自适应多尺度特征融合的单目图像深度估计
Monocular Image Depth Estimation with Adaptive Multi-scale Feature Fusion
陈国军 1付云鹏 1于丽香 1崔涛1
作者信息
- 1. 中国石油大学(华东)计算机科学与技术学院,青岛 266580
- 折叠
摘要
在基于深度学习的单目图像深度估计方法中,卷积神经网络在下采样过程中会出现图像深度信息丢失的情况,导致物体边缘深度估计效果不佳.提出一种多尺度特征融合的方法,并采用自适应融合的策略,根据特征数据动态调整不同尺度特征图的融合比例,实现对多尺度特征信息的充分利用.由于空洞空间金字塔池化(ASPP)在单目深度估计任务中,会丢失图像中的像素点信息,影响小物体的预测结果.通过在对深层特征图使用ASPP时融合浅层特征图的丰富特征信息,提高深度估计结果.在NYU-DepthV2 室内场景数据集的实验结果表明,本文所提方法在物体边缘处有更准确的预测,并且对小物体的预测有明显的提升,均方根误差(RMSE)达到 0.389,准确率(δ<1.25)达到0.897,验证了方法的有效性.
Abstract
In the monocular image depth estimation method based on deep learning,the depth information of the image is lost during the subsampling process of the convolutional neural networks,which leads to poor depth estimation of object edges.To solve this problem,this study presents a multi-scale feature fusion method,and an adaptive fusion strategy is adopted to dynamically adjust the fusion ratio of feature maps of different scales according to feature data to make full use of multi-scale feature information.In the monocular depth estimation task using atrous spatial pyramid pooling(ASPP),the pixel information loss affects the prediction results of small objects.When using ASPP on deep feature maps,the depth estimation result is improved by fusing rich feature information of shallow feature maps.The experimental results on the NYU-DepthV2 indoor dataset show that the method proposed in this study has a more accurate prediction of object edges and significantly improves the prediction of small objects.The root mean square error(RMSE)reaches 0.389 and the accuracy(δ<1.25)reaches 0.897,which verifies the effectiveness of the method.
关键词
单目图像/深度估计/卷积神经网络/多尺度特征Key words
monocular image/depth estimation/convolutional neural network(CNN)/multi-scale feature引用本文复制引用
基金项目
山西省交通建设科技项目(2019-2-8)
出版年
2024
NETL
NSTL
万方数据