浏览全部资源
扫码关注微信
Published： 16 December 2024 ，
移动端阅览
柏栋， 于英， 宋亮， 程彬彬， 高寒. 2024. 面向军用车辆细粒度检测的遥感图像数据集构建与验证. 中国图象图形学报， 29(12):3564-3577
Bai Dong， Yu Ying， Song Liang， Cheng Binbin， Gao Han. 2024. Construction and validation of remote sensing image dataset for fine-grained detection of military vehicles. Journal of Image and Graphics， 29(12):3564-3577
目的
2
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
2
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
2
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
2
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
https://github.com/baidongls/MVRSD
。
Objective
2
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
2
We construct our dataset using Google Earth data， collected 3 000 remotely sensed images from more than 40 military scenarios within Asia， North America， and Europe， and acquired 32 626 military vehicle targets from these images. These images have a spatial resolution of 0.3 m and size of 640 × 640 pixels. Our dataset consists of remotely sensed images and the corresponding labeled files， and the targets were manually selected and classified by experts through the interpretation of high-resolution optical images. We divide the granular categories in the dataset into the following categories based on vehicle size and military function： small military vehicles （SMV）， large military vehicles （LMV）， armored fighting vehicles （AFV）， military construction vehicles （MCV）， and civilian vehicles （CV）. The geographic environments of the samples include cities， plains， mountains， and deserts. To solve the difficulty of recognizing military vehicles in remote sensing images， the proposed benchmark model takes into account the characteristics of those military vehicles with small targets and fuzzy shapes and appearances along with interclass similarity and intraclass variability. The number of instances of each category in the dataset and the number of instances of each image depend on their actual distribution in the remote sensing scene， which can reflect the realism and challenges of the dataset. We then design a cross-scale target-size-based detection head and context aggregation module based on YOLOv5s to improve the detection performance for fine-grained military vehicle targets.
Result
2
We analyze the characteristics of military vehicle targets in remote sensing images and the challenges being faced in the fine-grained detection of these vehicles. To address the poor detection accuracy of the YOLOv5 algorithm for small targets and reduce its risks of omission and misdetection， we design an improved model based on YOLOv5s as our baseline model and select a cross-scale detector head based on the dimensions of the targets in the dataset to efficiently detect the targets at different scales. We insert the attention mechanism module in front of this detector head to inhibit the interference of complex backgrounds on the target. Based on this dataset， we applied five target detection models for our experiments. Results of our experiments show that our proposed benchmark model improves its mean average precision by 1.1% compared with the classical target detection model. Moreover， the deep learning model achieves good performance in the fine-grained accurate detection of military vehicles.
Conclusion
2
The MVRSD dataset can support researchers in analyzing the features of remote sensing images of military vehicles from different countries and provide training and test data for deep learning methods. The proposed benchmark model can also effectively improve the detection accuracy for remotely sensed military vehicles. The MVRSD dataset is available at
https://github.com/baidongls/MVRSD
https://github.com/baidongls/MVRSD
.
目标检测军用车辆数据集高分辨率遥感细粒度深度学习
target detectionmilitary vehicle datasethigh-resolution remote sensingfine-graineddeep learning
Fan D P， Ji G P， Sun G L， Cheng M M， Shen J B and Shao L. 2020. Camouflaged object detection//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， USA： IEEE： 2774-2784 ［DOI： 10.1109/CVPR42600.2020.00285http://dx.doi.org/10.1109/CVPR42600.2020.00285］
Fan D P， Ji G P， Cheng M M and Shao L. 2022. Concealed object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence， 44（10）： 6024-6042 ［DOI： 10.1109/TPAMI.2021.3085766http://dx.doi.org/10.1109/TPAMI.2021.3085766］
Li A， Wang S Q， Zheng B Y， Chen J Y and Ji J X. 2020. Improvement of RetinaNet and its application in military vehicle detection. Electronics Optics and Control， 27（10）： 78-82， 98
李昂， 王晟全， 郑宝玉， 陈济颖， 纪佳馨. 2020. 改进的用于军用车辆目标检测的RetinaNet. 电光与控制， 27（10）： 78-82， 98 ［DOI： 10.3969/j.issn.1671-637X.2020.10.016http://dx.doi.org/10.3969/j.issn.1671-637X.2020.10.016］
Liao Y R， Wang H N， Li C B， Li Y， Fang Y Q and Yan S Y. 2022. Research progress of deep learning-based object detection of optical remote sensing image. Journal on Communications， 43（5）： 190-203
廖育荣， 王海宁， 林存宝， 李阳， 方宇强， 倪淑燕. 2022. 基于深度学习的光学遥感图像目标检测研究进展. 通信学报， 43（5）： 190-203 ［DOI： 10.11959/j.issn.1000-436x.2022071http://dx.doi.org/10.11959/j.issn.1000-436x.2022071］
Lin T Y， Maire M， Belongie S， Hays J， Perona P， Ramanan D， Dollr P and Zitnick C L. 2014. Microsoft COCO： common objects in context//Proceedings of the 13th European Conference on Computer Vision. Zurich， Switzerland： Springer： 740-755 ［DOI： 10.1007/978-3-319-10602-1_48http://dx.doi.org/10.1007/978-3-319-10602-1_48］
Lin Z P， Li Z H， Liu Z and Shen W M. 2021. Bilateral-branch multi-label classification method with rebalanced weights for remote sensing images. Journal of Computer Applications， 41（S2）： 86-92
蔺智鹏， 李铸洪， 刘舟， 沈未名. 2021. 双分支遥感影像多标签重平衡权重分类方法. 计算机应用， 41（S2）： 86-92 ［DOI： 10.11772/j.issn.1001-9081.2020121944http://dx.doi.org/10.11772/j.issn.1001-9081.2020121944］
Liu C C. 2015. Research on Vehicle Identification and Velocity Estimation Based on Optical Satellite Imagery. Beijing： Beijing Jiaotong University
刘超超. 2015. 基于光学卫星影像的车辆识别和速度估算研究. 北京： 北京交通大学
Liu J W， Liu J W and Luo X L. 2021. Research progress in attention mechanism in deep learning. Chinese Journal of Engineering， 43（11）： 1499-1511
刘建伟， 刘俊文， 罗雄麟. 2021. 深度学习中注意力机制研究进展. 工程科学学报， 43（11）： 1499-1511 ［DOI： 10.13374/j.issn2095-9389.2021.01.30.005http://dx.doi.org/10.13374/j.issn2095-9389.2021.01.30.005］
Liu T， Ding X Y， Zhang B B and Zhang J X. 2023. Improved YOLOv5 for remote sensing image detection. Computer Engineering and Applications， 59（10）： 253-261
刘涛， 丁雪妍， 张冰冰， 张建新. 2023. 改进YOLOv5的遥感图像检测方法. 计算机工程与应用， 59（10）： 253-261 ［DOI： 10.3778/j.issn.1002-8331.2212-0045http://dx.doi.org/10.3778/j.issn.1002-8331.2212-0045］
Liu W， Anguelov D， Erhan D， Szegedy C， Reed S， Fu C Y and Berg A C. 2016. SSD： single shot MultiBox detector//Proceedings of the 14th European Conference on Computer Vision. Amsterdam， the Netherland： Springer： 21-37 ［DOI： 10.1007/978-3-319-46448-0_2http://dx.doi.org/10.1007/978-3-319-46448-0_2］
Liu Y， Li H， Hu C， Luo S， Luo Y and Chen C W. 2024. Learning to aggregate multi-scale context for instance segmentation in remote sensing images ［EB/OL］. ［2023-12-21］. https://arxiv.org/pdf/2111.11057.pdfhttps://arxiv.org/pdf/2111.11057.pdf
Luo J H and Wu J X. 2017. A survey on fine-grained image categorization using deep convolutional features. Acta Automatica Sinica， 43（8）： 1306-1318
罗建豪， 吴建鑫. 2017. 基于深度卷积特征的细粒度图像分类研究综述. 自动化学报， 43（8）： 1306-1318 ［DOI： 10.16383/j.aas.2017.c160425http://dx.doi.org/10.16383/j.aas.2017.c160425］
Lyu Y N， Zhu H， Meng J， Cui C L and Song Q Q. 2022. A review and adaptability study of deep learning models for vehicle detection based on high-resolution remote sensing images. Remote Sensing for Natural Resources， 34（4）： 22-32
吕雅楠， 朱红， 孟健， 崔成玲， 宋其淇. 2022. 面向高分辨率遥感影像车辆检测的深度学习模型综述及适应性研究. 自然资源遥感， 34（4）： 22-32 ［DOI： 10.6046/zrzyyg.2022010http://dx.doi.org/10.6046/zrzyyg.2022010］
Miao Z， Zhao X， Wang J B， Li Y， Li H and Zhang R. 2021. Using fine-grained recognition technology in the military domain. National Defense Technology， 42（4）： 57-63
苗壮， 赵勋， 王家宝， 李阳， 李航， 张睿. 2021. 军事领域细粒度识别技术与应用. 国防科技， 42（4）： 57-63 ［DOI： 10.13943/j.issn1671-4547.2021.04.10http://dx.doi.org/10.13943/j.issn1671-4547.2021.04.10］
Redmon J， Divvala S， Girshick R and Farhadi A. 2016. You only look once： unified， real-time object detection//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Las Vegas， USA： IEEE： 779-788 ［DOI： 10.1109/CVPR.2016.91http://dx.doi.org/10.1109/CVPR.2016.91］
Ren S Q， He K M， Girshick R and Sun J. 2017. Faster R-CNN： towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence， 39（6）： 1137-1149 ［DOI： 10.1109/TPAMI.2016.2577031http://dx.doi.org/10.1109/TPAMI.2016.2577031］
Shi Y， Wu J， Zhao S X， Gao G Y， Deng T and Yan H M. 2022. Rethinking the detection head configuration for traffic object detection ［EB/OL］. ［2023-12-21］. https://arxiv.org/pdf/2210.03883.pdfhttps://arxiv.org/pdf/2210.03883.pdf
State Administration for Market Regulation and National Standardization Administration. 2022. GB/T 2659.1-2022 Codes for the representation of names of countries and their subdivisions—Part 1： country code. Beijing： Standards Press of China： 42-48
国家市场监督管理总局， 国家标准化管理委员会. 2022. GB/T 2659.1-2022世界各国和地区及其行政区划名称代码 第1部分： 国家和地区代码. 北京： 中国标准出版社： 42-48
Sun X， Wang P J， Yan Z Y， Xu F， Wang R P， Diao W H， Chen J， Li J H， Feng Y C， Xu T， Weinmann M， Hinz S， Wang C and Fu K. 2022. FAIR1M： a benchmark dataset for fine-grained object recognition in high-resolution remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing， 184： 116-130 ［DOI： 10.48550/arxiv.2103.05569http://dx.doi.org/10.48550/arxiv.2103.05569］
Wang J B， Li Y and Wang B. 2019. Research on fine-grained recognition of armored targets in land battlefield. National Defense Technology， 40（5）： 6-11
王家宝， 李阳， 王彬. 2019. 陆战场装甲目标细粒度识别技术. 国防科技， 40（5）： 6-11 ［DOI： 10.13943/j.issn1671-4547.2019.05.02http://dx.doi.org/10.13943/j.issn1671-4547.2019.05.02］
Wu F， Zhang H， Wang C， Li L， Li J J， Chen W R and Zhang B. 2022. SARBuD1.0： a SAR building dataset based on GF-3 FSII imageries for built-up area extraction with deep learning method. National Remote Sensing Bulletin， 26（4）： 620-631
吴樊， 张红， 王超， 李璐， 李娟娟， 陈卫荣， 张波. 2022. SARBuD 1.0： 面向深度学习的GF-3精细模式SAR建筑数据集. 遥感学报， 26（4）： 620-631 ［DOI： 10.11834/jrs.20220296http://dx.doi.org/10.11834/jrs.20220296］
Yamazaki F， Liu W and Vu T T. 2007. Speed detection for moving objects from digital aerial camera and QuickBird sensors//Proceedings of the 5th International Workshop on Remote Sensing Applications to Natural Hazards. Washington， USA： ［s.n.］： 1-6
Zhang L， Zhang Y S， Yu Y， Ma Y Z and Jiang H G. 2022. Survey on object detection in tilting box for remote sensing images. National Remote Sensing Bulletin， 26（9）： 1723-1743
张磊， 张永生， 于英， 马永政， 姜怀刚. 2022. 遥感图像倾斜边界框目标检测研究进展与展望. 遥感学报， 26（9）： 1723-1743 ［DOI： 10.11834/jrs.20210247http://dx.doi.org/10.11834/jrs.20210247］
Zhang Y F， Kang B Y， Hooi B， Yan S C and Feng J S. 2023. Deep long-tailed learning： a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence， 45（9）： 10795-10816 ［DOI： 10.1109/TPAMI.2023.3268118http://dx.doi.org/10.1109/TPAMI.2023.3268118］
Zhao G L and Song J P. 2022. SAR target recognition of MSTAR dataset based on joint use of multiple features. Engineering Journal of Wuhan University， 55（7）： 732-739
赵高丽， 宋军平. 2022. 联合多特征的MSTAR数据集SAR目标识别方法. 武汉大学学报（工学版）， 55（7）： 732-739 ［DOI： 10.14188/j.1671-8844.2022-07-012http://dx.doi.org/10.14188/j.1671-8844.2022-07-012］
Zheng W L， Yang P， Yan S Q， Wu F X and Yan S. 2022. Analysis on the research status and development trend of military camouflage technology. Modern Defense Technology， 50（1）： 81-86
郑万里， 杨萍， 闫少强， 吴丰轩， 燕松. 2022. 军事伪装技术研究现状及发展趋势分析. 现代防御技术， 50（1）： 81-86 ［DOI： 10.3969/j.issn.1009-086x.2022.01.012http://dx.doi.org/10.3969/j.issn.1009-086x.2022.01.012］
Zhou L J and Mao J N. 2023. Vision Transformer-based recognition tasks： a critical review. Journal of Image and Graphics， 28（10）： 2969-3003
周丽娟， 毛嘉宁. 2023. 视觉Transformer识别任务研究综述. 中国图象图形学报， 28（10）： 2969-3003 ［DOI： 10.11834/jig.220895http://dx.doi.org/10.11834/jig.220895］
相关文章
相关作者
相关机构
京公网安备11010802024621