Finding Point with Image: A Simple and Efficient Method for UAV Self-Localization

13 Aug 2022  ·  Ming Dai, Enhui Zheng, ZhenHua Feng, Jiahao Chen, Wankou Yang ·

Image retrieval has emerged as a prominent solution for the self-localization task of unmanned aerial vehicles (UAVs). However, this approach involves complicated pre-processing and post-processing operations, placing significant demands on both computational and storage resources. To mitigate this issue, this paper presents an end-to-end positioning framework, namely Finding Point with Image (FPI), which aims to directly identify the corresponding location of a UAV in satellite-view images via a UAV-view image. To validate the practicality of our framework, we construct a paired dataset, namely UL14, that consists of UAV and satellite views. In addition, we establish two transformer-based baseline models, Post Fusion and Mix Fusion, for end-to-end training and inference. Through experiments, we can conclude that fusion in the backbone network can achieve better performance than later fusion. Furthermore, considering the singleness of paired images, Random Scale Crop (RSC) is proposed to enrich the diversity of the paired data. Also, the ratio and weight of positive and negative samples play a key role in model convergence. Therefore, we conducted experimental verification and proposed a Weight Balance Loss (WBL) to weigh the impact of positive and negative samples. Last, our proposed baseline based on Mix Fusion structure exhibits superior performance in time and storage efficiency, amounting to just 1/24 and 1/68, respectively, while delivering comparable or even superior performance compared to the image retrieval method. The dataset and code will be made publicly available.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods