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.
Visual separability between different objects in various image classification tasks is highly uneven. As a consequence, humans need different levels of detailed descriptions to separate objects in multi-granularity similarities. Meanwhile, deep networks, such as convolutional neural networks (C-NNs) have demonstrated great ability in multilevel representations for an object. Unfortunately, existing...
In order to remove the problem of the shadow of moving vehicles in video surveillance, this paper presents an algorithm based on projection features of the connected regions to eliminate the dynamic shadow. Firstly, the Frame Difference method is applied to image blocks to extract the background. Then, the moving vehicles are detected as the foreground in the current frame by background subtraction...
Classification of images based on the feelings generated by each image in its reviewers is becoming more and more popular. Due to the difficulty of gathering training data, this task is intrinsically a small-sample learning problem. Hence, the results produced by most existing solutions are less accurate. In this paper, we propose the semi-supervised hierarchical classification (SSHC) algorithm for...
Feature integration theory, the classic visual attention model, provides a theoretical foundation for optimizing visual communication. This paper proposes a set of glyphs named RoseShape that aim at improving users' visual information search in visualization. RoseShapes integrate rich and easy-to-catch attributes for mapping data variables, enabling automatic and unconscious information processing...
Traditional level-set-based methods of tracking contours suffered from occlusion and fusion. In this paper, the proposed method introduces dynamic incident detection to find and handle occlusion and fusion. Color histogram of the hue component in HSV color space is used to identify the objects re-entering after occlusion. On the other hand, object features including the size and the motion pattern...
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.