摘要
针对建筑物场景,提出两种在基于图的立体匹配算法中融合部分深度数据来提高视差图质量的方法。若该部分深度线索来自扫描仪获取的准确测量数据,则可以从中直接抽取出对应于三维空间平面的视差层组成标号集,并以颜色块代替像素作为图结点。进一步地,将扫描仪的使用限制在离线阶段,即仅用于训练数据库的建立,然后在立体匹配的图中添加一个图像块层,来融合通过统计学习获得的单目图像深度推断线索。实验结果很好地证明了算法的有效性。
Focusing on scenes of outdoor buildings,the authors present graph-based stereo matching methods that incorporate depth cues to acquire more accurate disparity maps.Firstly,given a portion of scan data,planar disparity layers,which correspond to 3D planes,are precisely extracted to compose the label set.After that,the graph-based matching algorithm can be formulated in the color segment domain instead of pixel domain.Furthermore,in order to avoid the inconvenient scanning for every scene,the scanner is only used to create a training set consisting of image-depthmap pairs. Then the depth cues, predictedthrough training a Markov Random Field to model the relationship between the depth and the image features, can still serve as extra constraint for the correspondence problem. The experimental results show the convincing performance of proposed methods in the reconstruction of different scenes.
出处
《北京大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2009年第5期791-797,共7页
Acta Scientiarum Naturalium Universitatis Pekinensis
基金
国家重点基础研究发展计划项目(2004CB318000)
国家高技术研究发展计划专项经费(2007AA01Z336)
教育部科学技术研究重大项目(103001)资助
关键词
立体匹配
平面视差层
马尔科夫随机场
统计学习
stereo matching
planar disparity layer
Markov Random Field
statistical learning
