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.
This paper presents a novel approach for unexpected behavior recognition in image sequences with attention to high density crowd scenes. Due to occlusions, object-tracking in such scenes is challenging and in cases of low resolution or poor image quality it is not robust enough to efficiently detect abnormal behavior. The wide variety of possible actions performed by humans and the problem of occlusions...
This paper presented a new method for scene images classification via Partially Connected Neural Network. The neural network has a mesh structure in which each neuron maintain a fixed number of connections with other neurons. In training, the evolutionary computation method was used to optimize the connection target neurons and its connection weights. The model is able to receive a large number of...
This papers presents a weakly supervised method to simultaneously address object localization and recognition problems. Unlike prior work using exhaustive search methods such as sliding windows, we propose to learn category and image-specific visual words in image collections by extracting discriminating feature information via two different types of support vector machines: the standard L2-regularized...
In this paper we propose a new framework for view-invariant 3D object recognition, based on what we call Visibility Maps. A Visibility Map (VM) encodes a compact model of an arbitrary 3D object for which a set of images taken from different views is available. Representative local invariant features extracted from each image are selectively combined to form a visibility basis, in terms of which an...
Multi-person activity recognition is a challenging task due to the complex interactions between people and the multi-dimensionality of features. This paper proposes a hierarchical and observation decomposed hidden Markov model to classify multi-person activities. In order to give detailed descriptions of people's interactions by different feature scale, states of individual persons and states of interactions...
Two dimensional shape models have been successfully applied to solve many problems in computer vision such as object tracking, recognition and segmentation. Typically, 2D shape models (e.g. Point Distribution Models, Active Shape Models) are learned from a discrete set of image landmarks once the rigid transformations are removed applying Procrustes Analysis (PA). However, the standard PA process...
Visual recognition and detection are computationally intensive tasks and current research efforts primarily focus on solving them without considering the computational capability of the devices they run on. In this paper we explore the challenge of deriving methods that consider constraints on computation, appropriately schedule the next best computation to perform and finally have the capability...
Due to the lack of explicit spatial consideration, existing epitome model may fail for image recognition and target detection, which directly motivates us to propose the so-called spatialized epitome in this paper. Extended from the original graphical model of epitome, the spatialized epitome provides a general framework to integrate both appearance and spatial arrangement of patches in the image...
This paper presents a general approach for recognition of driving maneuvers in advanced driver assistance systems (ADAS). Such systems often rely on the identification of driving maneuvers (overtaking, left turn at intersections, etc.) to improve the prediction of potential collisions or to trigger appropriate support for the driver. The proposed maneuver recognition approach combines a fuzzy rule...
This paper describes an extension of separable lattice 2-D HMMs (SL-HMMs) using state duration models for image recognition. SL-HMMs are generative models which have size and location invariances based on state transition of HMMs. However, the state duration probability of HMMs exponentially decreases with increasing duration, therefore it may not be appropriate for modeling image variations accuratelty...
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...
The correct segmentation of textural pattern into different meaningful regions is one of the most important problems in automatic texture image recognition. In this paper, we presented a variational integration of shape prior statistics into a phase-field based segmentation process. By derivating the new phase field functionals with gradient shape policy, we obtain the interface evolution process...
Embedded hidden Markov model (EHMM) has been applied to many areas due to its excellent features. In this paper, we present a novel method for facial expression recognition by using the EHMM. We use five scales and eight orientations Gabor features to represent the expression image. Further, we use the EHMM to recognize the facial expression. In the EHMM structure, the super states are used to model...
Neuroscience has revealed many properties of neurons and of the functional organization of visual cortex that are believed to be essential to human vision, but are missing in standard artificial neural networks. Equally important may be the sheer scale of visual cortex requiring ~1 petaflop of computation, while the scale of human visual experience greatly exceeds standard computer vision datasets:...
Natural scene categorization (NSC) is an important and challenging task. Several state-of-the-art NSC systems use a codebook of visual terms to characterize images with the statistic of visual word counts. However, some kind of codebook generally tends to be more favorable for characterizing a special scene category, which takes either flat property or salient one. To obtain the good tradeoff performance...
We present a novel and robust system for recognizing two handed motion based gestures performed within continuous sequences of sign language. While recognition of valid sign sequences is an important task in the overall goal of machine recognition of sign language, detection of movement epenthesis is important in the task of continuous recognition of natural sign language. We propose a framework for...
Generative embeddings use generative probabilistic models to project objects into a vectorial space of reduced dimensionality - where the so-called generative kernels can be defined. Some of these approaches employ generative models on latent variables to project objects into a feature space where the dimensions are related to the latent variables. Here, we propose to enhance the discriminative power...
An integrated silhouette with perfect appearance is helpful for gait recognition. However, the silhouettes often have holes or missing parts, because the commonly used motion detection and extraction methods are not always suitable for every case. A robust post-processing strategy is proposed here to refine the raw silhouettes. First, an individual silhouette model which represents the mutual characteristic...
Standard hidden Markov model (HMM) and the more general dynamic Bayesian network (DBN) models assume stationarity of state transition distribution. However, this assumption does not hold for many real life events of interest. In this paper, we propose a new time sequence model that extends HMM to time varying scenario. The time varying property is realized in our model by explicitly allowing the change...
Hidden Markov Model (HMM) based human action recognition (HAR) has been broadly adopted by HAR community. However, existing works donpsilat pay attention to the relationship between the layout of the model and the property of human action. In this paper, a novel HAR method is proposed based on the assumption that human action can be essentially recognized by three key postures located around the initial,...
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.