基于改進(jìn)YOLOv3目標(biāo)檢測算法的船舶運(yùn)載貨物自動(dòng)識(shí)別研究

打開文本圖片集

摘要：船舶貨物自動(dòng)識(shí)別高精度數(shù)據(jù)獲取難，影響檢測性能。該文利用弱監(jiān)督至全監(jiān)督框架，結(jié)合改進(jìn)算法構(gòu)建組合框架，平均識(shí)別精度達(dá)32.0%，定位精度達(dá)73.8%，高于對比方法。該框架在弱監(jiān)督環(huán)境下表現(xiàn)優(yōu)異，適用于船舶貨物自動(dòng)識(shí)別。

關(guān)鍵詞：YOLOv3；弱監(jiān)督；船舶運(yùn)載；候選區(qū)域

doi：10.3969/J.ISSN.1672-7274.2024.09.001

中圖分類號(hào)：TP 391.41                 文獻(xiàn)標(biāo)志碼：A            文章編碼：1672-7274（2024）09-000-03

Research on Automatic Identification of Ship Cargo Based on Improved YOLOv3 Object Detection Algorithm

HOU Guojiao1， SUN Rong1， XIAO Shengkui1， LI Wen1， ZHANG Dong2

（1. The Navigation Authority of Yangtze Gorges， Yichang 443002， China;

2. Hunan Tianxiakuan Information Technology Co.， Ltd.， Changsha 410000， China）

Abstract： The difficulty in obtaining high-precision data for automatic identification of ship cargo affects the detection performance. This study utilizes a weak supervision to full supervision framework combined with improved algorithms to construct a combined framework. The average recognition accuracy reaches 32.0%， and the positioning accuracy reaches 73.8%， which is higher than the comparison methods. This framework performs excellently in a weak supervision environment and is suitable for automatic identification of ship cargo.

Keywords： YOLOv3; weak supervision; ship transportation; candidate region

0   引言

在船舶貨物自動(dòng)識(shí)別領(lǐng)域，視覺圖像的檢測識(shí)別扮演著核心角色，而人工智能算法的興起為此提供了新的思路[1]。（剩余3662字）