基于改进双目视觉算法的三维重建研究
Research on 3D reconstruction based on improved binocular vision algorithm
邹家豪 1赵燕东1
作者信息
- 1. 北京林业大学工学院,北京 100083
- 折叠
摘要
为解决现有立体匹配算法在图像弱纹理等区域鲁棒性差以及模型参数较大的问题,对PS-MNet立体匹配方法进行改善,通过使用空洞空间卷积池化金字塔结构(atrous spatial pooling pyr-amid,ASPP)提取图像在不同尺度下的空间特征信息.随后引入通道注意力机制,给予不同尺度的特征信息相应的权重.融合以上信息构建匹配代价卷,利用沙漏形状的编解码网络对其进行规范化操作,从而确定特征点在各种视差情况下的相互对应关系,最后采用线性回归的方法得到相应的视差图.与PSMNet相比,该研究在SceneFlow和KITTI2015数据集里的误差率各自减少了14.6％和11.1％,且计算复杂度下降了 55％.相比较于传统算法,可以改善视差图精度,提升三维重建点云数据质量.
Abstract
To address the issues of poor robustness and large model parameters in existing stereo matc-hing algorithms in areas such as weak texture images,the PSMNet stereo matching method is improved by using an atrous spatial convolutional pooling pyramid structure(ASPP)to extract spatial feature in-formation of images at different scales.Subsequently,a channel attention mechanism is introduced to as-sign corresponding weights to feature information at different scales.The above information is integrated to construct a matching cost volume,an hourglass shaped encoding and decoding network is used to standardize it,and determine the correspondence between feature points in various disparity situations.Finally,the linear regression is used to obtain the corresponding disparity map.Compared with PSMNet,the error rates of this study in the SceneFlow and KITTI 2015 datasets are reduced by 14.6％and 11.1％respectively,and the computational complexity is reduced by 55％.Compared with traditional al-gorithms,it can improve the accuracy of disparity maps and enhance the quality of 3D reconstructed point cloud data.
关键词
双目视觉/立体匹配/点云/三维重建Key words
binocular vision/stereo matching/point cloud/3D reconstruction引用本文复制引用
基金项目
中国博士后科学基金(2022T150055)
北京市共建资助项目()
出版年
2024
NETL
NSTL
万方数据