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.
Many computer vision applications adopting consumer depth cameras have recently received much attention due to the availability at low prices and the potential benefits to provide more useful information, which can result in a higher accuracy (e.g., for object recognition). In this work, to address the problem of drinking activity recognition in vision-based Ambient Assisted Living by using depth...
With the proliferation of Internet of Things (IoT) devices such as smartphones, sensors, cameras, and RFIDs, it is possible to collect massive amount of data for localization and tracking of people within commercial buildings. Enabled by such occupancy monitoring capabilities, there are extensive opportunities for improving the energy consumption of buildings via smart HVAC control. In this respect,...
In various real-world applications of distributed and multi-view vision systems, the ability to learn unseen actions in an online fashion is paramount, as most of the actions are not known or sufficient training data is not available at design time. We propose a novel approach which combines the unsupervised learning capabilities of Hierarchical Dirichlet Processes (HDP) with Temporal Self-Similarity...
This paper presents a model of monitoring method in videos and imagines. In the case of a fixed camera, when moving object appears, all data indicating object movement will change greatly. The real moving target will be detected after processing the data which larger change. The accuracy and instantaneity of will be tested by MATLAB stimulation.
Based on the analysis of the existing opinion mining techniques, mining accuracy and complexity, this paper proposes a opinion mining system which mines useful opinion information from camera reviews by utilizing Semantic Role Labeling (SRL) and polarity computing method. Feature lexicon and sentiment lexicon are constructed to mine features and emotional items. In the end, the comparison between...
This paper addresses the multimodal nature of social dominance and presents multimodal fusion techniques to combine audio and visual nonverbal cues for dominance estimation in small group conversations. We combine the two modalities both at the feature extraction level and at the classifier level via score and rank level fusion. The classification is done by a simple rule-based estimator. We perform...
An effective approach to extracting geometric information of scenes from a single uncalibrated image is presented in this paper. Without any prior knowledge of the camera, we describe how to employ cross ratio to compute the length of a line segment on plane surface, while only the length(s) of the certain segment(s) is/are known. Real images of indoor and outdoor scene tests validate our approach.
We propose a camera-based online signature verification system. Time-series images are obtained from a camera while a signature is being written. Then, online signature data are obtained by tracking the pen tip from these images with a particle filter (sequential Monte Carlo). The proposed system has an advantage that special devices such as an electronic tablet are not necessary. In this system,...
We propose a localization system based on artificial landmarks and omnidirectional vision for agricultural vehicle navigation. The system sets four red artificial landmarks as a rectangle in the corners of an operating spot and estimates an absolute position. This paper introduces an algorithm in which red landmark pixels beyond the threshold were extracted as a small area and the center of gravity...
The paper presents a combination calibration method of digital cameras based on the ten-parameter model and the finite element model. The predictable distortion errors can be compensated with the ten-parameter model while the unpredictable ones compensated with the finite element model. A calibration experiment has been carried out on the metric camera Inca3 and non-metric cameras Canon 5D Mark II...
Without the ground truth image, there is no proper objective method to evaluate sprite generation. In this paper, we propose several complex camera motion patterns to generate synthetic video from original images. Our camera motion patterns include rotation, affine, and pan-tilt-zoom (PTZ) transformations. In addition, they also include combined patterns. Subsequently, we applied sprite generation...
This paper presents the results of the crowd image analysis challenge of the Winter PETS 2009 workshop. The evaluation is carried out using a selection of the metrics developed in the video analysis and content extraction (VACE) program and the classification of events, activities, and relationships (CLEAR) consortium. The evaluation highlights the detection and tracking performance of the authors'...
This paper describes a simple method for classifying the condition of morning and afternoon measurement of eye movement based on the Fuzzy rule, the first step to find the relation between eye movement and fatigue. The eye movement is taken by camera and processed by computer. The left eye pupil center coordinates are used as eye movement data. These coordinates are extracted to obtain their features...
The process of creating photorealistic 3-dimensional computer graphic (3DCG) images is divided into two stages, i.e., modeling and rendering. Automatic rendering has gained popularity, and photorealistic rendering is generally used to render different types of images. However, professional artists still model characters manually. Moreover, not much progress has been achieved with regard to 3-D shape...
This paper proposes a reliable solution to the problem of estimating the motion of a rigid object moving freely in 3D space, through the use of a passive vision system. The feature-based tracking technique builds upon the selection of a consistent set of features and their tracking on a frame-by-frame basis. A thorough investigation is conducted to determine a proper vision system setup, which results...
The paper introduces an absolute orientation detection method for spherical motor based on machine vision. The code generation algorithm, image processing algorithm, image matching algorithm and the method of deriving the orientation of the rotor using unit quaternion are presented. The color pattern painted on the surface of the rotor and camera model are simulated in OpenGL .With the machine vision...
This paper proposes a block-based approach to the problem of image registration for detecting camera motion in the presence of moving objects, intended for application in the area of video inpainting for the film industry. The method of aggregating search results on individual blocks during the registration offers a simple and effective way to isolate the background transform, as well as offering...
This paper presents a method to create an illusion of seeing moving objects through occluding surfaces in a video. This illusion is achieved by transferring information from a camera viewing the occluded area. In typical view interpolation approaches for 3D scenes, some form of correspondence across views is required. For occluded areas, establishing direct correspondence is impossible as information...
A simple flexible technique is proposed to easily calibrate five intrinsic parameters a camera based on the three side lengths of a triangle. The technique only requires taking the template with a triangle, and matching the three vertices of the triangle between the template and its image. Analytical solution is given to guarantee algorithm accomplishment successfully. The essential relations for...
This paper proposed a biometric identification system through 2D fingers' geometry measurements. The hand image captured from digital camera was first preprocessed to segment hand and its contour out from background. Then the finger tops and valleys were located by tracking out the maximum and minimum radial distances to a wrist reference point. The geometry features of index, middle, ring and little...
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.