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.
Learning visual representations with self-supervised learning has become popular in computer vision. The idea is to design auxiliary tasks where labels are free to obtain. Most of these tasks end up providing data to learn specific kinds of invariance useful for recognition. In this paper, we propose to exploit different self-supervised approaches to learn representations invariant to (i) inter-instance...
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...
Saliency-based approaches has been well studied and successfully used in object detection for visible images. However, few researches have been done for saliency detection in infrared images, which are characterized with low resolution, SNR and contrast, fuzzy edge and lack of color features. In this paper, a contrast and distribution based saliency detection approach is proposed for infrared images...
Object level saliency detection is useful for many content-based computer vision tasks. In this letter, we present a novel bottom-up salient object detection approach by exploiting contrast, and center priors. In the past, the algorithms of saliency detection are generally based on the contrast of the priors, but only using a prior that there are still many problems, if not uniformly outstanding goals...
This paper presents a new generic framework for human visual system inspired object detection and recognition and introduces the idea of feature extraction based on the human visual sensitivity. These methods can greatly enhance robotic vision applications. Additionally a new computationally effective object detection algorithm is presented based on image morphology and visual sensitivity. This new...
License plates detection is widely considered a solved problem, with many systems already in operation. However, the existing algorithms or systems work well only under some controlled conditions. There are still many challenges for license plate detection in an open environment, such as various observation angles, background clutter, scale changes, multiple plates, uneven illumination, and so on...
The problem of amorphous object detection is investigated. A dataset of amorphous objects, Panda bears, with no defined shape or distinctive edge configurations is introduced. A biologically plausible amorphous object detector, based on discriminant saliency templates, is then proposed. The detector is based on the principles of discriminant saliency, and implemented with a hierarchical architecture...
This paper presents an efficient camera tracking using prior knowledge of a target scene - 3-D object models with scene textures. The camera tracking uses partially modeled 3-D objects instead of complete and delicate modeling, which is not easy in complex scenes with a variety of 3-D objects. For robust and accurate camera tracking, scene textures are also sparsely modeled, and they support reducing...
In recent years several works have aimed at exploiting color information in order to improve the bag-of-words based image representation. There are two stages in which color information can be applied in the bag-of-words framework. Firstly, feature detection can be improved by choosing highly informative color-based regions. Secondly, feature description, typically focusing on shape, can be improved...
A novel approach is presented to detect contour of object. Firstly, the zero-cross operator to imitate the visual receptive field is used to detect edge of image. Secondly, facing the large amount of noise in complex background, the neighborhood description operator is designed, and the neighborhood information of interesting point is analyzed as well. Then the contours of objects are acquired by...
Object localization in an image is usually handled by searching for an optimal subwindow that tightly covers the object of interest. However, the subwindows considered in previous work are limited to rectangles or other specified, simple shapes. With such specified shapes, no subwindow can cover the object of interest tightly. As a result, the desired subwindow around the object of interest may not...
In this paper, we address the problem of automatic pre-segmentation for object detection and recognition in remote sensing image processing. It plays an important role in reducing computational burden and increasing efficiency for further image processing and analysis. A visual-attention based saliency computation approach is introduced to select the perceptually salient and highly informative regions...
Corner detection is an important early vision problem. In early vision processing of the mammalian visual system, the oriented tuned, contrast-driven cells in the visual cortex have the problems of positional and orientational uncertainty. That means the oriented receptive fields (RFs) of simple cells can not detect the orientational information of the line ends and corners efficiently. In this paper,...
In this paper we propose a novel computational method to infer visual saliency in images. The computational method is based on the idea that salient objects should have local characteristics that are different than the rest of the scene, being edges, color or shape, and that these characteristics can be combined to infer global information. The proposed approach is fast, does not require any learning...
The paper presents a probabilistic tracking framework to fuse high-level object detection cues with low-level image feature cues using particle filters. First, an adaptive ICONDENSATION (AICONDENSATION) is introduced to better exploit object detection cues to guide importance sampling, where the proposal distribution is derived in a more principled approach using data association methods so that mixture...
In outsized multimedia databases video segmentation is a fundamental constituent necessary to assist proficient content based retrieval and browsing of visual information. This paper presents work towards an integrated framework for computerized video shot detection. In this framework a set of representative key frames are selected which helps in summarizing of the entire video content into an abstract...
Online shopping is becoming more and more popular for a number of reasons; prices are often lower online, you don't have to queue up in busy shops and you can buy almost any product imaginable with just a few clicks of your mouse. But the general problems of shopping Web site is that, most of the existing online shops list products based on keywords. As the inherent limitation, keyword browsing makes...
In this paper we introduce a new kind of feature - the multi-local feature, so named as each one is a collection of local features, such as oriented edgels, in a very specific spatial arrangement. A multi-local feature has the ability to capture underlying constant shape properties of exemplars from an object class. Thus it is particularly suited to representing and detecting visual classes that lack...
In this paper we introduce a statistical framework for image quality assessment based on the properties of hierarchical receptive fields (RFs) which are the primary mechanism for detection of visual patterns in the human visual system (HVS). We show how this frame work can be used to learn about different aspects of RFs such as the shape and size of RFs in the early vision and the directional preference...
Detection of saliency regions in images is useful for object based image understanding and object localization. In our work, we investigate a saliency region detection algorithm based on the human visual attention (HVA) model. In the first phase, we use mutual information and probability-of-boundary (PoB) for color saliency and edge detection respectively to filter SURF (speeded up robust features)...
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.