摘要
针对无监督单目深度估计生成深度图质量低、边界模糊、伪影过多等问题,该文提出基于密集特征融合的深度网络编解码结构。设计密集特征融合层(DFFL)并将其以密集连接的形式填充U型编解码器,同时精简编码器部分,实现编、解码器的性能均衡。在训练过程中,将校正后的双目图像输入给网络,以重构视图的相似性约束网络生成视差图。测试时,根据已知的相机基线距离与焦距将生成的视差图转换为深度图。在KITTI数据集上的实验结果表明,该方法在预测精度和误差值上优于现有的算法。
In view of the problems of low quality,blurred borders and excessive artifacts generated by unsupervised monocular depth estimation,a deep network encoder-decoder structure based on dense feature fusion is proposed.A Dense Feature Fusion Layer(DFFL)is designed and it is filled with U-shaped encoderdecoder in the form of dense connection,while simplifying the encoder part to achieve a balanced performance of the encoder and decoder.During the training process,the calibrated stereo pair is input to the network to constrain the network to generate disparity maps by the similarity of reconstructed views.During the test process,the generated disparity map is converted into a depth map based on the known camera baseline distance and focal length.The experimental results on the KITTI data set show that this method is superior to the existing algorithms in terms of prediction accuracy and error value.
作者
陈莹
王一良
CHEN Ying;WANG Yiliang(Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education),Jiangnan University,Wuxi 214122,China)
出处
《电子与信息学报》
EI
CSCD
北大核心
2021年第10期2976-2984,共9页
Journal of Electronics & Information Technology
基金
国家自然科学基金(61573168)。
关键词
深度估计
无监督
密集特征融合层
编解码器
Depth estimation
Unsupervised learning
Dense Feature Fusion Layer(DFFL)
Encoder-decoder