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.
Lateral localization of an autonomous vehicle within its lane is major information for its adequate control and navigation. Computer vision and robotics communities have used primarily images to Bird's Eye View for easier data manipulation than perspective image. Nevertheless, this technique usually assumes that the terrain is flat and needs calibration for its transformation matrix. In this paper...
Tracking-by-detection based on online learning has shown superior performance in visual tracking of unknown objects. However, most existing approaches use a fixed-size box to represent objects and can merely show the unoccluded area of the object. To overcome the limitations, we propose a novel tracking-by-detection approach based on local patches. We extend ferns forest to visual tracking and optimize...
This paper presents an efficient feature detection algorithm based on the classical SURF (Speeded Up Robust Feature) detector. The image features are represented and scored with respect to its local symmetry property. The local symmetry has natural properties of scale and transformation invariants, and also insensitive to illumination change and local noise. By the proposed feature descriptor, the...
The importance of choosing a suitable feature detector and descriptor to find the optimal correspondence between two sets of image features has been highlighted. In this direction, this paper presents an evaluation of some well known feature detectors and descriptors; including HARRIS-FREAK, HESSIAN-SURF, MSER-SURF, and FAST-FREAK; in the search for an optimal detector and descriptor pair that best...
A new color attention preserved sparse generative object model is proposed to handle occlusion and illumination variations in the visual tracking task. The color attention is represented by the fast calculated color descriptor on color names, which is used to weight the similarity measurement of the sparse generative model. In the sparse generative model, the image region of the object is divided...
This paper proposed a new improved singular value decomposition method to achieve high accuracy and much more number of correct point correspondences between uncalibrated images with large scene variations. The proposed matching method is based on singular value decomposition and Sift feature descriptor. The proximity matrix for decomposition is redefined to improve the performance of robustness and...
This paper presents a novel procedure for localizing text on scene photos. It takes advantage of the fact that text should present some contrast in comparison with the background, in order to be distinguished by the human eye. A procedure of binarization is applied in order to create appropriate images for the text detection. The connected components of the image are extracted and some heuristic rules...
The problem of viewpoint changes is an important issue in the study of human action recognition. In this paper, we propose the use of spatial features in a spatiotemporal self-similarity matrix (SSM) based on action recognition that is robust in viewpoint changes from depth sequences. The spatial features represent a discriminative density of 3D point clouds in a 3D grid. We construct the spatiotemporal...
To understand the human action in still images, it is effective to detect the human region. However, since appearance of human is much different due to pose and occlusion, the detection is quite difficult. Here we propose robust human detection method to pose and occlusion using Bag-of-Words (BoW). In general, the location information is helpful in classification. When the human has occlusion and...
As an increasing number of digital images are generated, a demand for an efficient and effective image retrieval mechanisms grows. In this work, we present a new skeleton-based shape retrieval algorithm, which starts by drawing circles of increasing radius around skeleton points. Since each skeleton corresponds to the center of a maximally inscribed circle, this process results in circles that are...
In recent years, deep models offer a promising solution to extract powerful features. Motivated by the effectiveness of the Convolutional Networks (ConvNets) model in image classification and object detection, we present a visual tracking algorithm using the ConvNets model to extract multistage features. The key point of this paper is to show that the multi-stage features extracted by the ConvNets...
This article presents an improved feature matching method based on gradient constraint. SIFT is regarded as one of the most powerful features because of the conspicuous invariance of image rotation, noise and illumination. However, there will still be many mismatches when SIFT features are matched across images, especially when the amount of features is very large. In order to reduce the number of...
This paper present a discriminative sparse point matching method (DSPM) for tracking generic objects in vision applications. Different from the conventional tracking methods that involves the construction of high-level or self-learning features, DSPM particularly focuses on a optical flow based point matching optimization method for overcoming the variation of object deformation in motion. The algorithm...
Computer vision systems are being introduced in pre-screening of cervical cytopathology slides to identify samples that require study by cytopathologists. These systems work on the principle of imaging and analysis of cytology features in general and nuclear features in particular. Thus accurate localization and segmentation of the nuclei is crucial for the systems. Though several methods have been...
This paper presents an emotional gesture recognition system that is robust to dark illumination condition. This system employs a Kinect sensor to get a bright infrared image sequence in a dark environment and extract dense corner feature trajectories to capture spatio-temporal regions of interest. Furthermore, this system adopts bag-of-features (BOF) to represent a gesture and uses support vector...
This paper proposes a new method for tracking with accurate scale estimation using motion vector errors. First we estimate an object displacement vector using the set of inlier motion vectors(VMF) filtered out by Median Flow tracker [2]. Then we calculate each motion vector error, i.e. the distance between each VMF and the estimated object displacement vector. 50 percent of VMF with large motion vector...
A sparse feature-based motion segmentation algorithm for RGB-D data is proposed which offers us a unified way to handle outliers and dynamic scenarios. Together with the pose-graph SLAM framework, they constitute an effective and robust solution that enable us to do RGB-D SLAM in wide range of situations, although traditionally they have been divided into different categories and treated separately...
Since feature extraction not only plays a key role, but also have a great effect on image analysis and registration. In this paper, we evaluate a comparative performance of three point feature extraction algorithm such as SIFT, SURF and BRISK. The experimental results show that SURF exhibited a better significant results on extracting point features and matching time, compared to SIFT and BRISK. The...
Natural markers are increasingly being adopted by the Augmented Reality (AR) community. These systems require several steps of data processing to be carried out with the aim of allowing a less parameterized image be recognized by the computer system. Among the possibilities for this task there are the proposals that employ interest points (or feature points). The steps needed to process the natural...
While much progress has been made for object tracking in recent years, it is still a challenging problem to handle large change in motion, appearance, scale and pose variation. One of the main reasons is the lack of effective representation to account for appearance variation. For this issue a flexible method based on superpixel segmentation is applied to divide an image into several patches. Besides,...
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.