VisLanding: Monocular 3D Perception for UAV Safe Landing via Depth-Normal Synergy

TL;DR

VisLanding introduces a monocular 3D perception framework that uses depth-normal synergy prediction to accurately identify safe landing zones for UAVs in complex environments, enhancing robustness and generalization.

Contribution

The paper proposes a novel end-to-end safe landing zone estimation framework leveraging depth-normal synergy prediction and a safe zone segmentation branch, improving accuracy and robustness in UAV landing.

Findings

Significantly improves safe zone identification accuracy.

Demonstrates strong cross-domain generalization and robustness.

Enables estimation of landing zone area for decision support.

Abstract

This paper presents VisLanding, a monocular 3D perception-based framework for safe UAV (Unmanned Aerial Vehicle) landing. Addressing the core challenge of autonomous UAV landing in complex and unknown environments, this study innovatively leverages the depth-normal synergy prediction capabilities of the Metric3D V2 model to construct an end-to-end safe landing zones (SLZ) estimation framework. By introducing a safe zone segmentation branch, we transform the landing zone estimation task into a binary semantic segmentation problem. The model is fine-tuned and annotated using the WildUAV dataset from a UAV perspective, while a cross-domain evaluation dataset is constructed to validate the model's robustness. Experimental results demonstrate that VisLanding significantly enhances the accuracy of safe zone identification through a depth-normal joint optimization mechanism, while retaining the zero-shot generalization advantages of Metric3D V2. The proposed method exhibits superior generalization and robustness in cross-domain testing compared to other approaches. Furthermore, it enables the estimation of landing zone area by integrating predicted depth and normal information, providing critical decision-making support for practical applications.