شماره ركورد كنفرانس :
4753
عنوان مقاله :
Applying Combining Tracker-Level strategies for Optimizing Motion Mining Algorithms
عنوان به زبان ديگر :
Applying Combining Tracker-Level strategies for Optimizing Motion Mining Algorithms
پديدآورندگان :
Ghahari Bidgoli Milad m.ghahari@siiau.ir Sama Technical and Vocational training college, Islamic Azad University, Islamshahr Branch, Islamshahr, Iran , Shakarami Ali Islamic Azad University, Qom Branch, Qom, Iran
كليدواژه :
Motion mining , Trajectory , Tracker , level fusion , Video tracking
عنوان كنفرانس :
اولين كنفرانس بين المللي محاسبات و سامانه هاي توزيع شده
چكيده فارسي :
In recent years, researches in motion mining and correct tracking without error in the proper time have been highly important. This paper presents a new model for motion mining using a combination of data tracker-level strategies and then utilizes an additional layer as a tracker-level fusion to achieve the best results at the surface. In fact, in this model, fusion at tracker level models such as a black box that its output will be achieved by combining different algorithms and images features. In comparison with the other existing models, the most important advantages of this model are acceptable speed and accuracy for tracking in the higher layers.
چكيده لاتين :
In recent years, researches in motion mining and correct tracking without error in the proper time have been highly important. This paper presents a new model for motion mining using a combination of data tracker-level strategies and then utilizes an additional layer as a tracker-level fusion to achieve the best results at the surface. In fact, in this model, fusion at tracker level models such as a black box that its output will be achieved by combining different algorithms and images features. In comparison with the other existing models, the most important advantages of this model are acceptable speed and accuracy for tracking in the higher layers.