4.6 Article

Monocular Depth Estimation Based on Multi-Scale Depth Map Fusion

Journal

IEEE ACCESS
Volume 9, Issue -, Pages 67696-67705

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3076346

Keywords

Feature extraction; Estimation; Fuses; Decoding; Semantics; Predictive models; Data mining; Monocular depth estimation; dense feature fusion network; depth adaptive fusion module; multi-scale depth maps; indoor

Funding

  1. School Research Projects of Wuyi University [2019AL032]

Ask authors/readers for more resources

In this paper, a Dense feature fusion network and an adaptive depth fusion module are proposed to fuse multi-scale depth maps effectively for improving the accuracy and object information retrieval in monocular depth estimation. The method enhances the depth map's structure and contour information by integrating diverse depth maps at different scales.
Monocular depth estimation is a basic task in machine vision. In recent years, the performance of monocular depth estimation has been greatly improved. However, most depth estimation networks are based on a very deep network to extract features that lead to a large amount of information lost. The loss of object information is particularly serious in the encoding and decoding process. This information loss leads to the estimated depth maps lacking object structure detail and have non-clear edges. Especially in a complex indoor environment, which is our research focus in this paper, the consequences of this loss of information are particularly serious. To solve this problem, we propose a Dense feature fusion network that uses a feature pyramid to aggregate various scale features. Furthermore, to improve the fusion effectiveness of decoded object contour information and depth information, we propose an adaptive depth fusion module, which allows the fusion network to fuse various scale depth maps adaptively to increase object information in the predicted depth map. Unlike other work predicting depth maps relying on U-NET architecture, our depth map predicted by fusing multi-scale depth maps. These depth maps have their own characteristics. By fusing them, we can estimate depth maps that not only include accurate depth information but also have rich object contour and structure detail. Experiments indicate that the proposed model can predict depth maps with more object information than other prework, and our model also shows competitive accuracy. Furthermore, compared with other contemporary techniques, our method gets state-of-the-art in edge accuracy on the NYU Depth V2 dataset.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available