Skip to content
Conference

CAA-YOLO: SAR image detection method based on improved YOLO11

Oct 2026 · International Conference on Image Processing, Object Detection and Tracking · Vol 14506, pp. 145061K - 145061K-6 · 0 citations · 15 references
Engineering

Abstract

SAR image ship detection faces issues such as speckle noise, weak small target features, and arbitrary target rotation. This paper optimizes the algorithm based on YOLO11 by integrating three types of modules. The lightweight Context module expands the receptive field, enhances small target features, and suppresses noise; the AIFI module extracts rotation-invariant features based on positional encoding, completes global correlations with self-attention, and corrects localization errors; the AMF alternating scale fusion module fuses multi-layer features, improving multi-scale detection balance. Tested on the HRSID and SSDD datasets, the mAP50 reached 88.5% and 97.3%, respectively, with overall performance superior to similar algorithms. It is highly adaptable to complex scenarios and can serve marine remote sensing intelligent monitoring tasks.

View source

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.