HMPNet: A Feature Aggregation Architecture for Maritime Object Detection from a Shipborne Perspective

TL;DR

HMPNet is a lightweight, feature-aggregation architecture designed for maritime object detection, leveraging a new maritime dataset to improve accuracy and efficiency in shipborne navigation systems.

Contribution

The paper introduces HMPNet, a novel lightweight detection model with hierarchical dynamic modulation and multi-scale feature aggregation, tailored for maritime environments.

Findings

HMPNet achieves 3.3% higher mAP than YOLOv11n.

HMPNet reduces model parameters by 23%.

HMPNet outperforms existing methods in accuracy and efficiency.

Abstract

In the realm of intelligent maritime navigation, object detection from a shipborne perspective is paramount. Despite the criticality, the paucity of maritime-specific data impedes the deployment of sophisticated visual perception techniques, akin to those utilized in autonomous vehicular systems, within the maritime context. To bridge this gap, we introduce Navigation12, a novel dataset annotated for 12 object categories under diverse maritime environments and weather conditions. Based upon this dataset, we propose HMPNet, a lightweight architecture tailored for shipborne object detection. HMPNet incorporates a hierarchical dynamic modulation backbone to bolster feature aggregation and expression, complemented by a matrix cascading poly-scale neck and a polymerization weight sharing detector, facilitating efficient multi-scale feature aggregation. Empirical evaluations indicate that HMPNet surpasses current state-of-the-art methods in terms of both accuracy and computational efficiency, realizing a 3.3% improvement in mean Average Precision over YOLOv11n, the prevailing model, and reducing parameters by 23%.