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.
State-of-the-art video deblurring methods are capable of removing non-uniform blur caused by unwanted camera shake and/or object motion in dynamic scenes. However, most existing methods are based on batch processing and thus need access to all recorded frames, rendering them computationally demanding and time-consuming and thus limiting their practical use. In contrast, we propose an online (sequential)...
Removing undesired reflections from a photo taken in front of a glass is of great importance for enhancing the efficiency of visual computing systems. Various approaches have been proposed and shown to be visually plausible on small datasets collected by their authors. A quantitative comparison of existing approaches using the same dataset has never been conducted due to the lack of suitable benchmark...
Person re-identification is important and challenging parts in a non-overlapping camera network. In this paper, we propose the person re-identification framework which consists of kernel size into convolutional layers considering the person ratio and relationship matrix that train the relationship information related to neighborhoods. Our framework deals with global feature extracted from the whole...
This paper addresses the problem of defocus map estimation from a single image. We present a fast yet effective approach to estimate the spatially varying amounts of defocus blur at edge locations, which is based on the maximum ranks of the corresponding local patches with different orientations in gradient domain. Such an approach is motivated by the theoretical analysis which reveals the connection...
In this paper, we investigate deep neural networks for blind motion deblurring. Instead of regressing for the motion blur kernel and performing non-blind deblurring outside of the network (as most methods do), we propose a compact and elegant end-to-end deblurring network. Inspired by the data-driven sparse-coding approaches that are capable of capturing linear dependencies in data, we generalize...
The conventional methods for estimating camera poses and scene structures from severely blurry or low resolution images often result in failure. The off-the-shelf deblurring or super-resolution methods may show visually pleasing results. However, applying each technique independently before matching is generally unprofitable because this naive series of procedures ignores the consistency between images...
Visual or image-based self-localization refers to the recovery of a camera's position and orientation in the world based on the images it records. In this paper, we deal with the problem of self-localization using a sequence of images. This application is of interest in settings where GPS-based systems are unavailable or imprecise, such as indoors or in dense cities. Unlike typical approaches, we...
Kinect sensörler yakin geçmişte oyun konsollari ile birlikte kendini göstersede nesne takip, patern tanima, nesne ebat kontrolü, engel tanima ve iç mekan haritalama gibi bir çok mühendislik alanida kullanilmaktadir. Kinect sensörü içerdiği RBG kamera ve IR kamera ile ayni anda iki farkli kameradan veri alarak nesneye ait farkli özelliklerin kayit edilmesini sağlamaktadir. Bu bildiride RGB-D sensörlerin...
Activity recognition from first-person (ego-centric) videos has recently gained attention due to the increasing ubiquity of the wearable cameras. There has been a surge of efforts adapting existing feature descriptors and designing new descriptors for the first-person videos. An effective activity recognition system requires selection and use of complementary features and appropriate kernels for each...
This paper focuses on a novel approach for handling radical overhaul of anomalous behavior in a visual surveillance network. The initial objective is online detection of anomalies using a Kernel-based online anomaly detection algorithm. The algorithm will operate onimages collected from a moving camera over a span of space and time. The proposed algorithm established based upon machine learning principles...
Pedestrian detection is considered as an active area of research and the advent of autonomous vehicles for a smarter mobility has spearheaded the research in this field. In this paper, design of a real-time pedestrian detection system for autonomous vehicles is proposed and its performance is evaluated using images from standard datasets as well as realtime video input. The proposed system is designed...
Maximum Entropy (MaxEnt) and Compressive Sensing (CS) are two paradigms that allow good image reconstruction from a low number of measurements. MaxEnt is based on the maximization of entropy while CS uses the minimization of l1 norm of image sparse representation. In this paper, MaxEnt and CS are tested in conditions simulating the acquisition by Single Pixel Camera. The set of measurements is obtained...
We study the problem of deblurring light fields of general 3D scenes captured under 3D camera motion and present both theoretical and practical contributions. By analyzing the motion-blurred light field in the primal and Fourier domains, we develop intuition into the effects of camera motion on the light field, show the advantages of capturing a 4D light field instead of a conventional 2D image for...
Non-uniform blind deblurring for general dynamic scenes is a challenging computer vision problem as blurs arise not only from multiple object motions but also from camera shake, scene depth variation. To remove these complicated motion blurs, conventional energy optimization based methods rely on simple assumptions such that blur kernel is partially uniform or locally linear. Moreover, recent machine...
We present a novel strategy to shrink and constrain a 3D model, represented as a smooth spline-like surface, within the visual hull of an object observed from one or multiple views. This new background or silhouette term combines the efficiency of previous approaches based on an image-plane distance transform with the accuracy of formulations based on raycasting or ray potentials. The overall formulation...
Row-wise exposure delay present in CMOS cameras is responsible for skew and curvature distortions known as the rolling shutter (RS) effect while imaging under camera motion. Existing RS correction methods resort to using multiple images or tailor scene-specific correction schemes. We propose a convolutional neural network (CNN) architecture that automatically learns essential scene features from a...
Scene flow describes the motion of 3D objects in real world and potentially could be the basis of a good feature for 3D action recognition. However, its use for action recognition, especially in the context of convolutional neural networks (ConvNets), has not been previously studied. In this paper, we propose the extraction and use of scene flow for action recognition from RGB-D data. Previous works...
Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-image deblurring, video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a result the best performing methods rely on the alignment of nearby frames. However, aligning images is a computationally expensive and fragile procedure, and methods...
Due to the low weight of monocular camera, monocular Simultaneous Localization and Mapping (SLAM) is an area of popular research and promotes countless applications of micro Unmanned Aerial Vehicles (UAVs), especially in some GPS-denied indoor environments. Nevertheless, the motion of UAVs is often faster and more complex than that of ground-based robots. It would also lead to error accumulation if...
This paper combines three contributions to establish a new state-of-the-art in dynamic scene recognition. First, we present a novel ConvNet architecture based on temporal residual units that is fully convolutional in spacetime. Our model augments spatial ResNets with convolutions across time to hierarchically add temporal residuals as the depth of the network increases. Second, existing approaches...
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.