欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对街景图像中往往包含大量行人等隐私对象的问题,以移除图像中的行人为例,提出一种全局优化的时空图像修补方法.首先利用运动获得结构算法建立参考图像与目标图像之间的对应关系,该过程不依赖场景的简化假设,使得该图像修补方法适合各类复杂场景;然后对待修补区域建立马尔科夫随机场,通过合理设计标号集和能耗函数,把时域和空域修补结合到同一优化过程中,并自动判断何时选择何种修补方式,使修补结果尽量符合实际场景同时又具有较好的视觉一致性.大量实验结果表明,该方法对各种复杂场景的街景图像都能够得到较好的修补效果.
英文摘要：
Since street images usually contain privacy contents like pedestrians,a global optimized spatial-temporal image completion method is presented for pedestrian removal.Firstly,a structure from motion（SFM） algorithm is applied to build the relationship between the target and the reference images,which guarantees the effectiveness of the proposed method in complex situations.Then,a Markov random field（MRF） model is built and the global optimization method is used for the target region completion.In this stage,the spatial and temporal completions are integrated into one process.And a genuine and visually consistent result is obtained through an automatically selected completion method.Experimental results on a wide variety of images are presented,which demonstrate the effectiveness of the proposed image completion algorithm for complex scenes.
同期刊论文项目
同项目期刊论文
Multi-Scale Locality-Constrained Spatiotemporal Coding for Local Feature Based Human Action Recognit
Defocus Deblurring for Catadioptric Omnidirectional Imaging Based on Spatially Invariant Point Sprea
Spatially Regularized and Locality-Constrained Linear Coding for Human Action Recognition（SCI检索号0003
Real-Time Distortion Correction of Fish-Eye Lens Based on Bayer Image Signal（SCI检索号 000334253000009）
Omni-gradient based Total Variation Minimization for Sparse Reconstruction of Omnidirectional Image（
Angle Consistency for Registration between Catadioptric Omni-images and Orthorectified Aerial Images
期刊信息
位置：