English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this work, we analyze different topics in the study of object tracking. In Section 2, we study algorithms for tracking objects in a video sequence, based on the selection of landmark points representative of the moving objects in the first frame of the sequence to be analyzed. The movement of these points is estimated using a sparse optical-flow method. Methods of this kind are fast, but they are not very robust. Particularly, they are not able to handle the occlusion of the moving objects in the video. To improve the performance of optical flow-based methods, we propose the use of adaptive filters to predict the expected instantaneous velocities of the objects, using the predicted velocities as indicators of the performance of the tracking algorithm. The efficiency of this strategy to handle occlusion problems are tested with a set of synthetic and real video sequences. In (Parrilla et al., 2008) we develop a similar study using neural networks. Video tracking deals with the problem of following moving objects across a video sequence (Trucco & Plakas, 2006), and it has many applications as, for example, traffic monitoring and control (Inigo, 1989), (Erdem et al., 2003), robotic tasks, surveillance, etc. Simple algorithms for video tracking are based on the selection of regions of interest in the first frame of a video sequence, which are associated with moving objects to be followed and a system for estimating the movement of these regions across the sequence. More demanding methods impose constrains on the shape of the tracked objects (Erdem et al., 2003; Shin et al., 2005), or use methods to separate the moving objects from the background of the images (Ji et al, 2006; Wren et al., 1997). Most of these more demanding algorithms deal with partial occlusion of the moving objects, that is, the algorithms are not lost when the target temporarily disappears from the frame and they resume correctly when the target reappears. Generally, this kind of algorithms include an a priori training of the possible shape of the object to be followed and occlusion is handled following the movement of the contour. This is expensive from the computational point of view and makes these algorithms difficult to be implemented in a real-time application. We have used adaptive filters (Haykin, 1986; Ljung, 1999) to predict the velocities of the object to track. These expected velocities are compared with the ones computed with the optical flow method and are used as indicators of the performance of the method. If the optical flow method fails to compute reasonable values for the velocities, the velocity values predicted by the filter can be used as reliable values for the velocities of the object. A system of this kind Fuzzy Control System to Solve Coupling Between Tracking and Predictive Algorithms 7