# High-Precision Marine Radar Object Detection Using Tiled Training and SAHI Enhanced YOLOv11-OBB

## TL;DR

A new method combining tiled training, SAHI, and YOLOv11-OBB improves marine radar object detection accuracy and enables real-time performance on edge devices.

## Contribution

The integration of tiled training, SAHI, and YOLOv11-OBB for high-precision marine radar detection with oriented bounding boxes.

## Key findings

- The proposed method achieves over 0.95 mAP@0.5 on the DAAN marine radar dataset.
- Oriented bounding boxes outperform axis-aligned boxes and segmentation masks for vessel localization.
- Lightweight models enable near real-time inference at 4–6 FPS on edge hardware.

## Abstract

What are the main findings?
The combination of tiled training, SAHI, and YOLOv11-OBB achieves over 0.95 mAP@0.5 on the challenging real-world DAAN marine radar dataset, outperforming standard full-image detection approaches.Oriented bounding boxes provide better localization and tighter fits for vessels compared to axis-aligned boxes and segmentation masks.

The combination of tiled training, SAHI, and YOLOv11-OBB achieves over 0.95 mAP@0.5 on the challenging real-world DAAN marine radar dataset, outperforming standard full-image detection approaches.

Oriented bounding boxes provide better localization and tighter fits for vessels compared to axis-aligned boxes and segmentation masks.

What are the implications of the main findings?
High-precision detection with lightweight models enables real-time deployment on edge hardware suitable for small to medium-sized vessels.Accurate orientation and centroid estimation improve maritime tasks such as multi-target tracking and collision avoidance in cluttered environments.

High-precision detection with lightweight models enables real-time deployment on edge hardware suitable for small to medium-sized vessels.

Accurate orientation and centroid estimation improve maritime tasks such as multi-target tracking and collision avoidance in cluttered environments.

Reliable object detection in marine radar imagery is critical for maritime situational awareness, collision avoidance, and autonomous navigation. However, it remains challenging due to sea clutter, small targets, and interference from fixed navigational aids. This study proposes a high-precision detection pipeline that integrates tiled training, Sliced Aided Hyper Inference (SAHI), and an oriented bounding box (OBB) variant of the lightweight YOLOv11 architecture. The proposed approach effectively addresses scale variability in Plan Position Indicator (PPI) radar images. Experiments were conducted on the real-world DAAN dataset provided by the German Aerospace Center (DLR). The dataset consists of 760 full-resolution radar frames containing multiple moving vessels, dynamic own-ship, and clutter sources. A semi-automatic contour-based annotation pipeline was developed to generate multi-format labels, including axis-aligned bounding boxes, oriented bounding boxes (OBBs), and instance segmentation masks, directly from radar echo characteristics. The results demonstrate that the tiled YOLOv11n-OBB model with SAHI achieves an mAP@0.5 exceeding 0.95, with a mean center localization error below 10 pixels. The proposed method shows better performance on small targets compared to standard full-image baselines and other YOLOv11 variants. Moreover, the lightweight models enable near real-time inference at 4–6 FPS on edge hardware. These findings indicate that OBBs and scale-aware strategies enhance detection precision in complex marine radar environments, providing practical advantages for tracking and navigation tasks.