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.
Improving the precision of shot boundary detection is very important. This paper presents an algorithm for shot boundary detection based on SVM (support vector machine) in compressed domain. It uses the features, such as the type of macroblock, the difference between DC coefficients of two co-located blocks in successive frames and the type of frame, to segment a video into the shots by classifying...
We construct Kernel Co-occurrence Matrices (KCMs) to represent the target model and the target candidates. Then those matrices are employed as the tracking cues in mean shift framework. Some improvements are presented in the implementation of the algorithm. First, the angle relation between pixel-pairs is redefined to depict the asymmetric characteristic of the object. Second, the KCMs of the target...
Motivated by the non-linear manifold learning ability of the kernel principal component analysis (KPCA), we propose in this paper a method for detecting human postures from single images by employing KPCA to learn the manifold span of a set of HOG features that can effectively represent the postures. The main contribution of this paper is to apply the KPCA as a non-linear learning and open-set classification...
Spatiogram were generalization of histograms, which can harvest spatial information of images. In this paper, we address the object tracking problem using spatiogram as feature descriptor. We use an improved spatiogram similarity measure which is recently proposed. Based on the measure, we derive a kernel tracking algorithm utilizing mean shift procedure. We test our tracking algorithm on several...
In this paper, a method for real-time tracking of moving targets is proposed. The particle filter and mean shift technical for color-based tracking is used. The traditional tracker always focuses on how to track with the object robustly in a short period of time. Most of them modify the model after the tracking is finished in current frame. But in long time tracking, the object model is changing continuously...
Object detection is an important function for intelligent multimedia processing, but its computational complexity prevented its pervasive uses in consumer electronics. Cost-effective & energy-efficient computations are now available with various innovative multicore architectures proposed for embedded systems. However, extensive software optimizations are needed to unravel the inherent parallelisms...
In this paper we implement a wireless vision based object tracking system with wireless surveillance camera which uses a novel color based object tracking algorithm designed to work on any non-ideal environment. The implementation of the kernel-based tracking of moving video objects based on the CAMSHIFT algorithm is presented. We show that the algorithm performs exceptionally well on moving objects...
The mean-shift algorithm is very useful in object tracking for its many advantages, such as good performance in real-time tracking, nonparametric density model, etc. Although the scale of the mean-shift kernel is a crucial parameter, there exists presently still no clear mechanism in choosing or updating the scale when the kernel of changing size is tracked. In this paper, a new method is introduced...
This paper proposes an efficient approach for object classification. This method bases on bag-of-features classification framework and extends the limits of it. It applies modified spatial PACT as local feature descriptor, which can efficiently catch image patch's characteristic. In order to address the speed bottleneck of codebook creation, extremely randomized clustering forest is used to create...
The strategies for the preservation of historical documents can include their digitization, which is an effective way to make them publicly available while preventing degradation of the original sources. The Arquivo Publico Mineiro (APM), the Archives of the State of Minas Gerais, has a collection of historical photographs from Brazil, and some of them have been digitized. The availability of digital...
The paper presents a method for efficient text detection in unconstrained environments, based on image features derived from connected components and on a classification architecture implementing a focus of attention approach.The main application motivating the work is container code detection with the final goal of checking freight trains composition. Although the method is strongly influenced by...
In this paper, a new integrated particle filter is proposed for video object tracking. After particles are generated by importance sampling, each particle is regressed on the transformation space where the mapping function is learned offline by regression on pose manifold using Lie algebra, leading to a more effective allocation of particles. Experimental results on synthetic and real sequences clearly...
In this paper we present a combined approach for object localization and classification. Our contribution is twofold. (a) A contextual combination of localization and classification which shows that classification can improve detection and vice versa. (b) An efficient two stage sliding window object localization method that combines the efficiency of a linear classifier with the robustness of a sophisticated...
Context is critical for minimising ambiguity in object detection. In this work, a novel context modelling framework is proposed without the need of any prior scene segmentation or context annotation. This is achieved by exploring a new polar geometric histogram descriptor for context representation. In order to quantify context, we formulate a new context risk function and a maximum margin context...
Our objective is to obtain a state-of-the art object category detector by employing a state-of-the-art image classifier to search for the object in all possible image sub-windows. We use multiple kernel learning of Varma and Ray (ICCV 2007) to learn an optimal combination of exponential χ2 kernels, each of which captures a different feature channel. Our features include the distribution of edges,...
We present methods for training high quality object detectors very quickly. The core contribution is a pair of fast training algorithms for piece-wise linear classifiers, which can approximate arbitrary additive models. The classifiers are trained in a max-margin framework and significantly outperform linear classifiers on a variety of vision datasets. We report experimental results quantifying training...
We present an algorithm for detecting human actions based upon a single given video example of such actions. The proposed method is unsupervised, does not require learning, segmentation, or motion estimation. The novel features employed in our method are based on space-time locally adaptive regression kernels. Our method is based on the dense computation of so-called space-time local regression kernels...
Many recent visual recognition systems can be seen as being composed of multiple layers of convolutional filter banks, interspersed with various types of non-linearities. This includes Convolutional Networks, HMAX-type architectures, as well as systems based on dense SIFT features or Histogram of Gradients. This paper describes a highly-compact and low power embedded system that can run such vision...
This paper examines the problem of moving object detection. More precisely, it addresses the difficult scenarios where background scene textures in the video might change over time. In this paper, we formulate the problem mathematically as minimizing a constrained risk functional motivated from the large margin principle. It is a generalization of the one class support vector machines (1-SVMs) to...
In this paper, we propose a method for fast pedestrian detection in images/videos. Multi-scale orientated (MSO) features are proposed to represent coarse pedestrian contour, on which Adaboost classifiers are trained for pedestrian coarse location. In the fine detection, histogram of oriented gradient (HOG) features and SVM classifiers are employed to precisely classify pedestrians and non-pedestrians...
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.