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 extend the nearest convex hull classifier to Symmetric Positive Definite (SPD) manifolds. SPD manifold features have been shown to have excellent performance in various image/video classification tasks. Unfortunately, SPD manifolds naturally possess non-Euclidean geometry, so existing Euclidean machineries such as the nearest convex hull classifier cannot be used directly. To that...
Application of the benefits of modern computing technology to improve the efficiency of agricultural fields is inevitable with growing concerns about increasing world population and limited food resources. Computing technology is crucial not only to industries related to food production but also to environmentalists and other related authorities. It is expected to increase the productivity, contribute...
Deep convolutional neural networks (CNN) brought revolution without any doubt to various challenging tasks, mainly in computer vision. However, their model designing still requires attention to reduce number of learnable parameters, with no meaningful reduction in performance. In this paper we investigate to what extend CNN may take advantage of pyramid structure typical of biological neurons. A generalized...
In the recent history, kernel methods had established themselves as powerful tools for computer vision. In this paper we introduce an integer image kernel function based on Ramanujan Sums which finds its place in image vision. The paper proves the validity of kernel function theoretically and also shows the application of the kernel in image vision. Ramanujan Sums are based on number theory and hence...
Semantically describing the contents of images is one of the classical problems of computer vision. With huge numbers of images being made available daily, there is increasing interest in methods for semantic pixel labelling that exploit large image sets. Graph transduction provides a framework for the flexible inclusion of labeled data that can be exploited in the classification of unlabeled samples...
Recently, Scientists needs to know the behavior of fish populations in underwater. Previously many algorithms are used but they are suffered in complex textures and low detection rate. This paper proposed a multi threading fuzzy c-mean (MFC mean) approach to detect multi-moving fishes in a noisy and dense condition. In this approach, we combines the multi threaded parallel (MTP) approach and kernel...
Convolutional Neural Network (CNN) is a powerful technique widely used in computer vision area, which also demands much more computations and memory resources than traditional solutions. The emerging metal-oxide resistive random-access memory (RRAM) and RRAM crossbar have shown great potential on neuromorphic applications with high energy efficiency. However, the interfaces between analog RRAM crossbars...
Images taken in low-light environments are often degraded due to camera shake and pixel saturation. In this paper, a motion deblurring method for non-uniform blur is proposed, in which an optimization problem is formulated using a maximum a posteriori approach. In the final deconvolution process, a modified Richardson-Lucy algorithm with regularization is used to reduce ringing artifacts and noise,...
Human activity recognition is a fundamental problem in computer vision with many applications such as video retrieval, automatic visual surveillance and human computer interaction. Sports represent one of the most viewed content on digital tv and the web. Automatically collected statistics of team sports game play represent actionable information for many end users such as coaches and broadcast speakers...
In this paper, we introduce a new public image dataset for Devanagari script: Devanagari Handwritten Character Dataset (DHCD). Our dataset consists of 92 thousand images of 46 different classes of characters of Devanagari script segmented from handwritten documents. We also explore the challenges in recognition of Devanagari characters. Along with the dataset, we also propose a deep learning architecture...
In the automotive industry, there is currently great interest in supporting driver-assist and autonomouscontrol features that utilize vision-based sensing through cameras. The usage of graphics processing units (GPUs) can potentially enable such features to be supported in a cost-effective way, within an acceptable size, weight, and power envelope. OpenVX is an emerging standard for supporting computer...
Bird strikes present a huge risk for air vehicles, especially since traditional airport bird surveillance is mainly dependent on inefficient human observation. Recently, multiple groups have proposed bird monitoring using computer vision to detect birds, determine bird flying trajectories, and predict aircraft takeoff delays. However, the characteristics of bird flight using imagery which should be...
Haze and mist always affect the quality of vision. If an image is suffered from haze or mist, then the object is unclear and the image seems whiter than the original one. There are several haze removal algorithms that can reduce the effect of haze and mist. However, if an image is not suffered from the haze and mist, applying the haze removal algorithm may darken the image. Therefore, in computer...
We explore the efficiency of the CRF inference beyond image level semantic segmentation and perform joint inference in video frames. The key idea is to combine best of two worlds: semantic co-labeling and more expressive models. Our formulation enables us to perform inference over ten thousand images within seconds and makes the system amenable to perform video semantic segmentation most effectively...
It is estimated that 80% of crashes and 65% of near collisions involved drivers inattentive to traffic for three seconds before the event. This paper develops an algorithm for extracting characteristics allowing the cell phones identification used during driving a vehicle. Experiments were performed on sets of images with 100 positive images (with phone) and the other 100 negative images (no phone),...
his article presents a novel systematic methodology for the detection of interest points in 3D point clouds and its corresponding descriptors by using the information of an RGB camera and a structured-light sensor. This is achieved by fusing Speeded-Up Robust Features (SURF) in the image space, and histograms that statistically represent the relationship of three dimensional geometric data around...
Recognizing human action is valuable for many real world applications such as video surveillance, human computer interaction, smart home and gaming. In this paper, we present a method of action recognition based on hypothesizing that the classification of action can be boosted by motion information using optical flow. Emergence of automatic RGBD video analysis, we propose fusing optical flow is extracted...
We develop a new paradigm for designing fully streaming, area-efficient FPGA implementations of common building blocks for vision algorithm. By focusing on avoiding redundant computation we achieve a reduction of one to two orders of magnitude reduction in design area utilization as compared to previous implementations. We demonstrate that our design works in practice by building five 325 frames per...
We introduce methods to estimate infinite-dimensional Region Covariance Descriptors (RCovDs) by exploiting two feature mappings, namely random Fourier features and the Nyström method. In general, infinite-dimensional RCovDs offer better discriminatory power over their low-dimensional counterparts. However, the underlying Riemannian structure, i.e., the manifold of Symmetric Positive Definite (SPD)...
In this paper, we propose an accurate approximation framework for separable edge-preserving filtering. Naïve implementation of edge-preserving filtering, such as bilateral filtering and non-local means filtering, consumes enormous computational costs. Separable implementation of such filters is an efficient approximation method for real-time filtering. The accuracy of the conventional separable representation,...
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.