期刊
IEEE ACCESS
卷 9, 期 -, 页码 145638-145647出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3122894
关键词
Semantics; Task analysis; Noise reduction; Deep learning; Three-dimensional displays; Pipelines; Image reconstruction; UAV; height; DSM; CNN; autoencoders; multi-task
The paper presents a two-stage approach utilizing multi-task neural network and denoising autoencoder to predict height maps, which achieves more accurate height prediction results compared to traditional methods.
Deep learning provides a powerful new approach to many computer vision tasks. Height prediction from aerial images is one of those tasks which benefited greatly from the deployment of deep learning, thus replacing traditional multi-view geometry techniques. This manuscript proposes a two-stage approach to solve this task, where the first stage is a multi-task neural network whose main branch is used to predict the height map resulting from a single RGB aerial input image, while being augmented with semantic and geometric information from two additional branches. The second stage is a refinement step, where a denoising autoencoder is used to correct some errors in the first stage prediction results, producing a more accurate height map. Experiments on two publicly available datasets show that the proposed method is able to outperform state-of-the-art computer vision based and deep learning-based height prediction methods. Code is publicly available at: https://github.com/melhousni/DSMNet.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据