Homero Vladimir Rios-Figueroa

Cervical cancer detection using colposcopic images: a temporal approach

In the present work, we propose a methodology analysis of the colposcopic images to help the expert to make a more robust diagnosis of precursor lesions of cervical cancer. Although some others approaches have been used to assess cervical lesion, a complete methodology to evaluate temporal changes of tissue color is still missing. The different processes involved in the analysis are described. The image registration was implemented using the phase correlation method followed by a locally applied algorithm based on the normalized cross-correlation. During the parameterization process, each time series obtained from the image sequences was represented as a parabola in a parameter space. A supervised Bayesian learning approach is proposed to classify the features in the parameter space according to the classification made by the colposcopist. Then those labels are used as a criterion to categorize the tissue and perform the image segmentation. Some preliminary results are shown using unsupervised learning with real data.

Improved multi-objective clustering with automatic determination of the number of clusters

The multi-objective clustering with automatic determination of the number of clusters (MOCK) approach is improved in this work by means of an empirical comparison of three multi-objective evolutionary algorithms added to MOCK instead of the original algorithm used in such approach. The results of two different experiments using seven real data sets from UCI repository are reported: (1) using two multi-objective optimization performance metrics (hypervolume and two-set coverage) and (2) using the F-measure and the silhouette coefficient to evaluate the clustering quality. The results are compared against the original version of MOCK and also against other algorithms representative of the state of the art. Such results indicate that the new versions are highly competitive and able to deal with different types of data sets.

Decision making for obstacle avoidance in autonomous mobile robots by time to contact and optical flow

Vision is a vital cue for human navigation, and it has become in a powerful tool for robot navigation. Computer vision is useful for recognition of positional relationship and relative motion between themselves and objects in the environment. So, we address the problem of navigation for mobile robot in indoor environment. To this task, we tackle the problem using monocular vision, i.e., without other kind of sensors. Insects and some animals use tools as optical flow estimations and time to contact, to their navigation [1]. So, in this paper, we propose a method for obstacle avoidance, without constantly calculating the optical flow field, only it is calculated when the robot is close to colliding with an obstacle, and so, it uses the flow field divergence to decide which direction will should be taken. Physical experiments using a real robot have been conducted in unknown environments.

Tracking and prediction of motion of segmented regions using the Kalman filter

Currently many applications require tracking moving objects through a sequence of images. However, sometimes we do not know the characteristics of the movement and even the objects that we will track. In this paper, a complete model for the description and inference of motion of segmented regions is presented, using the Kalman filter without requiring a priori information the scene. Three scenarios with different characteristics are presented as test cases. Segmentation of moving objects is done through the clustering of optical flow vectors for similarity, which are obtained by Pyramid Lucas and Kanade algorithm.

Impact of commercial sensors in human computer interaction: a review

Nowadays, the communication gap between humans and computers might be reduced due to multimodal sensors available in the market. Therefore, it is important to know the specifications of these sensors and how they are being used in order to create human computer interfaces, which tackle complex tasks. The purpose of this paper is to review recent research regarding the up-to-date application areas of the following sensors: (1) Emotiv sensor, which identifies emotions, facial expressions, thoughts, and head movements from users through electroencephalography signals, (2) Leap motion controller, which recognizes hand and arm movements via vision techniques, (3) Myo armband, which identifies hand and arm movements using electromyography signals and inertial sensors, and (4) Oculus rift, which provides immersion into virtual reality to users. The application areas discussed in this manuscript go from assistive technology to virtual tours. Finally, a brief discussion regarding advantages and shortcomings of each sensor is presented.

Predicting collisions: time-to-contact forecasting based on probabilistic segmentation and system identification

The Time-to-contact (TTC) estimate is mainly used in robotics navigation, in order to detect potential danger with obstacles in the environment. A key aspect in a robotic system is to perform its tasks promptly. Several approaches have been proposed to estimate reliable TTC in order to avoid collisions in real-time; nevertheless they are time consuming due to a calculation of scene characteristics in every frame. This paper presents an approach to estimate TTC using monocular vision based on the size change of the obstacles over time (); therefore, the robotic system may react promptly to its environment. Our approach collects information from few data of an obstacle, then the behavior of the movement is found through an online recursive modeling process, and finally, a forecasting of the upcoming positions is computed. We segment the obstacles using probabilistic hidden Markov chains. Our proposal is compared to a classical color segmentation approach using two real image sequences, each sequence is composed of 210 frames. Our results show that our proposal obtained smoother segmentations than a traditional color-based approach.

Perspective Reconstruction by Determining Vanishing Points for Autonomous Mobile Robot Visual Localization on Supermarkets

Mobile robots are more and more used on diverse environments to provide useful services. One of these environments are supermarkets, where a robot can help to find and carry products, maintain the account of them and to mark out from a list, the products already in the shopping car (maybe the same robot). However, a common problem on these environments is the autonomous localization, due to the fact that supermarkets are a set of aisles, and most of them look the same for laser range finders; sensors commonly used for localization. On this paper, we present an approach to localize autonomous mobile robots on supermarket by using a perspective reconstruction of the shelves and then an statistical comparison of the products present in them. In order to detect the shelves, the vanishing points are estimated to provide a fast and efficient way to segment products on them. To avoid multiple vanishing points on this kind of environments, result of the variety of products present, a variation of a RANSAC approach is proposed. Once a vanishing point has been determined, an homography process is applied to the shelves in order to rectify images. And finally, by horizontal histograms the robot is able to segment individual products to be compared to the data base. Then the robot will be able to detect by a probability function the correct aisle where it is.

Home Furniture Detection by Geometric Characterization by Autonomous Service Robots

Service robots are nowadays more and more common on diverse environments. In order to provide useful services, robots must not only identify different objects but also understand their use and be able to extract characteristics that make useful an object. In this work, a framework is presented for recognize home furniture by analyzing geometrical features over point clouds. A fast and efficient method for horizontal and vertical planes detection is presented, based on the histograms of 3D points acquired from a Kinect like sensor onboard the robot. Horizontal planes are recovered according to height distribution on 2D histograms, while vertical planes with a similar approach over a projection on the floor (3D histograms). Characteristics of points belonging to a given plane are extracted in order to match with planes from furniture pieces in a database. Proposed approach has been proved and validated in home like environments with a mobile robotic platform.

Detecting falling people by autonomous service robots: A ROS module integration approach

In this paper is presented the integration of diverse modules for people fallen detection by a mobile service robot. This integration has been achieved in the middleware ROS (Robotics Operation System). The proposed implementation are arranged over an modular architecture of three layers: Hardware, Processing and Decision. The modules implemented are on the processing layer. The first module uses an RGB-D camera to detect and track a person in the environment. This module calculate features to detect the fallen pose. In the second module, a PID controller in a pan/tilt unit is used, in order to track the person with a minimum error and soft movement. For this purpose the centroid of the person is located at the center of the plane image. The main characteristics in our architecture are: 1) Segmentation in depth is used, because 3D information is required for detecting the fallen pose; 2) The parameters of PID control are tuned using a manual method and a genetic algorithm, to compare and improve the performance of the tracking person module. Once the PID controller was optimized, the architecture to follow the person and detect the fallen pose, is probed in real time.

A human–computer interface for wrist rehabilitation: a pilot study using commercial sensors to detect wrist movements

Health conditions might cause muscle weakness and immobility in some body parts; hence, physiotherapy exercises play a key role in the rehabilitation. To improve the engagement during the rehabilitation process, we therefore propose a human–computer interface (serious game) in which five wrist movements (extension, flexion, pronation, supination and neutral) are detected via two commercial sensors (Leap motion controller and Myo armband). Leap motion provides data regarding positions of user’s finger phalanges through two infrared cameras, while Myo armband facilitates electromyography signal and inertial motion of user’s arm through its electrodes and inertial measurement unit. The main aim of this study is to explore the performance of these sensors on wrist movement recognition in terms of accuracy, sensitivity and specificity. Eight healthy participants played 5 times a proposed game with each sensor in one session. Both sensors reported over 85% average recognition accuracy in the five wrist movements. Based on t test and Wilcoxon signed-rank test, early results show that there were significant differences between Leap motion controller and Myo armband recognitions in terms of average sensitivities on extension (