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.
This paper presents a two-pass clustering technique for orientation-invariant text line clustering in a language-independent text localization problem based on the connected component analysis (CCA) approach. Instead of doing a single-pass cluster in the conventional way, the proposed technique firstly explores nearby objects around the candidate components. By setting up the global constraints with...
A complex activity is a temporal composition of sub-events, and a sub-event typically consists of several low level micro-actions, such as body movement of different actors. Extracting these micro actions explicitly is beneficial for complex activity recognition due to actor selectivity, higher discriminative power, and motion clutter suppression. Moreover, considering both static and motion features...
Small infrared target detection in complex backgrounds is a challenging task. Due to dynamic background clutter and low signal-to-clutter ratio, most conventional methods fail to produce satisfactory results. In this paper, an effective spatial and temporal filter is proposed. The spatial filter is used to remove cloud edge, and the temporal filter is used to remove point-like background clutter....
Current traffic monitoring is limited by the small coverage of camera surveillance systems, for example, a specific area around one road intersection. Satellite high definition videos are becoming available which can provide videos over several squared kilometers. Thus, these videos introduce new possibilities for better traffic control and management. However, parallax motions caused by the movements...
Saliency detection aims to find the useful and attractive regions from an image. In many situations, there may be multiple objects in the image, and these objects may have equal attractiveness. Moreover, the appearance of pixels in one object may demonstrate large difference, which could lead to lose the object integrality when detecting saliency. To this end, this paper proposes a multi-saliency...
This paper addresses a specific example of nonperiodic translation symmetry and presents an algorithm to automatically detect multiple poles, or their shadows, in aerial imagery by looking for consistent and overlapping regions of self-similarity across a non-urban scene. The algorithm does not rely on having a pole template or knowing its exact size. For each image patch, similar regions (or blobs)...
Morphologic filters are used here to interpolate missing values from sets of frequency domain measurements, as occurs in Magnetic Resonance Imaging. MRI data acquisition is done in the Fourier domain which is often sub-sampled to reduce the required scan time. Partial recovery of the missing frequency samples permits direct Fourier inversion to provide a rapid and improved initial estimation of the...
Kernel descriptors have been proven to outperform existing histogram based local descriptors as such descriptors are extracted from the match kernels which measure similarities between image patches using different pixel attributes (gradient, colour or LBP pattern). The extraction of kernel descriptors does not require coarse quantization of pixel attributes. Instead, each pixel equally participates...
Facial micro-expression refers to split-second muscle changes in the face, indicating that a person is either consciously or unconsciously suppressing their true emotions and even mental health. Therefore, micro-expression recognition attracts increasing research efforts in both fields of psychology and computer vision. Existing research on micro-expression recognition has mainly used hand-crafted...
Tamura features are based on human visual perception and have huge potential in image representation. Conventional Tamura features only work on homogeneous texture images and perform poor on generic images. Therefore, many researchers attempt to improve Tamura features and most of the improvements are based on histogram based representation. Kernel descriptors have been shown to outperform existing...
This paper develops a general framework of image retrieval, named A3, by introducing an auxiliary set of samples (object references), each of which is annotated with semantic attributes (tags). Given a query image (without tags), we first map it into the references by a non-convex sparse coding formulation, which jointly optimizes appearance reconstruction of the query and semantics consistency among...
Image compression plays more and more important role in image processing. Image sparse coding with learned over-complete dictionaries shows promising results on image compression by representing images with dictionary atoms compactly. Within the sparse coding based compression framework, a sparse dictionary is first learned from training images in a predefined image library, and then an image is compressed...
Automated image stylization to create artistically pleasing images from ordinary photographs is an interesting and useful task in computer vision. Therefore, several automated styling methods have been developed using powerful Deep Neural Network (DNN) features. They typically use a carefully constructed joint loss function to separately consider the similarities between a proposed output and the...
Human pose forecasting is an important problem in computer vision with applications to human-robot interaction, visual surveillance, and autonomous driving. Usually, forecasting algorithms use 3D skeleton sequences and are trained to forecast for a few milliseconds into the future. Long-range forecasting is challenging due to the difficulty of estimating how long a person continues an activity. To...
Salient object detection using RGB-D data is an emerging field in computer vision. Salient regions are often characterized by an unusual surface orientation profile with respect to the surroundings. To capture such profile, we introduce the histogram of surface orientation (HOSO) feature to measure surface orientation distribution contrast for RGB-D saliency. We propose a new unified model that integrates...
Convolutional neural network (CNN) has drawn increasing interest in visual tracking, among which fully-convolutional Siamese network based method (SiamFC) is quite popular due to its competitive performance in both precision and efficiency. Generally, SiamFC captures robust semantics from high-level features in the last layer but ignores detailed spatial features in earlier layers, thus tending to...
This paper deals with automatic estimation of the horizon in videos from fixed surveillance cameras. The proposed algorithm is fully automatic in the sense that no user input is needed per-camera and it works with various scenes (indoor, outdoor, traffic, pedestrian, livestock, etc.). The algorithm detects moving objects, tracks them in time, assesses some of their geometric properties related to...
Automatic face retrieval or verification is a matter to identify whether the target person is the same person, which has been received considerable attention by researchers in computer vision. This paper proposes a method to localize a face from video sequences by considering only one shot. First, Cascade AdaBoost is applied to identify region of a face from the video sequence. The image enhancement...
Road pixel segmentation in airborne data is an important and challenging task. Recently, a sophisticated and robust approach based on superpixels and minimum cost paths has been published. In order to find out which of the numerous features are most essential, we propose a forward-search wrapper approach for feature selection which was tested with two different classifiers and with both generic and...
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.