基于阴影检测的增强现实光照一致性实现  

Realizing Illumination Consistency in Augmented Reality Based on Shadow Detection

作　　者：吴广运 周治平[1,2] Wu Guangyun;Zhou Zhiping(School of Internet of Things Engineering,Jiangnan University,Wuxi,Jiangsu 214122,China;Engineering Research Center of Internet of Things Engineering Technology Application,Ministry of Education,Jiangnan University,Wuxi,Jiangsu 214122,China)

机构地区：[1]江南大学物联网工程学院,江苏无锡214122 [2]江南大学物联网技术应用教育部工程研究中心,江苏无锡214122

出　　处：《激光与光电子学进展》2022年第2期342-347,共6页Laser & Optoelectronics Progress

摘　　要：在增强现实领域,实现虚拟对象光照一致性一直是个难题,针对赋予虚拟对象阴影信息时阴影检测效率低的问题,提出一种基于阴影区域构建阴影体实现虚拟对象光照一致性的方法。首先,采用改进的超像素分割(Ⅰ-SLIC)算法对图像进行处理得到更稳定的超像素集合,并根据相邻超像素中心的颜色距离相似度进行超像素合并,以降低后续处理复杂度。然后,采用高斯混合背景模型对分割后的图像进行阴影检测,利用阴影区域与光照参数构建阴影体。最后,根据变换矩阵完成虚拟对象的注册并结合阴影体进行渲染。实验结果表明,所提方法实现了对虚拟对象的阴影渲染,大大提高了增强现实应用带来的真实感,对比其他方法,在时间效率上具有明显优势。In the augmented reality field,it is a challenge to achieve the illumination consistency of virtual objects.To address the low shadow detection efficiency problem when virtual objects are endowed with shadow,a method based on the shadow area is proposed to construct a shadow volume to achieve the illumination consistency of virtual objects.The proposed method first performs superpixel merging based on the color distance similarity according to adjacent superpixel centers.Superpixel collection is obtained using an improved simple linear iterative clustering(Ⅰ-SLIC)algorithm on the images.The number of superpixel collections and the subsequent processing complexity are reduced accordingly.Then,a Gaussian mixture background model is employed to detect the shadow of the segmented image,and the shadow body is constructed using the shadow region and illumination parameters.Finally,the registration of the virtual object is completed according to the transformation matrix combined with the shadow volume for rendering.Experimental results demonstrate that the proposed method realizes the shadow rendering of virtual objects and greatly improves the realism of augmented reality applications.Compared with existing methods,the proposed method demonstrates an obvious advantage in terms of time efficiency.

关 键 词：机器视觉 增强现实 光照一致性 阴影检测 超像素分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]