Related papers: Object-level Cross-view Geo-localization with Location Enhancement and Multi-Head Cross Attention

Object-level Cross-view Geo-localization with Location Enhancement and Multi-Head Cross Attention

URL: http://arxiv.org/abs/2505.17911v1
Date: Fri, 23 May 2025 13:55:56 GMT
Title: Object-level Cross-view Geo-localization with Location Enhancement and Multi-Head Cross Attention
Authors: Zheyang Huang, Jagannath Aryal, Saeid Nahavandi, Xuequan Lu, Chee Peng Lim, Lei Wei, Hailing Zhou,
Abstract summary: Cross-view geo-localization determines the location of a query image, captured by a drone or ground-based camera, by matching it to a geo-referenced satellite image.<n>We propose an Object-level Cross-view Geo-localization Network (OCGNet) to address these challenges.<n>OCGNet achieves state-of-the-art performance on a public dataset, CVOGL.
Score: 17.777115738099916
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Cross-view geo-localization determines the location of a query image, captured by a drone or ground-based camera, by matching it to a geo-referenced satellite image. While traditional approaches focus on image-level localization, many applications, such as search-and-rescue, infrastructure inspection, and precision delivery, demand object-level accuracy. This enables users to prompt a specific object with a single click on a drone image to retrieve precise geo-tagged information of the object. However, variations in viewpoints, timing, and imaging conditions pose significant challenges, especially when identifying visually similar objects in extensive satellite imagery. To address these challenges, we propose an Object-level Cross-view Geo-localization Network (OCGNet). It integrates user-specified click locations using Gaussian Kernel Transfer (GKT) to preserve location information throughout the network. This cue is dually embedded into the feature encoder and feature matching blocks, ensuring robust object-specific localization. Additionally, OCGNet incorporates a Location Enhancement (LE) module and a Multi-Head Cross Attention (MHCA) module to adaptively emphasize object-specific features or expand focus to relevant contextual regions when necessary. OCGNet achieves state-of-the-art performance on a public dataset, CVOGL. It also demonstrates few-shot learning capabilities, effectively generalizing from limited examples, making it suitable for diverse applications (https://github.com/ZheyangH/OCGNet).

Related papers

VAGeo: View-specific Attention for Cross-View Object Geo-Localization [19.4845592498138]
Cross-view object geo-localization (CVOGL) aims to locate an object of interest in a captured ground- or drone-view image within the satellite image.<n>This paper proposes a novel View-specific Attention Geo-localization method (VAGeo) for accurate CVOGL.
arXiv Detail & Related papers (2025-01-13T10:42:18Z)
GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks.<n>Our benchmark features over 10,000 manually verified instructions and spanning diverse visual conditions, object types, and scales.<n>We evaluate several state-of-the-art VLMs to assess performance on geospatial-specific challenges.
arXiv Detail & Related papers (2024-11-28T18:59:56Z)
United Domain Cognition Network for Salient Object Detection in Optical Remote Sensing Images [21.76732661032257]
We propose a novel United Domain Cognition Network (UDCNet) to jointly explore the global-local information in the frequency and spatial domains. Experimental results demonstrate the superiority of the proposed UDCNet over 24 state-of-the-art models.
arXiv Detail & Related papers (2024-11-11T04:12:27Z)
GOMAA-Geo: GOal Modality Agnostic Active Geo-localization [49.599465495973654]
We consider the task of active geo-localization (AGL) in which an agent uses a sequence of visual cues observed during aerial navigation to find a target specified through multiple possible modalities. GOMAA-Geo is a goal modality active geo-localization agent for zero-shot generalization between different goal modalities.
arXiv Detail & Related papers (2024-06-04T02:59:36Z)
Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs [5.891295920078768]
We introduce an advanced approach for fine-grained object visual key field detection. First, we use the segment anything model (SAM) to generate detailed spatial maps of objects in images. Next, we use Vision Studio to extract semantic object descriptions. Third, we employ GPT-4's common sense knowledge, bridging the gap between an object's semantics and its spatial map.
arXiv Detail & Related papers (2024-04-01T14:53:36Z)
GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization [61.10806364001535]
Worldwide Geo-localization aims to pinpoint the precise location of images taken anywhere on Earth. Existing approaches divide the globe into discrete geographic cells, transforming the problem into a classification task. We propose GeoCLIP, a novel CLIP-inspired Image-to-GPS retrieval approach that enforces alignment between the image and its corresponding GPS locations.
arXiv Detail & Related papers (2023-09-27T20:54:56Z)
DQnet: Cross-Model Detail Querying for Camouflaged Object Detection [54.82390534024954]
A convolutional neural network (CNN) for camouflaged object detection tends to activate local discriminative regions while ignoring complete object extent. In this paper, we argue that partial activation is caused by the intrinsic characteristics of CNN. In order to obtain feature maps that could activate full object extent, a novel framework termed Cross-Model Detail Querying network (DQnet) is proposed.
arXiv Detail & Related papers (2022-12-16T06:23:58Z)
CVLNet: Cross-View Semantic Correspondence Learning for Video-based Camera Localization [89.69214577915959]
This paper tackles the problem of Cross-view Video-based camera localization. We propose estimating the query camera's relative displacement to a satellite image before similarity matching. Experiments have demonstrated the effectiveness of video-based localization over single image-based localization.
arXiv Detail & Related papers (2022-08-07T07:35:17Z)
Visual and Object Geo-localization: A Comprehensive Survey [11.120155713865918]
Geo-localization refers to the process of determining where on earth some entity' is located. This paper provides a comprehensive survey of geo-localization involving images, which involves either determining from where an image has been captured (Image geo-localization) or geo-locating objects within an image (Object geo-localization) We will provide an in-depth study, including a summary of popular algorithms, a description of proposed datasets, and an analysis of performance results to illustrate the current state of each field.
arXiv Detail & Related papers (2021-12-30T20:46:53Z)
Location-Sensitive Visual Recognition with Cross-IOU Loss [177.86369890708457]
This paper proposes a unified solution named location-sensitive network (LSNet) for object detection, instance segmentation, and pose estimation. Based on a deep neural network as the backbone, LSNet predicts an anchor point and a set of landmarks which together define the shape of the target object.
arXiv Detail & Related papers (2021-04-11T02:17:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.