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.
Low-rank and sparse representation based methods have attracted wide attention in background subtraction and moving object detection, where moving objects in the scene are modeled as pixel-wise sparse outliers. Since in real scenarios moving objects are also structurally sparse, recently researchers have attempted to extract moving objects using structured sparse outliers. Although existing methods...
Diminished reality (DR) is a technique to remove or inpaint real objects in a display. While DR is one of the active topics in the ISMAR community, a fair comparison between existing or emerging DR methods is difficult, that is, many methods rely on subjective evaluation that uses their own results to demonstrate their advantages. We, therefore, present a common dataset as a basis of the research...
We present a method for generating images in which people are hidden from image sequences taken with a hand-held camera. Our method is basically used for privacy protection of people whose images are unintentionally captured in image sequences. We hide people from images by reconstructing a 3D model of background and projecting it to 2D images. By detecting the area in which people are present beforehand,...
We introduce a novel formulation of temporal color constancy which considers multiple frames preceding the frame for which illumination is estimated. We propose an end-to-end trainable recurrent color constancy network – the RCC-Net – which exploits convolutional LSTMs and a simulated sequence to learn compositional representations in space and time. We use a standard single frame color constancy...
Rain deteriorates outdoor vision and causes challenge for most vision based intelligent systems. In this paper we propose a method to efficiently remove the rain present in light field data. Firstly, the sub-view image sequence is globally aligned to the central view. Robust Principle Component Analysis (RPCA) are then applied to decompose the sequence into two parts, i.e., the low-rank data, and...
In this paper we consider critical motion sequences (CMSs) of rolling-shutter (RS) SfM. Employing an RS camera model with linearized pure rotation, we show that the RS distortion can be approximately expressed by two internal parameters of an imaginary camera plus one-parameter nonlinear transformation similar to lens distortion. We then reformulate the problem as self-calibration of the imaginary...
Since several years most glaciers all over the world are showing increasing retreat, thinning and acceleration. To understand and model the phenomena as well as to predict the future development of ice fields and glaciers, glaciologists need different data that describe the glaciers condition. Therein, an important issue is the determination of velocity fields. These can be derived using remote sensing...
A non-destructive testing method for internal defects detection is desperately needed due to wide and increasing application of composite insulators in the power grid. In this study, a novel approach based on pulsed infrared thermography was investigated with the aim of testing and evaluating the state of composite insulators. In pulsed infrared thermography, an external source of energy is required...
This paper studies monocular visual odometry (VO) problem. Most of existing VO algorithms are developed under a standard pipeline including feature extraction, feature matching, motion estimation, local optimisation, etc. Although some of them have demonstrated superior performance, they usually need to be carefully designed and specifically fine-tuned to work well in different environments. Some...
In the field of aerial surveillance, tracking targets in images is complicated by the possible motion of the camera, especially if frame differencing is used to detect moving objects. We propose in this paper to exploit the high similarity in sequences acquired from a nearly static camera. In this case distance maps grown from image edge points share many similarities and T-junctions of distance map...
Image stitching with large parallax has long been an important and challenging issue in computer graph and vision. Most studies focused on finding the best-fitting homography to align and seam the input images. Images with large parallax can not be mapped over the whole overlapping regions or aircrafts like ghosting and distortion may occur. In this paper, We combine the global 2D homography method...
The paper introduces an accurate solution to dense orthographic Non-Rigid Structure from Motion (NRSfM) in scenarios with severe occlusions or, likewise, inaccurate correspondences. We integrate a shape prior term into variational optimisation framework. It allows to penalize irregularities of the time-varying structure on the per-pixel level if correspondence quality indicator such as an occlusion...
Obstacle removal is a classic problem in image processing. Because the content behind obstacle can't be deduced only from one image, we introduce a motion obstacle removal problem from an image sequence. It is regarded as a sparse problem with the obstacles as noise. First we match the images with image features to transform the images to the same camera coordinate system. The features of motion objects...
Background modeling and subtraction are essential to video surveillance applications. There are two main issues related to background modeling: how to initialize the background model, and how to update the model based on observations. In this paper, we consider the first issue with the aim of generating a clear background image that does not contain foreground objects or noise. We used a bidirectional...
High dynamic range (HDR) imaging is highly demanded in computer vision algorithms. An HDR image is composed with several low dynamic range (LDR) images, which usually have some disparities. In many HDR imaging algorithms, the disparities are estimated based on the texture information of the LDR images. However, the texture information is often lost completely if scenes include extremely bright and...
Appearance-based action recognition can be considered as a natural extension of appearance-based object detection from the spatial to the spatio-temporal domain. Although this step seems natural, most action recognition approaches are evaluated in isolation. Towards this end the contribution of this paper is twofold. First, a view-independent approach to action recognition is proposed and second the...
People re-identification is a difficult problem in non-overlapping video surveillance, because pedestrian images contain variations in view angle, lighting, background clutter and occlusion. This paper presents an approach for person re-identification in surveillance system by taking pedestrian sequence (set) as processing element. The distance metric is learnt from relative and irrelative set-to-set...
3D object categorization is a non-trivial task in computer vision encompassing many real-world applications. We pose the problem of categorizing 3D polygon meshes as learning appearance evolution from multi-view 2D images. Given a corpus of 3D polygon meshes, we first render the corresponding RGB and depth images from multiple viewpoints on a uniform sphere. Using rank pooling, we propose two methods...
We propose a method for detecting obstacles by comparing input and reference train frontal view camera images. In the field of obstacle detection, most methods employ a machine learning approach, so they can only detect pre-trained classes, such as pedestrian, bicycle, etc. This means that obstacles of unknown classes cannot be detected. To overcome this problem, we propose a background subtraction...
We present a camera array based plenoptic image acquisition system and re-focus algorithms for the plenoptic image data acquired using the system. In order to get time-synchronized images with a high resolution of up to 1920 by 1080, we integrated 25 industrial cameras with an external exposure synchronization devices. By using industrial cameras with precise time synchronization functionality, we...
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.