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.
In a previous publication by the same authors, a computational design system was described that identifies aesthetical color combinations. In that work the type of color aesthetics pursued was to be determined prior to the design representing a given design objective. Complementing the previous study, in this work, the type of color aesthetics that is most suitable for a given scene at hand is pursued...
Convolutional Neural Networks have been performing exceptionally well for the recognition of worldly objects and there are various trained models available which can give you the class of an object if an image of the object is fed as their input. But, we can also retrain an already trained model for anotherset of classes of our interest and we have retrained such a model to check the severity of Diabetic...
In this paper we study single image haze removal techniques on outdoor images for visibility enhancement in foggy weather conditions. Haze removal techniques based on dark channel prior model have used different filters for estimating the transmission. We have studied effect of using different filters along with the fundamental mean and gaussian filters in the visibility enhancement in foggy conditions...
We propose a stereo vision based obstacle detection and scene segmentation algorithm appropriate for autonomous vehicles. Our algorithm is based on an innovative extension of the Stixel world, which neglects computing a disparity map. Ground plane and stixel distance estimation is improved by exploiting an online learned color model. Furthermore, the stixel height estimation is leveraged by an innovative...
Attitude estimation is essential for various types of vehicles, especially aerial and underwater vehicles. Many of those vehicles rely on onboard inertial mechanical units (IMUs) to estimate its attitude, and some incorporate further algorithms, such as Kalman Filter, to improve the estimation and thus the stability. However, drifting estimation from gyroscope and corrupted estimation from accelerometer...
Astrophysicists rely on crowd sourced initiatives to classify galaxies in large surveys. The next generation of telescopes will lead to a revolutionary increase in the amount of unlabelled data available to astrophysicists making crowd sourcing infeasible. To cope with this significant increase in data astrophysicists will need unsupervised techniques. In this paper we show that a model using unsupervised...
In this article, we propose a new optimized embedded architecture based soft-core processors oriented to visual attention based object recognition applications. Our recognition approach relies mainly on two specific modules for online processing of acquired images in real-time: a novel saliency based feature detector/descriptor module and then an object classifier module. To deal with such parallel/pipeline...
The proof of human parts has an imperative effect on pose evaluation, and can be effortlessly confused with difficult background due to indefinite part detector. This paper circumvents this predicament by performing a proof supporting approach, where each part also receives confidence from its neighborhood which uses the outline information between connect parts and mitigates the risk of being blindly...
Existing methods of texture generation from registered images only work well on accurate models. For inaccurate models, texture drifts may occur. In this paper, we propose a view-dependent seamless texture generation method for inaccurate models. Under a specific viewpoint, this method first assigns each mesh face with a label associated with a registered image to generate a primitive texture. Different...
In view of the main problems existed at present in no-reference (NR) natural image quality assessment (IQA), This paper proposes a more general-purpose, efficient and integrated resolution based on visual cognitive mechanism. Firstly, it puts forward a inspiring visual cognitive computing model (IVCCM) based on visual heuristic principles. Secondly, it presents a asymmetric generalized Gaussian mixture...
A new spatiotemporal saliency detection model is presented in this paper. Instead of previous works which combine the image saliency in the spatial domain with motion cues to build their video saliency model, we propose to apply the pattern mining algorithm. From initial saliency maps computed in spatial and temporal domains, discriminative saliency patterns can be recognized and used to detect pertinent...
Fast and accurate detection of human skin color is an important task in computer vision and image processing applications. Skin color detection algorithms are vital in medical application, especially in diagnosing skin diseases. This paper presents an approach for defining an explicit skin model by determining the optimal skin color regions in the selected color space. During the optimization, the...
Due to the advancement in multimedia technology, the images and videos play a major role in day today life. How the humans are looking into the image? The computational models of visual attention used in many of the computer vision tasks such as image segmentation, object recognition, image understanding, etc. The proposed method aims to construct visual saliency model with the help of the center...
In this paper, a new method for mapping textures onto a 3D model produced by a multi-view reconstruction pipeline is proposed. A Markov Random Field (MRF) is constructed so as to define each triangle face as a node. An optimal labeling is estimated by globally minimizing an energy function defined on the MRF using graph cuts algorithms. This labeling assigns exactly one view to each triangle face...
Saliency detection aims to focus attention on the important parts of a map, which is an excellent ability of human visual system. In this paper, we present a saliency detection model based on the principle that the pixels belong to the background are more disperse than the ones of the target area. Color contrast in different channels is employed to classify the pixels. Our method outperformed five...
Recently, the use of object proposals has been much introduced in the field of salient object segmentation methods. Object proposal methods provide a limited set of proposals per image which can successively be analyzed on their saliency. In this context, we regard saliency map computation as a regression problem and we used object proposals (selective search) to compute the saliency map. Our method...
Style transfer is an important task in which the style of a source image is mapped onto that of a target image. The method is useful for synthesizing derivative works of a particular artist or specific painting. This work considers targeted style transfer, in which the style of a template image is used to alter only part of a target image. For example, an artist may wish to alter the style of only...
Accurate segmentation of humans from live videos is an important problem to be solved in developing immersive video experience. We propose to extract the human segmentation information from color and depth cues in a video using multiple modeling techniques. The prior information from human skeleton data is also fused along with the depth and color models to obtain the final segmentation inside a graph-cut...
A generalized Swendsen-Wang (GSW) algorithm is proposed for the joint segmentation of a set of multiple images sharing, in part, an unknown number of common classes. The class labels are a priori modeled by a combination of the hierarchical Dirichlet process (HDP) and the Potts model. The HDP allows the number of regions in each image and classes to be automatically inferred while the Potts model...
A variety of methods have been proposed for object level saliency detection, which is useful for many content-based computer vision applications. Unlike most previous work that integrate multiple low level cues to compute the saliency map, this paper presents a novel hierarchical optimization model. First, we compute a rough saliency map using HS method, and then, boundary and foreground seeds are...
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.