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.
Due to the superiority in handling label ambiguity, multiple instance learning (MIL) has been introduced into adaptive tracking-by-detection methods to alleviate drift and yields promising tracking performance. However, the MIL tracker assumes that all samples in a positive bag contribute equally to the bag probability, which ignores sample importance. To address this issue, in this paper we propose...
Scene Text Recognition is an extremely useful but challenging task and has drawn much attention in recent years. The best of previous model is CNN-LSTM model with attention mechanism, and it can recognize the whole text without character-level segmentation and recognition. Compared with LSTM, Recurrent Highway Networks (RHN), as a popular architecture because of its capability of training deep structure,...
Real-time lane detection and tracking is one of the most reliable approaches to prevent road accidents by alarming the driver of the excessive lane changes. This paper addresses the problem of correct lane detection and tracking of the current lane of a vehicle in real-time. We propose a solution that is computationally efficient and performs better than previous approaches. The proposed algorithm...
Despite impressive results in object classification, verification and recognition, most deep neural network based recognition systems become brittle when the view point of the camera changes dramatically. Robustness to geometric transformations is highly desirable for applications like wild life monitoring where there is no control on the pose of the objects of interest. The images of different objects...
This paper describes a latent space understandable network: Self- excited Generative Adversarial Network (Self- ExGAN), a novel self- excited structure based on adversarial learning. Compared with the conventional generative adversarial networks, SelfExGAN consists of three components, which are en- coder (E), generator (G), and discriminator (D). Different from other papers which directly apply reconstruction...
In image retrieval, an effective dissimilarity (or similarity) measure is required to retrieve the perceptually similar images. Minkowski-type distance is widely used for image retrieval, however it has its limitation. It focuses on distance between image features and ignores the data distribution of the image features, which can play an important role in measuring perceptual similarity of images...
This paper introduces a new video understanding dataset which can be utilised for the related problems of event recognition, localisation and description in video. Our dataset consists of dense, well structured event annotations in untrimmed video of tennis matches. We also include highly detailed commentary style descriptions, which are heavily dependent on both the occurrence as well as the sequence...
A novel robust video watermarking scheme is proposed in this paper, in which crowdsourcing technique is used to extract the most important regions from the original video. In fact, these regions are obtained by interacting with users and analyzing their behaviors while using an interactive interface where the summaries of the videos are given. The obtained regions are then detected in the mosaic frame...
Routine can be defined as the frequent and regular activity patterns over a specified timescale (e.g. daily/weekly routine). In this work, we capture routine patterns for a single person from long- term visual data using a Dynamic Bayesian Network (DBN). Assuming a person always performs purposeful activities at corresponding locations; spatial, pose and time-of-day information are used as sources...
Viewpoint variation is a major challenge in video- based human action recognition. We exploit the simultaneous RGB and Depth sensing of RGB-D cameras to address this problem. Our technique capitalizes on the complementary spatio-temporal information in RGB and Depth frames of the RGB-D videos to achieve viewpoint invariant action recognition. We extract view invariant features from the dense trajectories...
Vision is a potent source of information, not just for humans, but for robots as well. Processing visual information is a computationally expensive task, one that is often difficult to accomplish in real-time on embedded hardware. In the broad field of visual research exists egomotion estimation, the process of determining self-motion from optical flow. Here we show a technological adaptation and...
We present the Region of Interest Autoencoder (ROIAE), a combined supervised and reconstruction model for the automatic visual detection of objects. More specifically, we augment the detection loss function with a reconstruction loss that targets only foreground examples. This allows us to exploit more effectively the information available in the sparsely populated foreground training data used in...
In this paper, we present a novel method to estimate dichromatic model parameters from a single color image. Estimation of reflectance, shading and specularity has many applications such as shape recovery, specularity removal and facilitates classical image processing and computer vision tasks such as segmentation or classification. Our method is based on two successive and independent constrained...
In this work, using a new set of color features in the field of computer vision and image processing which are inspired by the work of artists, we try to classify different subjective properties of paintings, including aesthetic quality, beauty, and liking of color. We then investigate if observers have individual tastes and opinions when evaluating different properties of artworks. The extracted...
Visual tracking is a very challenging problem in computer vision as the performance of a tracking algorithm may be degraded due to many challenging issues in the scenes, such as illumination change, deformation, and background clutter. So far no algorithms can handle all these challenging issues. Recently, it has been shown that correlation filters can be implemented efficiently and, with suitable...
A novel composite approach through integration of variational optical flow and surface splines is presented to obtain sub-pixel accurate dense disparity map for remotely sensed stereo image pair. It is well known that, surface splines handle geometric distortion very well. The performance of surface splines for dense correspondence can be significantly improved by the reliable control points, but...
Precision agriculture has enabled significant progress in improving yield outcomes for farmers. Recent progress in sensing and perception promises to further enhance the use of precision agriculture by allowing the detection of plant diseases and pests. When coupled with robotics methods for spatial localisation, early detection of plant diseases will al- low farmers to respond in a timely and localised...
In recent years, remarkable breakthrough has been achieved in person re-identification (Re-ID). However most methods are only tested in the closed-world setting where the probe person is assumed to be one of the gallery people. In this paper, we tackle a more realistic problem, open-world Re-ID, which requires to find out whether the probe person is among the gallery or not, and if so, who he is....
In typical applications, chromatic indices are calculated as linear combinations of the normalized r-, g- and b-channels and used as features for a later classification based on chromatic appearance. But the variety of indices used in the literature is very limited. Furthermore is the choice of which index to use justified either empirically, based on false mathematical assumptions or not justified...
Pedestrian trajectory prediction is important in various applications such as driverless vehicles, social robots, intelligent tracking systems and space planning. Existing methods focus on analysing the influence of neighbours but ignore the effect of the intended destinations of pedestrians which also plays a key role in route planning. In this paper, we propose a novel two- stage trajectory prediction...
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.