OWRT-DETR: A Novel Real-Time Transformer Network for Small-Object Detection in Open-Water Search and Rescue From UAV Aerial Imagery

Uncrewed aerial vehicle (UAV) object detection is crucial in open-water search and rescue missions. Due to varying perspectives and altitudes of UAV images, the apparent size of objects varies significantly. Challenges such as insufficient feature representation and background confusion make open-water object detection particularly difficult. Currently, deep learning-based detection methods rely on convolution to extract features at a fixed spatial scale. This limited receptive field leads to insufficient feature representation, causing false detections and missed detections, which severely impact detection accuracy. This article proposes an efficient feature-enhanced real-time detection network based on Transformer architecture, called OWRT-detection transformer (DETR), to address the challenges of diverse UAV image detection in open-water. To the best of authors’ knowledge, a Transformer-based detection network has not yet been explored for open-water UAV images. OWRT-DETR incorporates a cross-scale feature pyramid interaction module (CFPIM), multiscale sensing fusion (MSSF), and small-object enhancement module (SOEM). These modules enhance cross-scale interaction, cross-channel spatial global association, and local perception of the network, while avoiding increased complexity, improving weak feature representation of small targets, and suppressing easily confused backgrounds. Three public datasets are used to validate the effectiveness of OWRT-DETR. OWRT-DETR achieves an average precision (AP) of 51.5%, 45.9%, and 50.6% on the SeaDronesSee, aerial dataset of floating objects (AFOs), and aerialbus ship (AS) datasets, exceeding the performance of several state-of-the-art models. To ensure efficiency and reduce computational resources, OWRT-DETR is optimized by reconstructing the backbone network using partial convolution (PConv) and Rep, resulting in Light-OWRT-DETR. Compared with OWRT-DETR, Light-OWRT-DETR is faster, uses fewer parameters, requires less computational power, and achieves higher accuracy. The code will be available at https://github.com/mshauima/OWRT-DETR