用视觉语言模型提升自动驾驶定位精度
GeoVLM: Improving Automated Vehicle Geolocalisation Using Vision-Language Matching
- 通过自然语言描述匹配地表与卫星图像
- 在VIGOR和UK数据集上提升首位匹配准确率
- 零样本能力让定位结果可解释，适合车载系统
跨视图地理定位通过将地面图像与数据库中的地理标记卫星图像匹配，确定自动驾驶车辆的粗略位置。尽管该技术已有进展，但仍面临场景相似导致正确匹配难以排第一的问题。现有方法虽召回率高，但常无法将正确图像排在首位。本文提出GeoVLM，利用视觉语言模型的零样本能力，通过可解释的跨视图语言描述实现跨视图地理定位。GeoVLM是一种可训练的重排序方法，显著提升了跨视图地理定位的最佳匹配准确率。实验在标准基准VIGOR、University-1652以及本文新提出的跨视图英国数据集Cross-View United Kingdom上进行。结果表明，相比现有最先进方法，GeoVLM在检索性能上取得提升，且借助可解释的自然语言描述增强了可靠性。代码已开源。
原文摘要 · Abstract (English)
Cross-view geo-localisation identifies coarse geographical position of an automated vehicle by matching a ground-level image to a geo-tagged satellite image from a database. Despite the advancements in Cross-view geo-localisation, significant challenges still persist such as similar looking scenes which makes it challenging to find the correct match as the top match. Existing approaches reach high recall rates but they still fail to rank the correct image as the top match. To address this challenge, this paper proposes GeoVLM, a novel approach which uses the zero-shot capabilities of vision language models to enable cross-view geo-localisation using interpretable cross-view language descriptions. GeoVLM is a trainable reranking approach which improves the best match accuracy of cross-view geo-localisation. GeoVLM is evaluated on standard benchmark VIGOR and University-1652 and also through real-life driving environments using Cross-View United Kingdom, a new benchmark dataset introduced in this paper. The results of the paper show that GeoVLM improves retrieval performance of cross-view geo-localisation compared to the state-of-the-art methods with the help of explainable natural language descriptions. The code is available at https://github.com/CAV-Research-Lab/GeoVLM
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。