RMK RetinaNet: Rotated Multi-Kernel RetinaNet for Robust Oriented Object Detection in Remote Sensing Imagery
This work provides an incremental improvement for robust oriented object detection in remote sensing imagery, which is crucial for applications like aerial surveillance and urban planning.
This paper addresses challenges in rotated object detection in remote sensing imagery, specifically non-adaptive receptive fields, inadequate multi-scale feature fusion, and angle regression discontinuities. The proposed RMK RetinaNet achieves performance comparable to state-of-the-art methods on DOTA-v1.0, HRSC2016, and UCAS-AOD datasets, demonstrating improved robustness in multi-scale and multi-orientation scenarios.
Rotated object detection in remote sensing imagery is hindered by three major bottlenecks: non-adaptive receptive field utilization, inadequate long-range multi-scale feature fusion, and discontinuities in angle regression. To address these issues, we propose Rotated Multi-Kernel RetinaNet (RMK RetinaNet). First, we design a Multi-Scale Kernel (MSK) Block to strengthen adaptive multi-scale feature extraction. Second, we incorporate a Multi-Directional Contextual Anchor Attention (MDCAA) mechanism into the feature pyramid to enhance contextual modeling across scales and orientations. Third, we introduce a Bottom-up Path to preserve fine-grained spatial details that are often degraded during downsampling. Finally, we develop an Euler Angle Encoding Module (EAEM) to enable continuous and stable angle regression. Extensive experiments on DOTA-v1.0, HRSC2016, and UCAS-AOD show that RMK RetinaNet achieves performance comparable to state-of-the-art rotated object detectors while improving robustness in multi-scale and multi-orientation scenarios.