OPODet: Toward Open World Potential Oriented Object Detection in Remote Sensing Images
- 16 October 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-13
Abstract
Despite recent advances in object detection, closed-set detectors with fixed training classes often overlook or misclassify unannotated objects during testing. To address this, open world object detection algorithms identify and label these objects as unknown, better aligning with real-world scenarios and human learning. However, remote sensing images, with their arbitrary object orientations and large inter-class feature disparities, pose significant challenges for these algorithms. To tackle this, we propose OPODet, an Open-world Potential Oriented object Detection framework for remote sensing images. Specifically, we incorporate the Oriented Unknown Aware Region Proposal Network (OUA-RPN) into traditional oriented object detection models, enabling the network to predict potential oriented objects. To address the significant inter-class feature differences among potential unknown classes, we propose a Multi-unknown-class Clustering Aligning Prototype learning method (MCAP) to prevent feature collapse in the feature space. Additionally, to address the lack of rotation information for potential objects, we introduce a Rotation Potential Target Consistency Algorithm (RPTC) to impose explicit rotation constraints for generating more accurate potential unknown proposals. Extensive experiments on DIOR-R, DOTA-v1.0, and HRSC2016 datasets demonstrate the effectiveness of our approach in detecting potential oriented objects.Keywords
Funding Information
- National Natural Science Foundation of China (62271018)
This publication has 68 references indexed in Scilit:
- M-RRFS: A Memory-Based Robust Region Feature Synthesizer for Zero-Shot Object DetectionInternational Journal of Computer Vision, 2024
- PARDet: Dynamic point set alignment for rotated object detectionPattern Recognition, 2024
- UC-OWOD: Unknown-Classified Open World Object Detection2022
- Few-shot object detection via baby learningImage and Vision Computing, 2022
- Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery2019
- Zero-Shot Object Detection2018
- Feature Pyramid Networks for Object Detection2017
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014