面向主动跨视角目标地理定位

中文摘要 AI 辅助

跨视角目标地理定位（CVOGL）通常假设查询图像是固定的，忽略了移动智能体主动获取更多信息性观测的能力。为解决这一局限，我们引入了主动跨视角目标地理定位（ActiveGeo），其中智能体顺序选择新的视角并决定何时停止，旨在以最少的观测提高定位精度。我们进一步提出了ActiveMoPT，一个具有三阶段训练的ActiveGeo框架。首先，多视角提示保持适应使模型能够聚合多个查询视角，同时重用初始提示。其次，轨迹引导的策略初始化利用监督智能体轨迹来学习视角选择和初始停止行为。第三，成本感知的策略细化采用带有增益-成本奖励的GRPO来联合优化定位精度和观测效率。我们还构建了ActiveGeo-858，一个包含858个场景和1,716个目标标注的零样本测试集。实验表明，ActiveMoPT在MoP-UAV上平均仅使用1.45个查询视角即达到了最先进的性能，并在ActiveGeo-858的零样本评估中大幅优于之前的CVOGL方法。

英文摘要

Cross-view object geo-localization (CVOGL) typically assumes a fixed query image, overlooking the ability of mobile agents to actively acquire more informative observations. To address this limitation, we introduce Active Cross-View Object Geo-Localization (ActiveGeo), where an agent sequentially selects new viewpoints and determines when to stop, aiming to improve localization with minimal observations. We further propose ActiveMoPT, an ActiveGeo framework with three-stage training. First, Multi-View Prompt-Preserving Adaptation enables the model to aggregate multiple query views while reusing the initial prompt. Second, Trajectory-Guided Policy Initialization uses supervised agent trajectories to learn viewpoint selection and initial stopping behavior. Third, Cost-Aware Policy Refinement employs GRPO with a gain-cost reward to jointly optimize localization accuracy and observation efficiency. We also construct ActiveGeo-858, a zero-shot test set containing 858 scenes and 1,716 target annotations. Experiments show that ActiveMoPT achieves state-of-the-art performance on MoP-UAV using only 1.45 query views on average, and substantially outperforms previous CVOGL approaches under zero-shot evaluation on ActiveGeo-858.

发表机构

• Zhejiang University（浙江大学）
• Beijing University of Technology（北京工业大学）
• Tsinghua University（清华大学）
• Ningbo Global Innovation Center, Zhejiang University（浙江大学宁波全球创新中心）
• Jinhua Institute of Zhejiang University（浙江大学金华研究院）

机构由 AI 辅助整理，请以论文原文为准。