基于边缘检测的视差图效果优化  被引量:18

DISPARITY MAP OPTIMIZATION BASED ON EDGE DETECTION

在线阅读下载全文

作  者:王安 王芳荣[2] 郭柏苍 岳欣羽 Wang An;Wang Fangrong;Guo Baicang;Yue Xinyu(China-Japan Union Hospital,Jilin University,Changchun 130022,Jinlin,China;College of Communication Engineering,Jilin University,Changchun 130022,Jilin,China;College of Transportation,Jilin University,Changchun 130022,Jilin,China;Ningbo Geely Automobile Research and Development Co. ,Ltd. ,Ningbo 315336,Zhejiang,China)

机构地区:[1]吉林大学中日联谊医院,吉林长春130022 [2]吉林大学通信工程学院,吉林长春130022 [3]吉林大学交通学院,吉林长春130022 [4]吉利汽车研究院(宁波)有限公司,浙江宁波315336

出  处:《计算机应用与软件》2019年第7期236-241,共6页Computer Applications and Software

基  金:国家自然科学基金项目(51575229)

摘  要:在立体视觉中,匹配之后得到的视差图利用投影模型可以得到原图像的深度信息和三维信息。为了达到提高立体匹配的精度与速度的目的,提高视差图的质量成为了立体匹配的核心问题。利用Canny检测算法、Sobel检测算法、Scharr检测算法对双目图像进行边缘提取。在此基础上,分别使用BM(Boyer-Moore algorithm)算法、SGBM(Semi-global block Matching)算法以及DP(Dynamic programming)算法进行立体匹配,并且分别计算视差图及误匹配率。经分析,Canny检测算法与SGBM算法相结合的方法剔除了大量不相关信息,大幅度减少数据的处理量。选取真实场景图片对该方法进行结论验证。实验结果表明,该方法提高了视差图的质量。In stereo vision,disparity map after stereo matching using projection model can get the depth information and 3D information of the original image. In order to improve the accuracy and speed of stereo matching,improving the quality of disparity map becomes the core problem of stereo matching. The paper extracted edge information of binocular images using Canny,Scharr and Sobel edge detection algorithm. On this basis,BM(Boyer-Moore algorithm),SGBM(Semi-global block matching) algorithm and DP(Dynamic programming) algorithm were used for stereo matching,and disparity map and mismatch rate were calculated respectively. After analysis,the combination of Canny detection algorithm and SGBM algorithm could eliminate a large number of irrelevant information and reduce the amount of data processing. The real scene image was selected to validate the method. The experimental results show that this method improves the quality of disparity map.

关 键 词:立体视觉 边缘检测 立体匹配 视差图 

分 类 号:TP391[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象