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 proposes a fully automatic pipeline to generate accurate object segment proposals in realistic videos. Our approach first detects generic object proposals for all video frames and then learns to rank them using a Convolutional Neural Networks (CNN) descriptor built on appearance and motion cues. The ambiguity of the proposal set can be reduced while the quality can be retained as highly...
This paper presents an automatic event detection system fusing low and mid level features for soccer videos. We first employ an improved approach for Shot Boundary Detection with color and our mean-gradient feature. Then we classify the shots into two view types. We also perform a template-based replay detection for each shot. Play-break sequences are then generated using a rule-based method. We devise...
Detection of defects in printing is important in precise print industry. The problem is almost equal to detecting the foreground objectives from cluttered background in video surveillance. It has the same problem of background minor motions. The difficulty lies in how to detect the unknown flaws under complicated background effectively. Inspired by the background modeling approaches for moving objects...
We present a multi-feature based object extraction algorithm in this paper. Cutting in from the angle of multi-feature, this algorithm combines the high-efficient and good performance Graph Cut framework. We add foreground shape information and motion estimation as a compensation of the instability of using single color information.
This paper presents a robust and fully-automatic human motion tracking system without motion priors information using a camera in a fixed location. Bottom-up estimation approaches have recently been applied to such tasks with some success. However, the performance of these approaches is limited by the difficulty of building an effective appearance model. In particular, the appearance model must be...
In this paper, two new energy functions are presented to handle the slanted plane. First, the gradient information is used to get the initial disparity in a local energy function. Second, a global energy function is incorporating segment geometric constraints. To overcome the fronto-parallel model errors, the segment adjacent segments cooperative optimization is used to infer the unreliable pixel...
The aim of the stereo matching is to get the accurate disparity. But for the slanted and low textured plane, the ambiguity is increased. To get the more accurate disparity, most constraints are applied. In this paper, the statistical probability method (SPT) is applied to inferring disparity. The reliable confidence (RC) based on the SPT measures how the pixel disparity is reliable. The unreliable...
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.