to patient’s movement evaluation during physiotherapy. An analysis based on Mahalanobis distance between temporal windows is performed to identify the “idle/motion” state, which defines the beginning and end of the patient’s movement, for posterior patterns extraction based on Relative Wavelet Energy from sequences of invariant moments.
|
M. Diaz, Dennys Paillacho, C. Angulo, O. Torres, J. Gonzálalez, & J. Albo Canals. (2014). A Week-long Study on Robot-Visitors Spatial Relationships during Guidance in a Sciences Museum. In ACM/IEEE International Conference on Human-Robot Interaction (pp. 152–153).
Abstract: In order to observe spatial relationships in social human- robot interactions, a field trial was carried out within the CosmoCaixa Science Museum in Barcelona. The follow me episodes studied showed that the space configurations formed by guide and visitors walking together did not always fit the robot social affordances and navigation requirements to perform the guidance successfully, thus additional commu- nication prompts are considered to regulate effectively the walking together and follow me behaviors.
|
Ricardo Cajo, & Wilton Agila. (2015). Evaluation of algorithms for linear and nonlinear PID control for Twin Rotor MIMO System. In Computer Aided System Engineering (APCASE), 2015 Asia-Pacific Conference on, Quito, 2015 (pp. 214–219). IEEE.
Abstract: In this paper the linear and nonlinear PID control algorithms are analyzed and for a twin rotor MIMO system (TRMS), whose characteristic is not linear with two degrees of freedom and cross-links. The aim of this work is to stabilize the TRMS, to achieve a particular position and follow a trajectory in the shortest time. Mathematical modeling of helicopter model is simulated using MATLAB / Simulink, the two degrees of freedom are controlled both horizontally and vertically through the proposed controllers. Also nonlinear segmented observers for each degree of freedom are designed in order to measure statements required by the nonlinear controller. Followed, a comparative analysis of both algorithms is presented to evaluate their performance in the real TRMS.
|
Miguel Realpe, Boris X. Vintimilla, & L. Vlacic. (2015). Towards Fault Tolerant Perception for autonomous vehicles: Local Fusion. In IEEE 7th International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM), Siem Reap, 2015. (pp. 253–258).
Abstract: Many robust sensor fusion strategies have been developed in order to reliably detect the surrounding environments of an autonomous vehicle. However, in real situations there is always the possibility that sensors or other components may fail. Thus, internal modules and sensors need to be monitored to ensure their proper function. This paper introduces a general view of a perception architecture designed to detect and classify obstacles in an autonomous vehicle's environment using a fault tolerant framework, whereas elaborates the object detection and local fusion modules proposed in order to achieve the modularity and real-time process required by the system.
|
Dennys Paillacho, Cecilio Angulo, & Marta Díaz. (2015). An Exploratory Study of Group-Robot Social Interactions in a Cultural Center. In IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2015, International Conference on, Hamburg, Germany, 2015.
Abstract: This article describes an exploratory study of social human-robot interaction with the experimental robotic platform MASHI. The experiences were carried out in La B`obila Cultural Center in Barcelona, Spain to study the visitor preferences, characterize the groups and their spatial relationships in this open and unstructured environment. Results showed that visitors prefers to play and dialogue with the robot. Children have the highest interest in interacting with the robot, more than young and adult visitors. Most of the groups consisted of more than 3 visitors, however the size of the groups during interactions was continuously changed. In static situations, the observed spatial relationships denotes a social cohesion in the human-robot interactions.
|
Cristhian A. Aguilera, Angel D. Sappa, & R. Toledo. (2015). LGHD: A feature descriptor for matching across non-linear intensity variations. In IEEE International Conference on, Quebec City, QC, 2015 (pp. 178–181). Quebec City, QC, Canada: IEEE.
Abstract: This paper presents a new feature descriptor suitable to the task of matching features points between images with nonlinear intensity variations. This includes image pairs with significant illuminations changes, multi-modal image pairs and multi-spectral image pairs. The proposed method describes the neighbourhood of feature points combining frequency and spatial information using multi-scale and multi-oriented Log- Gabor filters. Experimental results show the validity of the proposed approach and also the improvements with respect to the state of the art.
|
M. Oliveira, L. Seabra Lopes, G. Hyun Lim, S. Hamidreza Kasaei, Angel D. Sappa, & A. Tomé. (2015). Concurrent Learning of Visual Codebooks and Object Categories in Open- ended Domains. In Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on, Hamburg, Germany, 2015 (pp. 2488–2495). Hamburg, Germany: IEEE.
Abstract: In open-ended domains, robots must continuously learn new object categories. When the training sets are created offline, it is not possible to ensure their representativeness with respect to the object categories and features the system will find when operating online. In the Bag of Words model, visual codebooks are usually constructed from training sets created offline. This might lead to non-discriminative visual words and, as a consequence, to poor recognition performance. This paper proposes a visual object recognition system which concurrently learns in an incremental and online fashion both the visual object category representations as well as the codebook words used to encode them. The codebook is defined using Gaussian Mixture Models which are updated using new object views. The approach contains similarities with the human visual object recognition system: evidence suggests that the development of recognition capabilities occurs on multiple levels and is sustained over large periods of time. Results show that the proposed system with concurrent learning of object categories and codebooks is capable of learning more categories, requiring less examples, and with similar accuracies, when compared to the classical Bag of Words approach using codebooks constructed offline.
|
Dennis G. Romero, A. Frizera, Angel D. Sappa, Boris X. Vintimilla, & T.F. Bastos. (2015). A predictive model for human activity recognition by observing actions and context. In ACIVS 2015 (Advanced Concepts for Intelligent Vision Systems), International Conference on, Catania, Italy, 2015 (pp. 323–333).
Abstract: This paper presents a novel model to estimate human activities – a human activity is defined by a set of human actions. The proposed approach is based on the usage of Recurrent Neural Networks (RNN) and Bayesian inference through the continuous monitoring of human actions and its surrounding environment. In the current work human activities are inferred considering not only visual analysis but also additional resources; external sources of information, such as context information, are incorporated to contribute to the activity estimation. The novelty of the proposed approach lies in the way the information is encoded, so that it can be later associated according to a predefined semantic structure. Hence, a pattern representing a given activity can be defined by a set of actions, plus contextual information or other kind of information that could be relevant to describe the activity. Experimental results with real data are provided showing the validity of the proposed approach.
|