In this paper, a novel approach for surveillance video cropping is presented. The basic idea is to obtain a trajectory that a small sub-window can take through the video, selecting the most important regions of the vi...
详细信息
In this paper, a novel approach for surveillance video cropping is presented. The basic idea is to obtain a trajectory that a small sub-window can take through the video, selecting the most important regions of the video for display on a smaller monitor. In this framework, the video content is firstly modeled by whether image frames change at each pixel. Then a shortest path algorithm is used to find the globally optimal trajectory for a cropping window. After that a second shortest path formulation is employed to find good cuts from one trajectory to another, improving the coverage of interesting events in the video content. Finally, additional techniques are demonstrated to improve the quality and efficiency of the algorithm, and results are shown on surveillance videos from PETS 2006.
To represent and reason with interval-value information of applications in description logic, based on interval-fuzzy set the classical des cription logic ALCN is extended to the fuzzy description logic IFALCN. Its...
详细信息
The satisfiability(SAT) problem is an important problem of automated reasoning. In the past decades, many methods of SAT are proposed, such as method based on resolution, method based on tableau and method based on ex...
详细信息
In recent years, with the development of the wireless sensor networks, the localization method receives the attention of many researchers. However, due to the network cost and characteristics of sensor nodes, most of ...
详细信息
Essential graph is a graphical representation for Markov equivalence classes of Bayesian networks. Learning essential graph can avoid some problems in traditional Bayesian networks learning algorithms: (1) the number ...
详细信息
The quantitative understanding of human behavior is a central question of modern science. Because of the complexity of human behavior, it is almost impossible to seek regularities in human dynamics. It is assumed that...
详细信息
The quantitative understanding of human behavior is a central question of modern science. Because of the complexity of human behavior, it is almost impossible to seek regularities in human dynamics. It is assumed that human actions are randomly distributed in time in current models for human dynamics. While the characteristics of human behavior combined with the queue model are considered as model for human dynamics based on habit to explain bursts and heavy tails in human dynamics more exactly. Normal distribution is used to simulate intervals of succession of events, and random parameters are set as unexpected events disturbing habit behaviors. Moreover, duration of events are proposed to imitate continual attention to some events in human behaviors.
Conventional models based on crisp regions can not deal with the Direction Relations between Uncertain Regions (DRUR). Using broad boundary to represent the uncertain boundary, a novel approach is proposed based on mo...
详细信息
The satisfiability(SAT) problem is a core problem of artificial intelligence. Research findings in SAT are widely used in many areas. The main methods solving SAT problem are resolution principle, tableau calculus and...
详细信息
Constraint satisfaction problems play a significant role in the field of Artificial Intelligence. Reducing the search space can improve the efficiency of solving the problems before the search of solutions. Applying i...
详细信息
There may be many groups of candidate results after the step of candidate generation in model-based diagnosis. Hwee Tou Ng proposed the Inc-Diagnose approach to further reduce the candidate results. However, the effic...
详细信息
暂无评论