CAJ | 학술논문

提出将视觉注意模型应用于虚拟与现实交互中，通过显著性原理检测出真实场景中的有效区域。采用将图像在空域和频域中分别进行显著特征提取，再通过特征组合理论进行特征融合。空域中采用区域颜色对比以及局部复杂度对比特征；提出在频域内进行有效频段分割，结合幅度信息提取显著特征，再加权后合成；特征组合理论是根据细胞调解原理来处理特征之间独立与联合作用的关系。最后提出将该方法应用于虚拟与现实交互中检测真实场景中的有效区，并同其他算法进行效果对比。
제출장시각주의모형응용우허의여현실교호중，통과현저성원리검측출진실장경중적유효구역。채용장도상재공역화빈역중분별진행현저특정제취，재통과특정조합이론진행특정융합。공역중채용구역안색대비이급국부복잡도대비특정；제출재빈역내진행유효빈단분할，결합폭도신식제취현저특정，재가권후합성；특정조합이론시근거세포조해원리래처리특정지간독립여연합작용적관계。최후제출장해방법응용우허의여현실교호중검측진실장경중적유효구，병동기타산법진행효과대비。
According to the human visual attention mechanism,this paper introduces a novel plausible model for image saliency detection .Firstly,saliency features are detected including regional color contrast and local complexity contrast based on the sparese representation principle; And proposing the Efficient Band Divided Method which unites information of amplitude with the phase spectrum for generating the saliency feature. Then refer to the principle that activity in cells responding to stimuli,.a new feature combination theory is proposed to deal with the relationship of the characteristics of independence and mutual interaction for achieving features fusion accurately. Afterwards,the proposed algorithm can effectively detect regions through some experiments,and applied in virtual and reality interaction to detect the effective region and eliminate noise area.