Oriented RepPoints for Aerial Object Detection

Li, Wentong; Chen, Yijie; Hu, Kaixuan; Zhu, Jianke

doi:10.1109/cvpr52688.2022.00187

Cited by 255 publications

(63 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During training and inference, all images are resized to 800 × 1333 without changing the aspect ratios. For a fair comparison with the compared methods, we follow the same dataset splits setting in [ 51 ], where the ratio between the training set, validation set, and testing set is 5:2:3.…”

Section: Resultsmentioning

confidence: 99%

Shared-Weight-Based Multi-Dimensional Feature Alignment Network for Oriented Object Detection in Remote Sensing Imagery

Zhu

2022

Sensors

View full text Add to dashboard Cite

Arbitrarily Oriented Object Detection in aerial images is a highly challenging task in computer vision. The mainstream methods are based on the feature pyramid, while for remote-sensing targets, the misalignment of multi-scale features is always a thorny problem. In this article, we address the feature misalignment problem of oriented object detection from three dimensions: spatial, axial, and semantic. First, for the spatial misalignment problem, we design an intra-level alignment network based on leading features that can synchronize the location information of different pyramid features by sparse sampling. For multi-oriented aerial targets, we propose an axially aware convolution to solve the mismatch between the traditional sampling method and the orientation of instances. With the proposed collaborative optimization strategy based on shared weights, the above two modules can achieve coarse-to-fine feature alignment in spatial and axial dimensions. Last but not least, we propose a hierarchical-wise semantic alignment network to address the semantic gap between pyramid features that can cope with remote-sensing targets at varying scales by endowing the feature map with global semantic perception across pyramid levels. Extensive experiments on several challenging aerial benchmarks show state-of-the-art accuracy and appreciable inference speed. Specifically, we achieve a mean Average Precision (mAP) of 78.11% on DOTA, 90.10% on HRSC2016, and 90.29% on UCAS-AOD.

show abstract

Section: Resultsmentioning

confidence: 99%

Shared-Weight-Based Multi-Dimensional Feature Alignment Network for Oriented Object Detection in Remote Sensing Imagery

Zhu

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…A critical feature-capturing network (CFC-Net) [29] was proposed to extract better discriminative features. Li et al [40] proposed the oriented reppoints for aerial object detection.…”

Section: Arbitrary Oriented Object Detectionmentioning

confidence: 99%

Dynamic Soft Label Assignment for Arbitrary-Oriented Ship Detection

Bian

Chen

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

“…One is built by taking the median values of points from the SemanticKITTI [60] point cloud, a semantically-labeled lidar scan captured from a ground viewpoint. The other is created by manually annotating Google Satellite images using QGIS [61] (the annotation can be automated by classifiers trained for aerial/satellite images [62], [63]). The aerial and lidar reference maps for Sequence 00 can be seen in Fig.…”

Section: Kitti Dataset Experimental Setupmentioning

confidence: 99%

Global Localization in Unstructured Environments using Semantic Object Maps Built from Various Viewpoints

Ankenbauer¹,

C.²,

How³

2023

Preprint

View full text Add to dashboard Cite

We present a novel framework for global localization and guided relocalization of a vehicle in an unstructured environment. Compared to existing methods, our pipeline does not rely on cues from urban fixtures (e.g., lane markings, buildings), nor does it make assumptions that require the vehicle to be navigating on a road network. Instead, we achieve localization in both urban and non-urban environments by robustly associating and registering the vehicle's local semantic object map with a compact semantic reference map, potentially built from other viewpoints, time periods, and/or modalities. Robustness to noise, outliers, and missing objects is achieved through our graph-based data association algorithm. Further, the guided relocalization capability of our pipeline mitigates drift inherent in odometry-based localization after the initial global localization. We evaluate our pipeline on two publiclyavailable, real-world datasets to demonstrate its effectiveness at global localization in both non-urban and urban environments. The Katwijk Beach Planetary Rover dataset [1] is used to show our pipeline's ability to perform accurate global localization in unstructured environments. Demonstrations on the KITTI dataset [2] achieve an average pose error of 3.8 m across all 35 localization events on Sequence 00 when localizing in a reference map created from aerial images. Compared to existing works, our pipeline is more general because it can perform global localization in unstructured environments using maps built from different viewpoints.

show abstract

Oriented RepPoints for Aerial Object Detection

Cited by 255 publications

References 38 publications

Shared-Weight-Based Multi-Dimensional Feature Alignment Network for Oriented Object Detection in Remote Sensing Imagery

Shared-Weight-Based Multi-Dimensional Feature Alignment Network for Oriented Object Detection in Remote Sensing Imagery

Dynamic Soft Label Assignment for Arbitrary-Oriented Ship Detection

Global Localization in Unstructured Environments using Semantic Object Maps Built from Various Viewpoints

Contact Info

Product

Resources

About