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.
Detecting roads using monocular vision is a very challenging task as the detection algorithm must be able to deal with complex real-road scenes. In this paper, we describe an algorithm for general path segmentation. There are three main technical contributions of the approach. First, a path segmentation framework is presented, which formulates road detection as a Bayesian posteriori estimation problem...
The connectivity analysis of spatially highly resolved data results in networks comprising an immense number of nodes and edges which makes it hard or even impossible to investigate the high-dimensional (HD) network as a whole. A solution to this problem is offered by a connectivity-based segmentation of the HD networks into subsets of functionally similar nodes (network modules) that exhibit pronounced...
The relative pose measurement method of the non-cooperative target in space is a problem that should be solved in space on-orbit manipulation. In this paper, we utilize a sensor of Kinect to obtain RGB information for simulating the above process. The scene segmentation and target recognition are achieved by using the method of invariant features and background differences. The recognized target areas...
The difficulty of image blind restoration is the lack of sufficient information of the point spread function to cause the ill-posed problem. In order to achieve satisfactory results of image restoration, and at the same time to speed up the restoration, a Bayesian image blind restoration method based on differential evolution optimization is proposed. Firstly, the Gauss model and Laplace model are...
The intensity of the light observed from every position and direction in a real scene can be modeled as a highdimensional field, namely the plenoptic function. This field codes the radiance information as a function of space, orientation, wavelength, and time. In the scope of depth estimation, several strategies have been developed to obtain a representation of the spatial structure of a scene. However,...
User location is crucial in understanding the dynamics of user activities, especially in relating their online and offline aspects. However, users' social media activities, such as tweets sent, do not always reveal their location. We consider the problem of estimating geo-tags for tweets and develop a comprehensive approach that incorporates textual content, the user's personalized behavior, and the...
In the last three decades there have been many multi-frame image super-resolution (SR) algorithms proposed, but there are still many problems, such as edge blurring, artifacts are existing in the final reconstructed image, and many previous algorithms are sensitive to noise. This paper reviews some typical algorithms and addresses their limitations. In this paper, we propose super-resolution with...
Blur trajectory estimation is the core problem in motion blurring restoring from a single image. Normalized blind deconvolution and Shock filter were employed to estimate the blur trajectory more accurately by image details enhancement and steady state solution of non-monolithic local minimum. To reduce disturbance of noises and patch textures, the bilateral grid filter was utilized. During the iteration...
This paper presents a novel image-reconstruction (IR) method for satellite imagery. To reduce unnatural artifacts, which often appear in existing IR methods, we propose a novel scheme to accurately estimate PSF and a novel regularization for IR. In the PSF estimation, hyper-parameters are estimated to reduce artifacts while improving sharpness based on our new criterion, which employs a residual of...
Detecting stair region and estimating the distance from a camera to stair in a stair image is the fundamental step in the implementation of autonomous stair climbing navigation, as well as alarm systems for vision impaired people. In this paper, a framework is proposed for detecting the stair region from stair image utilizing some natural properties of stair. One unique property of them is, every...
Automatic 2D-to-3D conversion aims to reduce the existing gap between the scarce 3D content and the incremental amount of displays that can reproduce this 3D content. Here, we present an automatic 2D-to-3D conversion algorithm that extends the functionality of the most of the existing machine learning based conversion approaches to deal with moving objects in the scene, and not only with static backgrounds...
An important problem in image smoothing is to reduce noise while preserving sharp edges. In this paper we extend the bilateral filter for better impulse noise suppression and near edge artifacts avoidance. The proposed method weights each pixel prior to bilateral filtering by an extra coefficient that is dependent on a noisiness measurement. Consequently, the influence of noisy pixels can be significantly...
For intelligent vehicle systems, lane detection is still a challenging task because it must cope with various road environments. In this paper, we propose a reliable method with Gabor filters. The proposed approach consists of two step. In the first step, the vanishing-point locations is estimated by the texture feature based method. The key attributes of this method consist of the dominant texture...
We study the performance of a denoising method based on the texture roughness appreciation realized using a semi-local estimation of the scaling exponent. This was previously tested on single look complex images, in terms of the equivalent number of looks (ENL), for quite large homogeneous areas. We establish here the ENL values are better estimated for smaller areas. We show the smoothness parameter...
This paper presents a fast and precious eye detection technique by using gradient value for improve the performance of inside-out camera. The propose methods using gradient vector to estimate a temporary pupil position before using ellipse fitting to detect actual eye position. We collected 280 eye images that capture from our inside-out camera, and apply the proposed method and previous method to...
Distortion in images is a biggest challenge now-a-days. This affects in many areas ranging from photography to medical imaging, astronomy, remote sensing and microscopy. Images get obscured due to many reasons like vibration due to hand movement as well as launch of vehicle (Satellite), Noise in image, Adverse Image/Environment condition, and Quick movement of objects. A technique is required which...
An image restoration scheme using frequency domain estimation to counter the motion blur effect is presented. The blurring process is characterized as a point spread function (PSF), which is further decomposed to a defocusing kernel and a motion kernel. The defocusing kernel, modeled as a Gaussian function, is estimated in the spatial domain while the motion kernel estimation is performed in the frequency...
3D vision is becoming increasingly important, in major motion pictures as well as in home entertainment. Depth map generation plays a major role in 2D-to-3D conversion and acts as a precursory stage to Depth Based Image Rendering (DIBR). This paper presents a novel algorithm for depth map generation using a block based approach. The algorithm is composed of 2 parts: Background depth map generation...
Aggressive Optical Proximity Correction (OPC) has been widely adopted in optical lithography to preserve circuit performance for sub-20nm technology nodes. However, complex mask patterns are output resulting in lower mask manufacturability and large computational time. In this paper, we propose a fast OPC algorithm in which intensity estimation during OPC is improved for better pattern fidelity and...
The additional information approaches, multiple image approaches and the single-image approaches are some of the techniques present for the removal of the haze. The first two methods are expensive one and has high computational complexity. Recently single image approach is used for this de-hazing process because of its flexibility and low cost. Bi-orthogonal wavelet transform is used to obtain the...
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.