University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization

Zheng, Zhedong; Wei, Yunchao; Yang, Yi

doi:10.1145/3394171.3413896

Cited by 181 publications

(172 citation statements)

References 40 publications

(119 reference statements)

Supporting

Mentioning

172

Contrasting

Order By: Relevance

“…The LCM is compared with the model of Zheng et al (hereinafter referred to as the Zheng model), which is the only study using the University-1652 dataset for cross-view image matching to date [46]. For a fair and reliable comparison, this data division in this study is consistent with the Zheng model.…”

Section: Test Dataset Splitmentioning

confidence: 55%

“…After passing through the convolutional layers of ResNet50, the feature dimension of a 384 × 384 × 3 image is 12 × 12 × 2048. Next, we use the global pooling method to change the image feature into a feature vector with a dimension of 2048 [46]. To change the size of the feature vector, a fully connected layer is added after the pooling layer.…”

Section: Methods Frameworkmentioning

confidence: 99%

“…Therefore, we need an indicator to measure the correlation between A and the images in B. In this framework, the cosine similarity (CS) is adopted to measure the correlation between the features of image A and the features of the image in B [46]. The larger CS means a smaller distance between the two features and a greater correlation between the corresponding images.…”

Section: Methods Frameworkmentioning

confidence: 99%

“…The dataset used in this study is University-1652, released by Zheng et al [46], which contains 1652 buildings (1652 locations) from 72 universities worldwide. Each building consists of images from three different views, including satellite view, UAV view, and ground view (street view).…”

Section: Datasetsmentioning

confidence: 99%

“…Workman and Jacobs [36] found that the classification model trained on the place dataset performed well in the feature recognition of other places. Zheng et al [46] used two-branch CNN and category labels to match the UAV-view, satellite-view, and ground-view images.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Practical Cross-View Image Matching Method between UAV and Satellite for UAV-Based Geo-Localization

et al. 2020

View full text Add to dashboard Cite

Cross-view image matching has attracted extensive attention due to its huge potential applications, such as localization and navigation. Unmanned aerial vehicle (UAV) technology has been developed rapidly in recent years, and people have more opportunities to obtain and use UAV-view images than ever before. However, the algorithms of cross-view image matching between the UAV view (oblique view) and the satellite view (vertical view) are still in their beginning stage, and the matching accuracy is expected to be further improved when applied in real situations. Within this context, in this study, we proposed a cross-view matching method based on location classification (hereinafter referred to LCM), in which the similarity between UAV and satellite views is considered, and we implemented the method with the newest UAV-based geo-localization dataset (University-1652). LCM is able to solve the imbalance of the input sample number between the satellite images and the UAV images. In the training stage, LCM can simplify the retrieval problem into a classification problem and consider the influence of the feature vector size on the matching accuracy. Compared with one study, LCM shows higher accuracies, and Recall@K (K ∈ {1, 5, 10}) and the average precision (AP) were improved by 5–10%. The expansion of satellite-view images and multiple queries proposed by the LCM are capable of improving the matching accuracy during the experiment. In addition, the influences of different feature sizes on the LCM’s accuracy are determined, and we found that 512 is the optimal feature size. Finally, the LCM model trained based on synthetic UAV-view images was evaluated in real-world situations, and the evaluation result shows that it still has satisfactory matching accuracy. The LCM can realize the bidirectional matching between the UAV-view image and the satellite-view image and can contribute to two applications: (i) UAV-view image localization (i.e., predicting the geographic location of UAV-view images based on satellite-view images with geo-tags) and (ii) UAV navigation (i.e., driving the UAV to the region of interest in the satellite-view image based on the flight record).

show abstract

Section: Test Dataset Splitmentioning

confidence: 55%

Section: Methods Frameworkmentioning

confidence: 99%

Section: Methods Frameworkmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Practical Cross-View Image Matching Method between UAV and Satellite for UAV-Based Geo-Localization

et al. 2020

View full text Add to dashboard Cite

show abstract

Building pose detection for the characterization of reinforced concrete buildings

Iturburu,

Liu,

Zhang

et al. 2024

Structural Design Tall Build

View full text Add to dashboard Cite

SummaryThe automated identification of building characteristics for seismic vulnerability remains a challenge for governments due to the high number of buildings in cities. The diverse architectural styles of these buildings complicate the automated identification of building information (e.g., number of stories, structural system, and material type). Deep learning techniques lose accuracy as they generalize information, while the visual contents of a building exhibit a considerable range and diversity. This study leverages the pose detection technique to tackle such issues by focusing on a common construction style: reinforced concrete buildings representing columns, beams, or floors on the façade. With an aim to enable the assessment of seismic vulnerability, the technique developed herein is conceived for buildings with up to six stories that are more likely to be moment‐frame buildings. The AI‐enabled proposed framework starts with collecting building images and categorizing those containing this specific building type. A bounding box detector is then used to isolate building facades, for the subsequent identification of the structural frame with the High‐Resolution Network (HR‐Net). For demonstration, we illustrate this technique by identifying the structural frame on concrete buildings with a sample dataset developed based on buildings found in Mexico City in a pre‐earthquake event state.

show abstract

Content-Aware Hierarchical Representation Selection for Cross-View Geo-Localization

Lu¹,

Pu²,

Chen³

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization

Cited by 181 publications

References 40 publications

A Practical Cross-View Image Matching Method between UAV and Satellite for UAV-Based Geo-Localization

A Practical Cross-View Image Matching Method between UAV and Satellite for UAV-Based Geo-Localization

Building pose detection for the characterization of reinforced concrete buildings

Content-Aware Hierarchical Representation Selection for Cross-View Geo-Localization

Contact Info

Product

Resources

About