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 paper, we present a SIFT based Slope K method which is faster and more robust than the classical SIFT in landmark based localization. First, the slope k value can be used to erase mismatched feature points (outliers) of the two compared images. Second, the y position is determined by the slope k value. Therefore, the Slope K method is able to localizes about twice as more accurate as the classical...
This paper describes a scalable method of estimating a vision graph, in which a pair of camera nodes are connected by an edge if the two nodes share the same field of view, based on local image feature correspondences. The proposed method is implemented in a distributed fashion, meanwhile avoiding the flooding of the image feature information since it can be a bottleneck in achieving scalability....
The selectivity of visual attention mechanism is influenced by bottom-up competition and top-down biasing. This paper presents an object-based visual attention model which simulates top-down influences. Five components of top-down influences are modeled: learning of object representations stored in long-term memory (LTM), deduction of task-relevant feature(s), estimation of top-down biases, mediation...
This paper presents a novel approach for face detection, which is based on the discriminative MspLBP features selected by a boosting technique called the Ada-LDA method. By scanning the face image with a scalable sub-window, many sub-regions are obtained from which the MspLBP features are extracted to describe the local structures of a face image. From a large pool of the MspLBP features within the...
This paper presents a novel local threshold segmentation algorithm for digital images incorporating shape information. In image segmentation, most of local threshold algorithms are only based on intensity analysis. In many applications where an image contains objects with a similar shape, besides the intensity information, prior known shape attributes could be exploited to improve the segmentation...
Efficiently and accurately detecting pedestrian plays a very important role in many computer vision applications such as Intelligent Transportation System and Safety Driving Assistant. This paper puts forwards a two-stage pedestrian detection method based on machine vision. Firstly, the expanded Haar-like characteristic is selected and calculated using integral map and the pedestrian detection cascaded...
Electroencephalography (EEG) is the reaction of the overall activities of the brain neurons. In the researches of Brain Computer Interface (BCI), the pattern recognition of EEG which is associated with mental tasks is the most important part of the BCI system. In this paper, data of ?? wave and ?? wave of C3, C4, P3 and P4 channels are certificated to be the proper sources for feature extraction,...
In order to resolve the problem incurred by low efficient manual classification of tremendous aurora images, an automatic aurora images classification system for huge dataset application is proposed. First, static aurora images are decomposed into texture part and cartoon part with a method called Morphological Component Analysis (MCA). Then features extracted from texture part are classified by three...
Adaptive local binary patterns method is proposed in this paper, on which an effective fabric defect detection algorithm is designed. ALBP method selects the frequently occurred patterns to construct the main pattern set, which avoids using the same pattern set to describe different texture structures in uniform local binary patterns method. The features of free defect image are extracted according...
Single-class support vector machines (SC-SVMs) are different from the standard two-class SVM techniques. This algorithm is used to allow the pass through of the only positive data by treating the origin as the only member of the second class. Here, we present an algorithm for rejecting out-of-vocabulary (OOV) phrases. Our method uses SC-SVM mechanism to detect and reject the phrases of OOV. We also...
The object-based attention theory has shown that perception processes only select one object of interest from the world at a time which is then represented for action. This paper therefore presents an autonomous visual perception model for robots by simulating the object-based bottom-up attention mechanism. Using this model visual perception of robots starts from attentional selection over the scene...
This paper introduces a method of hand-raising gestures detection in indoor environments, using shape and edge features. Past approaches have detected the gestures through recognizing the action for isolated or seated persons. Here, to deal with movements, non-rigidity and partially occlusions of human bodies, the gestures are detected by searching for raised hands and arms rather than recognizing...
This paper presents a neural network classifier based on fuzzy ARTMAP with conflict-resolving strategy. The proposed model explicitly resolves overlaps among prototypes of different classes through deploying a contraction procedure in the network, therefore, improving its generalization. Compared with other existing methods, the model has the priority of intuition and no parameter tuning. The performance...
Robust execution of robotic tasks is a difficult learning problem. Whereas correctly functioning sensors' statements are consistent, partially corrupted or otherwise incomplete measurements will lead to inconsistencies within the robot's learning model of the environment. So, methods of prediction (classification) of robot failure detection with erroneous or incomplete data deserve more attention...
This paper aims at automatically detection of car license plates via image processing techniques. The method used is a so-called gentle AdaBoost algorithm which is combined with a cascade structure. The gentle AdaBoost (GAB) algorithm is known to have a higher detection rate and a lower false positive rate than the basic discrete AdaBoost (DAB) which is currently reported being used for the license...
In this paper, a method of ECoG identification based on SVM ensemble was proposed to solve the problems of low classification accuracy and weak robustness for ECoG collection during different period of time. Common spatial pattern (CSP) algorithm is used for feature extraction, and support vector machine (SVM) ensemble is applied for classification of ECoG. Besides, bagging algorithm and cross-validation...
The paper describes a gesture recognition system which can effectively recognize static single-hand gestures and be applied in complex environments. The system involves a vocabulary of 20 gestures consisting of Chinese sign language for certain letters and digits. Segmentation based on color learning and normalization based on image moment invariants are used to extract candidate hand regions. Its...
The Common Spatial Pattern (CSP) algorithm is a popular method for efficiently calculating spatial filters. However, several previous studies show that CSP's performance deteriorates especially when the number of channels is large compared to small number of training datasets. As a result, it is necessary to choose an optimal subset of the whole channels to save computational time and retain high...
Natural language interface is an important research topic in the area of natural language processing (NLP). Natural language interaction with robot could be the most natural and efficient way. In order to build speech enabled human language interface of robots, our research goal is to study the problems in this area and develop technologies that can potentially improve human-robot interaction. In...
Research on thruster fault diagnosis of Underwater Robots (URs) is undertaken to improve its whole system reliability. Based on the BP neural network, a recurrent neural network (RNN) is presented and the network training algorithm is deduced. The RNN is trained by voyage head and yaw turning experiments, and the well trained network is applied to model for the URs. Compared the outputs between model...
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.