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 novel silhouette-based method to estimate 2D human pose. It takes a pre-defined human skeleton model as the prior information and a video sequence as the data source, and estimates human pose in each frame by the following steps: Firstly, the Gaussian Mixture Background Model (GMM) is adopted to extract silhouette from an image and this silhouette will be the human body...
This paper presents approach for an automated surveillance system which performs human detection and tracking across multiple non-overlapping cameras. Emphasis is put at single camera level where motion based segmentation is achieved using optical flow estimation. Feature matching and region-based shape descriptors are used for tracking. The proposed approach then extends feature and region-based...
As sole feature extraction method cannot reflect comprehensive face emotional information in expression recognition, this article proposes one kind expression recognition method based on VLBP and optical flow mixed features. In this method, firstly it extracts block vlbp features of eye region. Then it detects feature points of mouth region automatically and extracts optical flow feature vector of...
We present in this paper a human detection system for the analysis of video sequences. We perform first a foreground detection with a Gaussian background model. A tracking step based on connected components analysis combined with feature points tracking allows to collect information on 2D displacements of moving objects in the image plane and so to improve the performance of our classifier. A classification...
Dynamic textures are temporally continuous and infinitely varying sequences of images with certain spatial and temporal properties and have many potential applications. Such applications usually require dynamic texture segmentation that is not an easy task especially when the background is cluttered and textured. In this paper, we analyze the spatio-temporal slices of dynamic texture using Fourier...
Optical flow estimation is one of the main subjects in computer vision. Many methods developed to compute the motion fields are built using standard heuristic formulation. In this paper, however, we learn a motion model. We develop a hybrid model by combining the learnt model with Markov Random Field (MRF). And then we introduce a method based on "Radial Basis Function Neural Network" (RBF)...
A mura detection approach based on the difference accumulation and background estimation is proposed to detect mura in the thin film transistor liquid crystal display (TFT-LCD) images. We were motivated by wavelet transform to derive a multi-resolution method for accelerating the detecting speed of background estimation. While the visibility of mura depends on inspecting angles and online environmental...
This paper presents a video summarization method to visualize the video object trajectories across multiple cameras in a static image for monitoring the movements of suspicious people in a building. First, we have designed an object association algorithm across multiple stationary cameras, which can be used to build the object trajectories in the building with the assistants of the predefined locations...
Image super-resolution reconstruction (SRR) refers to a signal processing approach which produces a high-resolution (HR) image from observed multiple low-resolution (LR) images. In this paper, we propose a joint MAP formulation combining image registration, blur identification, and SRR together to deal with heavy aliasing in the observed LR images. A cyclic coordinate decent optimization procedure...
This paper proposes subject independent manifold features for dynamic emotion recognition. Facial action features, based on FACs, are firstly embedded into a low-dimensional manifold space using the ISOMAP algorithm, then the manifold features from different subjects are aligned into a global coordinate space by the supervised ISOMAP algorithm for recognition. To validate and evaluate the proposed...
In this paper, we propose a two-level integrated model for accurate 3D tracking of rigid head motion and non-rigid facial animation. At the lowest level, the 2D shape of facial features is robustly extracted using a regularized shape model and a cascade multi-stage algorithm. At the highest level, we estimate both the facial animation and 3D pose parameters via minimizing an energy function comprising...
This paper presents the design and implementation of an approach to creating a single-viewpoint full view panorama photograph from a set of image sequence. To ensure the simplicity for both shooting and stitching, input images are individual frames extracted from a panning video sequence. The ordered approach also proves to be computationally less expensive than the case where input images are disordered...
Motion Compensated Frame Interpolation (MCFI) is a commonly used method to enhance the temporal resolution of video sequences. However, when scene change occurs, there is less temporal correlation between frames, so the interpolation technique can't work well. Moreover, this motion-based method always induces visual artifacts due to incorrect motion vectors. In this paper, firstly a scene change detection...
A novel and convenient multi-camera self-calibration method is proposed in this paper. Different from other calibration methods, our method is done by analyzing human body motion. The only constraint is that several people of different heights are needed to walk around the experimental environment one by one in the calibration period. By this way, two kinds of corresponding points are extracted from...
Blotch is a typical artifact in old films and the detection of them is an important step in film restoration. The existing simplified rank-ordered difference detector achieves higher detection rates by reducing the value of threshold. However, the corresponding higher number of false alarms is undesirable. To maximize the ratio between correct detections and false alarms, this paper proposes an improved...
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.