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.
Today, there are typically two main approaches for dehazing, that is, enhancing images taken in hazy or foggy conditions. The first method is based on general image enhancement techniques where algorithms such as histogram equalization or Retinex are often used. The second one, uses an image restoration approach through the building of a haze physical model. In this paper, we make the dehazing task...
This paper proposes a new graph-theory-based Euler number computing algorithm. The proposed algorithm only needs to count two bit-quad patterns in the given image, while conventional bit-quad-based algorithms need to count ten. Moreover, by use of the information obtained during processing previous pixels, the average number of pixel checked for processing a bit-quad in the proposed algorithm will...
Point cloud completion is an indispensible process for handling the occlusion problem occurring during the data acquisition. For completion, 3D point clouds generate a much larger searching space than 2D images while searching for the best match for boundary patches. To handle the searching speed bottleneck, this paper proposed a novel optimization algorithm which is called the 3D-PatchMatch algorithm...
Recently sparse coding have been highly successful in image classification mainly due to its capability of incorporating the sparsity of image representation. In this paper, we propose an improved sparse coding model based on linear spatial pyramid matching(SPM) and Scale Invariant Feature Transform (SIFT) descriptors. The novelty is the simultaneous non-convex and non-negative characters added to...
Feature learning plays a crucial role in the successful human action recognition. There has been a number of approaches extracting action features from depth information and 3D skeletal data. However, either the skeleton information or the depth map is not accurate for feature learning unless complex descriptors are carefully designed and embedded. In this paper, we first propose a data sparsification...
Fast foreground extraction is an important and challenging problem. Although GrabCut can perform well in foreground extraction, the average accuracy is not satisfactory, and more importantly, its computational cost is large. In this paper, we propose a fast interactive foreground extraction based on superpixel GrabCut and matting. Specifically, we use a superpixel method to process images in order...
This paper presents a patch-based synthesis framework for lightfield image editing. The core of the proposed method builds upon a patch-based optimization approach. The main contribution of the paper is to extend the versatile patch-based image editing framework to 4D lightfield images and enable many editing applications for them. Specifically, the paper introduces a novel 4D lightfield patch consistency...
Automatic landmark identification is one of the hot research topics in computer vision domain. Efficient and robust identification of landmark points is a challenging task, especially in a mobile context. This paper addresses the pruning of near-duplicate images for creating representative training image sets to minimize overall query processing complexity and time. We prune different perspectives...
Currently, most of the human detection methods are based on low-level features. In this paper, we proposed a middle-level feature generation method based on non-negative matrix factorization (NMF) for human detection. We also proposed an improvement scheme to guarantee that a better middle-level feature can be achieved. The proposed scheme can be applied to a complex background and the experimental...
Object tracking is one of the most important components in numerous applications of computer vision. In this paper, the target is represented by a series of binary patterns, where each binary pattern consists of several rectangle pairs in variable size and location. As complementary to traditional binary descriptors, these patterns are extracted in both the intensity domain and the gradient domain...
There has been an increased interest in the field of abnormal human activity detection to find a good descriptor with a lower computational cost. In this paper, we propose such a Spatio-Temporal Descriptor (STD) based on spatio-temporal features of an image sequence. Proposed descriptor is based on a texture map, known as Spatio-Temporal Texture Map (STTM) and is based on 3-dimensional Harris function...
Tracking unknown objects using adaptive tracking-by-detection approaches are widely used in computer vision. In these approaches, tracking problem is treated as an online classification problem, where the object classifier model is updated in the current frame to be used for classification process in the next frame. One of the approaches is based on Tracking-Learning-Detection (TLD) framework, where...
In this paper, we present an improved version of MOBIL descriptor [1] (Improved MOments based BInary differences for Local description), which introduces two main contributions. The first one is the use of geometric information for the binary test instead of the classical intensity binary test, to get more precision in the description step. The second one is to attribute two bits for each test, to...
Oxy-hemoglobin and deoxy-hemoglobin, main blood chromatophores flowing through the arteries and veins, respectively, reflect sunlight differently. The biggest difference is at a specific wavelength in the visible spectrum. The amount of blood in the arteries varies during cardiac activity. As a result, the skin color changes, but its limits cannot be noticed in heart cycle. The authors present an...
The large amount of SIFT descriptors in an image and the high dimensionality of SIFT descriptor has made problems for large-scale image dataset in terms of speed and scalability. In this paper, we propose a descriptor selection algorithm via dictionary learning and only a small set of features are reserved, which we refer to as TOP-SIFT. We discover the inner relativity between the problem of descriptor...
This paper considers person re-identification issue in intelligent video surveillance systems. The problem is still difficult because of the large-scale search, especially when there are a huge amount of persons in multi-camera network. We propose a spatiotemporal model based on the statistics of space and time information for object tracking among multiple cameras. This model aims to predict the...
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)...
Local feature descriptor plays a fundamental role in many visual tasks, and its rotation invariance is a key issue for many recognition and detection problems. This paper proposes a novel rotation invariant descriptor by ordinal pyramid pooling of local Fourier transform features based on their radial gradient orientations. Since both the low-level feature and pooling strategy are rotation invariant,...
Definition and extraction of local features play a very important role in image retrieval (IR), pattern recognition and computer vision. Fast growth of technology today calls for local features to be as compact as possible toward real-time and limited bandwidth applications. In this paper, we study the problem of representing images in a compact way to achieve low bit-rate transmission while maintaining...
Image Super-resolution (SR) reconstruction techniques based on sparse representation have attracted ever-increasing attentions in recent years, where the choice of over-complete dictionary is of prime important for reconstruction quality. However, most of the image SR methods based on sparse representation fail to consider the discrimination and the redundance of the dictionaries, which lead to obvious...
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.