The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this work, we present an appearance based human activity recognition system. It uses background modeling to segment the foreground object and extracts useful discriminative features for representing activities performed by humans and robots. Subspace based method like principal component analysis is used to extract low dimensional features from large voluminous activity images. These low dimensional...
Based on the least squares support vector regression and the Nystrom approximation, it becomes possible to apply a nonlinear model for the prediction problem of water quality with large sample. This is done by using a reduce rank approximation of the nonlinear mapping induced by the primal kernel matrix, with an active selection of support vectors based on an unsupervised kernel clustering algorithm...
This paper proposes an image matching system using aerial images, captured in flight time, and aerial geo-referenced images to estimate the Unmanned Aerial Vehicle (UAV) position in a situation of Global Navigation Satellite System (GNSS) failure. The image matching system is based on edge detection in the aerial and geo-referenced image and posterior automatic image registration of these edge-images...
Recently, the problem of fully autonomous navigation of vehicle has gained major interest from research institutes and private companies. In general, these researches rely on GPS in fusion with other sensors to track vehicle in outdoor environment. However, as indoor environment such as car park is also an important scenario for vehicle navigation, the lack of GPS poses a serious problem. This study...
Most unsupervised learners such as Kmeans, Gaussian mixture model (GMM) or sparse coding do not use the structure information found from the neighbourhood of an image patch for parameter estimation. A recent image prior technique combine unsupervised learning with Markov Random Field (MRF) by replacing the MRF potential with an unsupervised learner. It uses a neighbourhood of image patches for learning...
The coefficient of high resolution (HR) block and low resolution (LR) block is assumed to be equal in selecting the corresponding atoms of HR dictionary in previous super-resolution (SR) reconstruction algorithms, which may cause error matching and decrease the accuracy of HR coefficient estimation. A learning method of structural dictionary and mapping relation (LCDMR) is combined to compensate this...
In this paper, we introduce the application of generic multi-level Convolutional Neural Networks (CNN) approach into the scene understanding or image parsing task. Given an input image, first, a set of similar images from the training set are retrieved based on global-level CNN feature matching similarities. Then, the input test image and the similar images are overseg-mented into superpixels. Next,...
This study reviews the educational theories and existing literature for the integration of robots to support teaching in classrooms by assessing integration methods and the effectiveness of educational robotics on student learning. Most of the research on this subject are only focused on children from kindergarten to middle schools and analyzed the end results from questionnaires and grades. Without...
In this paper, based on the virtual scene images generated by the Unity3D engine, a target tracking realization method in UAV(Unmanned Aerial Vehicle) simulation training system is proposed. To realize the target tracking steadily, the LOS(line of sight) tracking model utilizing the target pixel offset in the consecutive frame image and the velocity tracking model are established. Meanwhile, a digital...
Increasing the transparency of robotic systems used for gait rehabilitation can improve training of various daily activities such as walking or balancing. However, until today, there has been very little effort invested in a systematic analysis of occurring unwanted interaction forces between the patient and the robot. In this paper, we have developed such a setup for systematic analysis and quantification...
This paper presents a method for real-time detection and tracking of the human face. This is achieved using the Raspberry Pi microcomputer and the Easylab microcontroller as the main hardware with a camera mounted on servomotors for continuous image feed-in. Real-time face detection is performed using Haar-feature classifiers and ScicosLab in the Raspberry Pi. Then, the Easylab is responsible for...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.