Height Prediction and Refinement From Aerial Images With Semantic and Geometric Guidance

Elhousni, Mahdi; Zhang, Ziming; Huang, Xinming

doi:10.1109/access.2021.3122894

Cited by 4 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…between heights and semantics, and compared different multitask learning strategies. Elhousni et al [36] used further auxiliary geometric information, the normal vectors, in a twostage network, where the first stage results are fed into the second stage de-noising autoencoder for refinement.…”

Section: A Monocular Height Estimationmentioning

confidence: 99%

HTC-DC Net: Monocular Height Estimation From Single Remote Sensing Images

Chen,

Shi,

Xiong

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

3D geo-information is of great significance for understanding the living environment; however, 3D perception from remote sensing data, especially on a large scale, is restricted, mainly due to the high costs of 3D sensors such as LiDAR.To tackle this problem, we propose a method for monocular height estimation from optical imagery, which is currently one of the richest sources of remote sensing data. As an ill-posed problem, monocular height estimation requires well-designed networks for enhanced representations to improve performance. Moreover, the distribution of height values is long-tailed with the low-height pixels, e.g., the background, as the head, and thus trained networks are usually biased and tend to underestimate building heights. To solve the problems, instead of formalizing the problem as a regression task, we propose HTC-DC Net following the classification-regression paradigm, with the headtail cut (HTC) and the distribution-based constraints (DCs) as the main contributions. HTC-DC Net is composed of the backbone network as the feature extractor, the HTC-AdaBins module, and the hybrid regression process. The HTC-AdaBins module serves as the classification phase to determine bins adaptive to each input image. It is equipped with a vision transformer encoder to incorporate local context with holistic information and involves an HTC to address the long-tailed problem in monocular height estimation for balancing the performances of foreground and background pixels. The hybrid regression process does the regression via the smoothing of bins from the classification phase, which is trained via DCs. The proposed network is tested on datasets of different resolutions, namely , DFC19 (1.3 m) and GBH (3 m). Experimental results show the superiority of the proposed network over existing methods by large margins. Extensive ablation studies demonstrate the effectiveness of each design component. Codes and trained models are published at https://github.com/zhu-xlab/HTC-DC-Net.

show abstract

Section: A Monocular Height Estimationmentioning

confidence: 99%