面向军用车辆细粒度检测的遥感图像数据集构建与验证  

Construction and validation of remote sensing image dataset for fine-grained detection of military vehicles

作　　者：柏栋 于英[1] 宋亮 程彬彬 高寒 Bai Dong;Yu Ying;Song Liang;Cheng Binbin;Gao Han(Institute of Geospatial Information,Information Engineering University,Zhengzhou 450001,China;Unit 96833,Huaihua 418000,China;Unit 31016,Beijing 100000,China)

机构地区：[1]信息工程大学地理空间信息学院,郑州450001 [2]96833部队,怀化418000 [3]31016部队,北京100000

出　　处：《中国图象图形学报》2024年第12期3564-3577,共14页Journal of Image and Graphics

基　　金：国家自然科学基金项目(42071340);嵩山实验室项目(纳入河南省重大科技专项管理体系)(221100211000-01)。

摘　　要：目的 细粒度军事目标数据集是实现现代战争目标自动分类的重要支撑数据之一。当前缺乏高质量的细粒度军事目标遥感图像数据集,制约了军事目标自动精准检测的研究。为此,本文收集并标注了一个新的军用车辆细粒度检测遥感图像数据集MVRSD(military vehicle remote sensing dataset),并基于此设计了一种基于YOLOv5s(you only look once)的改进模型来提高军用车辆目标检测性能。方法 该数据集来源于谷歌地球数据,收集了亚洲、北美洲和欧洲范围内40多个军事场景下的3 000幅遥感图像,包含多个国家和地区的军用车辆目标。经高质量人工水平边界框标注,最终形成包含5个类别共计32 626个实例的军用车辆细粒度检测遥感图像数据集。针对遥感图像中军用车辆识别难题,本文提出的基准模型考虑了遥感军用车辆目标较小、形状和外观较为模糊以及类间相似性、类内差异性大的特点,设计了基于目标尺寸的跨尺度检测头和上下文聚合模块,提升细粒度军用车辆目标的检测性能。结果 提出的基准模型在军用车辆细粒度检测遥感图像数据集上的实验表明,对比经典的目标检测模型,新基准模型在平均精度均值(mean average precision,mAP)指标上提高了1.1%。结论 本文构建的军用车辆细粒度检测遥感图像数据集为军事目标自动分类算法的研究提供了参考与支持,有助于更为全面地研究遥感图像中军用车辆目标的特性。数据集及检测基准模型地址为:https://github.com/baidongls/MVRSD。Objective Informational warfare has put forward higher requirements for military reconnaissance,and military target identification,as one of the main tasks of military reconnaissance,needs to be able to deal with fine-grained military targets and provide personnel with more detailed target information.Optical remote sensing image datasets play a crucial role in remote sensing target detection tasks.These datasets provide valuable standard remote sensing data for model training and objective and uniform benchmarks for the comparison of different networks and algorithms.However,the current lack of high-quality fine-grained military target remote sensing image datasets constrains research on the automatic and accurate detection of military targets.As a special remote sensing target,military vehicles have certain characteristics,such as environmental camouflage,shape and structural changes,and movement “color shadows” that make their detection particularly challenging.Fig.1 shows the challenges posed by the fine-grained target characteristics of military vehicles in optical remote sensing images,which can be categorized into the following types according to the source of target characteristics:1) target characterization as affected by satellite remote sensing imaging systems;2) characterization of the vehicle target itself;3) military vehicle target characterization;4) characteristics affected by the combination;and 5) properties of fine-grained classification.To promote the development of deep-learning-based research on the fine-grained accurate detection of military vehicles in high-resolution remote sensing images,we construct a new high-resolution optical remote sensing image dataset called military vehicle remote sensing dataset(MVRSD).Using this model,we design an improved model based on YOLOv5s to improve the target detection performance for military vehicles.Method We construct our dataset using Google Earth data,collected 3 000 remotely sensed images from more than 40 military scenarios within Asia,North

关 键 词：目标检测 军用车辆数据集 高分辨率遥感 细粒度 深度学习 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]