Oriented RepPoints for Aerial Object Detection

By Wentong Li, Jianke Zhu. Computer Vision and Pattern Recognition, 2021

499 citations recorded by the source corpus.

In contrast to the generic object, aerial targets are often non-axis aligned with arbitrary orientations having the cluttered surroundings. Unlike the mainstreamed approaches regressing the bounding box orientations, this paper proposes an effective adaptive points learning approach to aerial object detection by taking advantage of the adaptive points representation, which is able to capture the geometric information of the arbitrary-oriented instances. To this end, three oriented conversion functions are presented to facilitate the classification and localization with accurate orientation. Moreover, we propose an effective quality assessment and sample assignment scheme for adaptive points learning toward choosing the representative oriented reppoints samples during training, which is able to capture the non-axis aligned features from adjacent objects or background noises. A spatial constraint is introduced to penalize the outlier points for roust adaptive learning. Experimental results on four challenging aerial datasets including DOTA, HRSC2016, UCAS-AOD and DIOR-R, demonstrate the efficacy of our proposed approach. The source code is availabel at: https://github.com/LiWentomng/OrientedRepPoints.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7cafbefcceba0f3f59d83b49602d731606b1cd58

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, background): “Oriented RepPoints [180] achieves 26.3% points on AP metric which is slightly inferior to Rotated RetinaNet, exhibiting such point set representation is unamiable for small objects in aerial scenario, especially for those with large aspect ratios which will be discussed in next section.”
Transformers in Remote Sensing: A Survey (2022, methodology): “RepPoints utilizes same structure of the shared head as in [46], except a quality assessment and sample assignment strategy (APAA) is employed for selecting high-quality sample points for training.”
Poly Kernel Inception Network for Remote Sensing Detection (2024, methodology): “Consequently, numerous prior efforts have been dedicated to developing various oriented bounding box (OBB) detectors [10, 20, 31, 65, 67, 71] and improving the angle prediction accuracy for OBBs [68, 70, 72–74].”