基于DCT域视觉的场馆监控图像显著区域检测  

Salient Area Detection of Venue Monitoring Image Based on DCT Domain Vision

作　　者：魏泽国[1] 赵长伟[1] WEI Ze-guo;ZHAO Chang-wei(Henan University of Science and Technology,Luoyang Henan 471000,China)

机构地区：[1]河南科技大学,河南洛阳471000

出　　处：《计算机仿真》2021年第1期408-411,470,共5页Computer Simulation

摘　　要：针对传统图像显著区域的目标运动检测能力不足,提出一种基于DCT域视觉的图像显著区域检测方法。以MCU为基本单位将监控图像分割成图块,利用DCT系数对颜色、亮度、纹理等特征向量进行提取计算得到全局对比度,运用最大类间方差法计算阈值将图像分割,获得视觉显著区域。同时,以全局背景判断图像中的注视区范围、注视点位置,计算注视点中最强的位置,完成显著图像的区域检测。实验证明,所提方法可以实时对出现在显著区域的目标进行检测,检测效率高。Currently,the traditional detection ability of target in salient region of image is poor.Therefore,this paper proposes a DCT domain vision based salient region detection method.The monitoring image was divided into blocks based on MCU.Through the utilization of DCT coefficients,the color,brightness,texture and other feature vectors were extracted and calculated to get the global contrast.Based on the maximum inter class variance method,the threshold was calculated to segment the image,thus the visual saliency region was obtained.Meanwhile,according to the global background,the range and position of fixation point in the image were determined,and the strongest position in the fixation point was calculated.Eventually,the region detection of salient image was achieved.The simulation results show that the method has high detection efficiency and real-time.

关 键 词：显著区域检测 阈值分割 注视区 注视点 视区追踪 

分 类 号：TP911.75[自动化与计算机技术]