Bow Direction Detection Based on Angular Coding With Heading Intersection Over Union Loss

doi:10.1109/TGRS.2025.3556480

Bow Direction Detection Based on Angular Coding With Heading Intersection Over Union Loss

2025-01-01

0

PRE

AI

熊守美 (Shengwu Xiong) *

X

Xiaoqiang Lu

DOI：10.1109/TGRS.2025.3556480

Original

Original request for help

Save

Abstract

En 中文

Accurate bow direction detection is essential for ship trajectory prediction and port monitoring. Existing ship detection networks typically output angles within 180 degrees, while extending to 360 degrees introduces cyclic issues affecting rotation intersection over union (RIoU) accuracy. This study proposes a novel bow direction detection algorithm that extends network output to 360 degrees and integrates a heading intersection over union (HIoU) loss to enhance detection accuracy and robustness. Additionally, an HIoU loss function is designed to improve bow direction identification and reduce quantization errors in hash codes. The algorithm is evaluated on three datasets: FGSD, OHD-SJTU-S, and OHD-SJTU-L. On FGSD, it achieves mean average precision (mAP) of 91.14%. On OHD-SJTU-S, it attains an mAP50:95 of 63.3% and a bow direction prediction accuracy of 90.7%. On OHD-SJTU-L, the mAP50:95 is 29.2%, with an accuracy of 80.2%.

Keywords:

Accuracy

Object detection

Marine vehicles

Prediction algorithms

Encoding

Technological innovation

Optimization

Training

Artificial intelligence

Shape

360 degrees angle processing

angle encoding

bow direction detection

computer vision

Bow Direction Detection Based on Angular Coding With Heading Intersection Over Union Loss

Abstract

Journal

Organization