摘要
为了解决弱纹理与遮挡区域中难以准确匹配对应点的问题,在马尔可夫随机场(Markov random field,MRF)框架下,提出一种结合卷积神经网络(convolutional neural network,CNN)与分割线索的立体匹配算法.首先,采用特征表达能力强的CNN提取立体图像特征并匹配区域块.同时,对图像进行区域分割.然后,基于CNN匹配结果构造MRF能量函数数据项.基于分割结果定义能量函数项,通过其他区域约束弱纹理和遮挡区域的匹配过程.最后,最优化求解能量函数计算视差.在Middlebury与KITTI数据集上验证该算法和能量函数各项的作用,并与近2年提出方法进行性能比较.结果表明,该算法准确度更高,应对弱纹理与遮挡区域效果更好.
To solve the matching problem in textureless and occluded regions, a stereo matching algorithm was presented in this paper, which integrated segmentation clues and convolutional neural network (CNN) matching results into an Markov random field (MRF) energy function. The unary term of the energy function was formulated by the output of CNN, which was powerful in feature expression. The pairwise smooth term was defined by the over-segmentation results of the input images to constrain matching in textureless and occluded regions. Experiments on Middlebury and KITTI datasets validated the performances of the algorithm and its components. Results show that the algorithm outperforms the other methods proposed in recent years, especially in dealing with textureless and occluded regions.
作者
马伟
李曈
龚超凡
丁治明
MA Wei;LI Tong;GONG Chaofan;DING Zhiming(Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China;Beijing Key Laboratory of Trusted Computing, Beijing 100124, China)
出处
《北京工业大学学报》
CAS
CSCD
北大核心
2019年第5期413-420,共8页
Journal of Beijing University of Technology
基金
国家重点研发计划资助项目(2017YFC0803300)
国家自然科学基金资助项目(61771026
91546111
91646201)
模式识别国家重点实验室开放课题基金资助项目
北京市教育委员会科技计划资助项目(KZ201610005009)
关键词
立体匹配
图像分割
卷积神经网络(CNN)
MRF能量函数
视差
stereo matching
image segmentation
convolutional neural network (CNN)
Markov random field (MRF) energy function
disparity
