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 have introduced a hierarchical object categorization method with automatic feature selection. A hierarchy obtained by natural similarities and properties is learnt by automatically selected features at different levels. The categorization is a top-down process yielding multiple labels for a test object. We have tested out method and compared the experimental results with that of...
GMM-SAMT, a new object tracking algorithm based on a combination of the mean shift principal and Gaussian mixture models is presented. GMM-SAMT uses an asymmetric shape adapted kernel, instead of a symmetrical one like in traditional mean shift tracking. During the mean shift iterations the kernel scale is altered according to the object scale, providing an initial adaption of the object shape. The...
This work focuses on the recognition of three-dimensional colon polyps captured by an active stereo vision sensor. The detection algorithm consists of SVM classifier trained on robust feature descriptors. The study is related to Cyclope, this prototype sensor allows real time 3D object reconstruction and continues to be optimized technically to improve its classification task by differentiation between...
In urban environment, pedestrian detection is a challenging task in automotive research, which often suffers from the lack of reliability due to the occurrences of spurious detections. In order to answer multitarget multisensor tracking problem and more specifically pedestrian tracking, we propose to use an algorithm based on a stochastic recursive Bayesian framework also called particle filter. We...
First step in bilateral asymmetry detection in mammographic image analysis is alignment of the left and right breast. Alignment may help radiologists in their search for signs of bilateral asymmetry as well as in comparison of corresponding regions in breasts with a computer aided detection system. Different interpolation methods may be used for breast alignment. We have compared nearest neighbor...
Object tracking plays an important role in video surveillance system. However, in the field of object tracking, complex object motion and object occlusions still remains challenging topics. This paper proposes a Estimation-Correction (EC) object tracking scheme in real scenarios, combining the strength of scale invariant feature transform (SIFT) and mean shift algorithm. The corresponding SIFT features...
Detecting pedestrians is a challenging task, which requires precise localization of pedestrians that appear in images and videos. Window-scanning based detection methods have demonstrated their promise by scanning the image densely with multi-scale detection window. However, an essential and critical issue, i.e., how to fuse these dense detections obtained through pedestrian detector and yield the...
Human detection has always been an important part of computer vision but many implementations lack the real-time performance that real world applications require. This paper presents a real-time implementation of human detection in video using the state-of-the-art histograms of oriented gradients method. Each image in the video sequence is tested at multiple scales using a sliding window. Histograms...
In batch learning all the training examples have to be available at once to train the model, which often leads to slow performance and large memory requirements. Little work has been done in developing incremental object learners. In this paper, we present an incremental method that finds corresponding points of similar object instances, appearing in natural grayscale images with arbitrary location,...
This paper presents an approach to label and track multiple objects through both temporally and spatially significant occlusions. To this end, tracking is performed at both the region level and the object level. At the region level, a kernel based particle filter method is used to search for optimal region tracks which limits the scope of object trajectories. At the object level, each object is located...
Multi-view tracking of objects in video surveillance consists in segmenting and automatically following them through different camera views. This may be achieved using geometric methods, e.g. by calibrating camera sensors and using their transformation matrices. However, in practice the precision of calibration is a major issue when trying to achieve this task robustly. In this paper, we present an...
We propose a nonlinear covariance region descriptor for target tracking. The target object appearance and spatial information is represented using a covariance matrix in a target derived Hilbert space using kernel principal component analysis. A similarity measure is derived, which computes the similarity of a candidate image region to the learned covariance matrix. A variational technique is provided...
Scale-space representation of an image is a significant way to generate features for classification. However, for a specific classification task, the entire scale-space may not be useful; only a part of it is typically effective. Toward this end, we design a data dependent classification kernel function, which is a weighted mixture of kernels defined on individual scales. In order to choose the optimum...
We propose a novel scheme that jointly employs anisotropic mean shift and particle filters for tracking moving objects from video. The proposed anisotropic mean shift, that is applied to partitioned areas in a candidate object bounding box whose parameters (center, width, height and orientation) are adjusted during the mean shift iterations, seeks multiple local modes in spatial-kernel weighted color...
This paper proposes a new tracking algorithm which combines object and background information, via building object and background appearance models simultaneously by non-parametric kernel density estimation. The major contribution is a novel bidirectional learning framework for discrimination between the object and background. It has the following advantages: 1) it embeds background information, unlike...
This paper presents a low-cost tracking algorithm based on multiple multiple fragments, increasing robustness with respect to partial occlusions. Given the initial template representing the desired target, each pixel is classified into a different cluster based on a Mixture of Gaussians (MOG) model, and a set of disjoint fragments is created. The mean vector and covariance matrix of each fragment...
Neuron axon analysis through confocal microscopic image stack is dedicated in visualizing the geometrical features and topological characteristics of the 3D tubular biological objects, to ascertain the morphological properties and reconstruct the connectivity of neurons. This paper proposes a new curvilinear tracking algorithm which initializes a superellipsoid kernel into the tube by fitting the...
A semi-supervised graph-based approach to target detection is presented. The proposed method improves the Kernel Orthogonal Subspace Projection (KOSP) by deforming the kernel through the approximation of the marginal distribution using the unlabeled samples. The good performance of the proposed method is illustrated in a hyperspectral image target detection application for thermal hot spot detection...
Multiple-extremum issue including the well-known ??singularity?? problem is one of the major defects in kernel-based object tracking. This paper studies this important problem and presents a novel approach called section-based tracking (SBT) that is based on the section information provided by the division of the object's weight image. This approach serves to eliminate fake extremal points and make...
Kernel tracking of density-based appearance models is implemented in this paper for real-time object tracking applications. First a ROI, i.e., the region of interest is selected in real-time to create a model. Then the matching and locating of the search object is achieved by using mean-shift algorithm. Experimental results show that this method can find perform object tracking with adaptation to...
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.