YOLO-ESFM: A multi-scale YOLO algorithm for sea surface object detection
Maochun Wei, Keyu Chen, Fei Yan, Jikang Ma, Kaiming Liu, En Cheng
Abstract
Environmental perception and object detection are pivotal research topics in the marine domain. The sea surface presents unique challenges, including harsh weather conditions, wave interference, and multi-scale targets, often resulting in suboptimal detection results. To address these issues, we present an innovative solution: the integration of the Efficient Scale Fusion Module (ESFM) into the advanced YOLO architecture, resulting in the enhanced model, YOLO-ESFM. The ESFM serves as both the backbone and detection head of the network, significantly improving performance compared to the baseline models in YOLOv5s, YOLOv7-tiny, and YOLOv7. Furthermore, to tackle the limitations of the CIOU in YOLOv7, we introduce an improved method, ZIOU, which has been rigorously evaluated and proven effective on the Sea Surface Target Dataset. Comparative studies demonstrate that YOLO-ESFM not only maintains efficiency in terms of parameters and FLOPs but also surpasses YOLOv7 in detection accuracy on both the Sea Surface Target Dataset and the PASCAL VOC 07+12 Dataset. • Improved Object Detection Metric: This paper presents a subtle yet effective modification to the YOLOv7 model by introducing ZIOU as an improved alternative to CIOU. Experimental results confirm that ZIOU significantly outperforms CIOU. • Versatile Multi-Scale Module: A novel multi-scale module is proposed, which can serve as the backbone and head of different networks. This module demonstrates its adaptability and effectiveness across diverse datasets, including The Sea Surface Target Dataset and the PASCAL VOC 07+12 Dataset. It offers a valuable tool for enhancing object detection across a wide range of applications. • YOLO-ESFM: A Superior Network: This work introduces YOLO-ESFM, a novel network architecture that surpasses YOLOv7 in terms of performance. YOLO-ESFM, featuring the integration of the Efficient Scale Fusion Module (ESFM) and ZIOU, outperforms the previous YOLO models and sets a new standard in object detection for marine environments and beyond.