1.平高集团智慧能源技术研究院,河南 郑州 450000
2.北京航天无人机系统工程研究所,北京 100094
刘彤(1997-),女,硕士,助理工程师,主要研究方向:图像处理、计算机视觉。
宋嘉乐(1997-),男,硕士,工程师,主要研究方向:人工智能、飞行控制。
李志和(1997-),男,本科,工程师,主要研究方向:图像处理、计算机视觉。
收稿:2026-01-04,
纸质出版:2026-04-06
移动端阅览
刘彤,宋嘉乐,李志和,等. 基于实例迁移的机载红外小目标检测算法[J]. 电子技术应用,2026,52(4):42-48.
Liu Tong,Song Jiale,Li Zhihe,et al. Airborne infrared small target detection algorithm based on instance migration[J]. Application of Electronic Technique,2026,52(4):42-48.
刘彤,宋嘉乐,李志和,等. 基于实例迁移的机载红外小目标检测算法[J]. 电子技术应用,2026,52(4):42-48. DOI: 10.16157/j.issn.0258-7998.267733.
Liu Tong,Song Jiale,Li Zhihe,et al. Airborne infrared small target detection algorithm based on instance migration[J]. Application of Electronic Technique,2026,52(4):42-48. DOI: 10.16157/j.issn.0258-7998.267733.
近年来,机载红外小目标检测技术已经成为军事和民用领域的研究热点。但在实际应用中,复杂背景和低信噪比等因素的影响仍然使红外小目标检测面临挑战。因此,针对小目标检测,选取更适合红外小目标及复杂背景的YOLOv7模型,在此基础上提出了一种改进的机载红外小目标检测算法AIR-YOLOv7,并利用实例迁移学习的方法分析红外小目标的特点,对数据集进行扩充,进一步提高算法的性能。实验结果表明,AIR-YOLOv7算法在机载复杂场景下的红外小目标检测方面具有更好的表现,mAP值达到97.09%,同时FPS为102.09帧/s。仅通过少量扩充本文数据集,实例迁移方法就使算法的mAP值提高了0.96个百分点,为后续硬件平台边缘计算移植提供了理论基础。
In recent years
airborne infrared small target detection technology has become a research hotspot in the military and civilian fields. However
in practical applications
the influence of factors such as complex background and low signal-to-noise ratio still make infrared small target detection a challenge. Therefore
this paper proposes an improved airborne infrared small target detection algorithm AIR-YOLOv7
and uses the example transfer learning method to analyze the characteristics of small infrared targets
expand the data set
and further improve the performance of the algorithm. The experimental results show that the AIR-YOLOv7 algorithm has a better performance in infrared small target detection in airborne complex scenes
with a mAP value of 97.09% and an FPS of 102.09. With only a small amount of expansion of the data set in this paper
the instance migration method increases the mAP value of the algorithm by 0.96 percentage points
which provides a theoretical basis for the subsequent hardware platform edge computing transplantation.
XIN J , CAO X , XIAO H , et al . Infrared small target detection based on multiscale kurtosis map fusion and optical flow method [J ] . Sensors , 2023 , 23 ( 3 ): 1660 .
MAN Y , YANG Q , CHEN T . Infrared single-frame small target detection based on block-matching [J ] . Sensors , 2022 , 22 ( 21 ): 8300 .
ZHANG G , MA H , HAMDULLA A . Infrared small target detection using regional feature difference of patch image [J ] . Sensors , 2022 , 22 ( 9 ): 3277 .
FAN M , TIAN S , LIU K , et al . Infrared small target detection based on region proposal and CNN classifier [J ] . Signal, Image and Video Processing , 2021 , 15 ( 8 ): 1927 - 1936 .
ZHANG W , FENG W , LI M , et al . A saliency-transformer combined knowledge distillation guided network for infrared small target detection [C ] // Signal and Information Processing, Networking and Computers: Proceedings of the 10th International Conference on Signal and Information Processing, Networking and Computers (ICSINC) . Singapore : Springer Nature Singapore , 2023 : 88 - 95 .
WANG C Y , BOCHKOVSKIY A , LIAO H Y M . YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2023 : 7464 - 7475 .
HOU Q , ZHOU D , FENG J . Coordinate attention for efficient mobile network design [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2021 : 13708 - 13717 .
LIU S , HUANG D , WANG Y . Receptive field block net for accurate and fast object detection [C ] // Proceedings of the European Conference on Computer Vision , 2018 : 385 - 400 .
LIN T Y , DOLLÁR P , GIRSHICK R , et al . Feature pyramid networks for object detection [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2017 : 2117 - 2125 .
汪兴 , 韩志科 , 黄晓辉 , 等 . RGE-YOLO:下采样与注意力机制融合的缺陷检测方法 [J/OL ] . 计算机工程与应用 , 1 - 15 [ 2025-11-06 ] . https://link.cnki.net/urlid/11.2127.TP.2025 1020.1644.004 https://link.cnki.net/urlid/11.2127.TP.20251020.1644.004 .
王康云 , 王成彪 , 陈兴通 . 基于YOLOv5的交通场景目标检测方法改进与实现 [J/OL ] . 汽车实用技术 , 1 - 5 [ 2025-11-06 ] . https://link.cnki.net/urlid/61.1394.th.20250613.1001.002 https://link.cnki.net/urlid/61.1394.th.20250613.1001.002 .
虎风林 . 基于深度学习的遥感图像舰船检测与分类识别研究 [D ] . 银川 : 宁夏大学 , 2022 .
张海超 . 基于梯度与进化的神经网络训练与架构优化研究 [D ] . 上海 : 东华大学 , 2023 .
吴慰 . 深度学习模型中梯度下降优化器的动态学习过程研究 [D ] . 武汉 : 武汉大学 , 2022 .
唐振超 , 韦蔚 , 罗蔚然 , 等 . 融合余弦退火与空洞卷积的遥感影像语义分割 [J ] . 遥感学报 , 2023 , 27 ( 11 ): 2579 - 2592 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010602201714号