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.
Compressed domain human action recognition algorithms are extremely efficient, because they only require a partial decoding of the video bit stream. However, the question what exactly makes these algorithms decide for a particular action is still a mystery. In this paper, we present a general method, Layer-wise Relevance Propagation (LRP), to understand and interpret action recognition algorithms...
For recognizing human actions in video sequences, it is necessary to extract sufficient information which can represent motion features. In recent years, dense trajectories based action recognition algorithms attract more attention for containing rich spatio-temporal information. However, these algorithms are always faced with cluttered background. To solve this problem, we involve object tracking...
Our daily life is more convenient than ever before because of the great progress of science and technology. However, the body building or fitness are always ignored in modern daily life. In this paper, we propose a Virtual Personal Trainer to provide real time visually action guide and action assessment during the fitness time of users via the Microsoft Kinect Sensor. The user actions are captured...
In this work human action recognition problem was discussed in video sequences. Solution of the problem was studied in three stages. Firstly, points of interest were detected with preproccesing and these points which are called cuboids were declared in small windows, then feature extraction was performed and finally, human action is decided by using classification. Features extraction is not only...
This paper describes our algorithms for players tracking and ball detection for an automatic broadcast tennis video annotation. The system detects and tracks the players using a robust non-parametric procedure for estimating density gradients called the mean shift algorithm. The basic mean shift tracking algorithm assumes that the target object has to separate sufficiently from background, but this...
Action recognition is an important research issue in intelligent surveillance and many other automatic video systems. In this paper, we describe a novel method for the human action recognition from its silhouette in the video. In the algorithm, diffusion maps is used for dimensionality reduction as well as to preserve much of the geometrical structure. A global geometry and local temporal similarity...
A foreground extraction algorithm based on background subtraction and edge detection was proposed to obtain the foreground with a little change. An action classification method based on Enhanced Gait Energy Image (EGEI) and Locality Preserving Projections (LPP) was used. The high dimensional feature space was non-linearly reduced to lower dimensional space, which outperformed PCA and 2DPCA. The nearest-neighbor...
A number of action recognition methods make use of spatio-temporal features. These features often consist of local spatio-temporal descriptors centered at locations provided by an interest point detector. The extracted descriptors will then serve as input to classification algorithms. The correct scale of these descriptors is an essential parameter to be determined. Improved information quality has...
An action can be represented as a sequence of salient postures. Effective modeling of the salient postures is critical for robust action recognition. This paper proposes to characterize the salient postures using a set of the spatio-temporal interesting points (STIPs). Local features are extracted at each STIP and the statistical distribution of the features for each salient posture is further modelled...
A new feature description is used for human behaviour representation and recognition. The feature is based on Radon transforms of extracted silhouettes. Key postures are selected based on the Radon transform. Key postures are combined to construct an action template for each sequence. Linear discriminant analysis (LDA) is applied to the set of key postures to obtain low dimensional feature vectors...
This paper describes a method for action recognition using a classification algorithm based on mixtures of von Mises distributions processing action signatures. An action signature is a ID sequence of angles, forming a trajectory, which are extracted from a 2D map of adjusted orientations (subtracting the average orientation) of the gradient of the motion-history image. To obtain the action signature,...
In this paper, we address the problem of representing human actions using visual cues for the purpose of learning and recognition. Traditional approaches model actions as space-time representations which explicitly or implicitly encode the dynamics of an action through temporal dependencies. In contrast, we propose a new compact and efficient representation which does not account for such dependencies...
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.