Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
The intensive annotation cost and the rich but unlabeled data contained in videos motivate us to propose an unsupervised video-based person re-identification (re-ID) method. We start from two assumptions: 1) different video tracklets typically contain different persons, given that the tracklets are taken at distinct places or with long intervals; 2) within each tracklet, the frames are mostly of the...
Fully convolutional neural networks (FCNs) have shown outstanding performance in many dense labeling problems. One key pillar of these successes is mining relevant information from features in convolutional layers. However, how to better aggregate multi-level convolutional feature maps for salient object detection is underexplored. In this work, we present Amulet, a generic aggregating multi-level...
A multi-focus image fusion (MFIF) framework for visual power patrol inspection is proposed in this paper. The traditional MFIF approaches based on redundant transform need lots of computation cost. In this study, the MFIF technique in dual domain is proposed. The proposed method efficiently captures detail informations of images, and reduce memory usage and computing time. The proposed MFIF method...
Recurrent neural networks (RNNs) have shown clear superiority in sequence modeling, particularly the ones with gated units, such as long short-term memory (LSTM) and gated recurrent unit (GRU). However, the dynamic properties behind the remarkable performance remain unclear in many applications, e.g., automatic speech recognition (ASR). This paper employs visualization techniques to study the behavior...
Most Traditional algorithms using only unilateral estimation or bidirectional estimation usually produce poor visual quality because of the fact that the unilateral motion estimation suffers from holes and overlaps and the bidirectional motion estimation suffers from inaccurate motion vector. This paper presents a new improved Frame rate up conversion(FRUC) scheme which combines the unilateral estimation...
Wide Area Motion Imagery (WAMI) are usually taken from unmaned air vehicles at low frame rates, and having very wide ground coverage. These images serve as rich source for many applications like surveillance, urban planing and traffic monitoring. Thus, understanding WAMI imagery exploitation has been gaining more interest recent years. In this paper, we focus on estimating the pose of vehicles in...
We propose a novel multi-view clustering method by learning auto-regression problems under structural constraints and treating the regression coefficients as new feature representations for the cluster partition. In particular, we take the data intrinsic correlation structure into account. Correlated data under one view tend to be also related under another view and are likely to fall into the same...
Recognizing objectionable content draws more and more attention nowadays given the rapid proliferation of images and videos on the Internet. Although there are some investigations about violence video detection and pornographic information filtering, very few existing methods touch on the problem of violence detection in still images. However, given its potential use in violence webpage filtering,...
In this paper we present an effective and fast tracking algorithm, in which object tracking is achieved by solving L2-regularized least square (L2-RLS) problem-s within a Bayesian inference framework. Firstly, we model the appearance of the tracked target with P-CA basis vectors and square templates which make the tracker not only exploit the strength of sub space repre-senation but also explicitly...
This paper presents a new method for object tracking based on global spatial correspondence with the geometric distribution of visual words. “Spatial Pyramid Histogram” - SPH is produced by partitioning the image into increasing sub-blocks and computing histograms of features found inside each sub-block. SIFT descriptors are extracted to represent the object to construct a visual dictionary. A classifier...
In this paper, we propose an incremental orthogonal projective non-negative matrix factorization algorithm (IOPNMF), which aims to learn a parts-based subspace that reveals dynamic data streams. There exist two main contributions. Firstly, our proposed algorithm can learn parts-based representations in an online fashion. Secondly, by using projection and orthogonality constrains, our IOPNMF algorithm...
In this paper, we propose a novel tracking framework, multi-cues spatial pyramid matching (MSPM). Different cues are used to generate a set of probability maps, where the value of each pixel indicates the probability that it belongs to the foreground. Then those probability maps are combined into a single probability map by a weighted linear function. There exist two main contributions. First, a generic...
The task of visual tracking is to deal with dynamic image streams that change over time. For color object tracking, although a color object is a 3-order tensor in essence, little attention has been focused on this attribute. In this paper, we propose a novel Incremental Multiple Principal Component Analysis (IMPCA) method for online learning dynamic tensor streams. When newly added tensor set arrives,...
In off-road simulation, the terrain is being modified as a result of its interaction with the vehicles. Previous methods just deal with relatively small scale terrain inputs. In this paper we describe a large scale dynamic terrain visualization method. The potentially visible portion of the terrain is cached in the form of texture arrays and is rendered from the GPU. The terrain deformation is generated...
In conventional vehicle driving simulation systems, the tracks effect does not alter the terrain surface topology that the tires interact with. In this paper, we propose a dynamic terrain visualization method based on modern Graphic Processing Unit features: vertex texture fetch, framebuffer object extension and shader technology. First, the height map to the initial terrain depth texture directly...
This paper presents a vision-based gesture interface called GIUC for ubiquitous computing environments. A camera mounted on top of screen facing the user is used to capture and interpret the movements of hand gestures for intelligent human computer interactions. We propose a tracking and recognition algorithm combining particle filter algorithms and elastic graph matching to recover gesture parameters...
It is the foundation of developing virtual prototype to construct assembly model. On the basis of that the advantages and disadvantages of the existing assembly model are pointed out through studying on relational models separately, a new virtual assembly model based on scene graphics technology of extensible group node, which is suitable to personal computer, is brought forward. Using this new scene...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.