西安交通大学 自动化学院, 西安 710049
韩德强(1980-), 男, 博士, 教授。 Email: deqhan@mail.xjtu.edu.cn
收稿:2026-06-04,
修回:2026-07-30,
网络首发:2026-08-17,
移动端阅览
杨卓,任予同,寇力天,等. 面向低空无人机探测的图像预处理增强框架[J]. 航空工程进展.
YANG Zhuo,REN Yutong,KOU Litian, et al. Research on image preprocessing and enhancement framework for low-altitude UAV detection[J]. Advances in Aeronautical Science and Engineering.(in Chinese)
低空无人机探测是安防、空域管控领域的重要研究方向。无人机具有目标小、运动快、特征弱的探测难点,现有研究多聚焦检测算法优化,普遍忽视噪声、雾霾、雨线导致的图像边缘模糊、对比度下降等退化问题,影响检测性能。构建多模块组合的预处理增强框架,分别通过平滑滤波结合证据理论去噪、改进特征融合注意力网络去雾、山形单阶段恢复网络去雨三类策略缓解图像退化,选取传统图像处理算法以及主流深度学习图像复原模型开展对比实验,从图像质量、目标检测精度与单帧运算耗时三个维度实施定量评测。在实拍数据集上的实验表明,该框架可有效提升图像质量,增强目标显著性,改善无人机检测性能。
Low-altitude unmanned aerial vehicle (UAV) detection is a critical research direction in the fields of public security and low-altitude airspace management. To address the inherent detection challenges of UAV targets, including small size, high mobility, and weak imaging features, most existing studies focus on the optimization of detection algorithms, while generally ignoring the negative impact of image degradation issues (including edge blurring and contrast reduction caused by noise, haze, and rain streaks) on detection performance. To fill this research gap, this paper constructs a multi-module integrated preprocessing enhancement framework, which mitigates image degradation through three targeted strategies: a denoising module combining smoothing filtering and evidence theory, a dehazing module based on an improved feature fusion attention network, and a deraining module using a hill-shaped single-stage restoration network. Comparative experiments are conducted using traditional image processing algorithms and mainstream deep learning image restoration models, with quantitative evaluations performed across three dimensions: image quality, object detection accuracy, and single-frame processing time. Ablation and comparative experiments verify that the proposed framework can effectively improve image quality, enhance target saliency, and boost the performance of UAV detection tasks.
罗俊海 , 王芝燕 . 无人机探测与对抗技术发展及应用综述 [J]. 控制与决策 , 2022 , 37 ( 3 ): 530 - 544 .
Luo Junhai , Wang Zhiyan . Review on the development and application of UAV detection and countermeasure technologies [J]. Control and Decision , 2022 , 37 ( 3 ): 530 - 544 . (in Chinese)
那振宇 , 程留洋 , 孙鸿晨 , 等 . 基于深度学习的无人机检测和识别研究综述 [J]. 信号处理 , 2024 , 40 ( 4 ): 609 - 624 .
Na Zhenyu , Cheng Liuyang , Sun Hongchen , et al . A review of UAV detection and recognition based on deep lear-ning [J]. Journal of Signal Processing , 2024 , 40 ( 4 ): 609 - 624 . (in Chinese)
张静 , 张科 , 王靖宇 , 等 . 低空反无人机技术现状与发展趋势 [J]. 航空工程进展 , 2018 , 9 ( 1 ): 1 - 8 .
Zhang Jing , Zhang Ke , Zhang Jingyu , et al . A survey on anti-UAV technology and its future trend [J]. Advances in Aeronautical Science and Engineering , 2018 , 9 ( 1 ): 1 - 8 . (in Chinese)
Wei W , Cheng Y , He J , et al . A review of small object detection based on deep learning [J]. Neural Computing and Applications , 2024 , 36 ( 12 ): 6283 - 6303 .
Hua W , Chen Q . A survey of small object detection based on deep learning in aerial images [J]. Artificial Intelligence Review , 2025 , 58 : 162 .
Zhu X , Lyu S , Wang X , et al . TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios [C]∥ Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops . Montreal : IEEE , 2021 : 2778 - 2788 .
Zhang Z . Drone-YOLO: An efficient neural network method for target detection in drone images [J]. Drones , 2023 , 7 ( 8 ): 526 .
Li Y , Li Q , Pan J , et al . SOD-YOLO: Small-object-detection algorithm based on improved YOLOv8 for UAV images [J]. Remote Sensing , 2024 , 16 ( 16 ): 3057 .
钱基德 , 严浩 , 梁琰 , 等 . 基于ECIOU结构嵌入YOLO的塔台视角目标检测 [J]. 航空工程进展 , 2025 , 16 ( 2 ): 70 - 78 .
Qian Jide , Yan Hao , Liang Yan , et al . Tower view object detection based on ECIOU structure embedded in YOLO [J]. Advances in Aeronautical Science and Engineering , 2025 , 16 ( 2 ): 70 - 78 . (in Chinese)
李永福 , 崔恒奇 , 朱浩 , 等 . 一种基于改进AOD-Net的航拍图像去雾算法 [J]. 自动化学报 , 2022 , 48 ( 6 ): 1543 - 1559 .
Li Yongfu , Cui Hengqi , Zhu Hao , et al . An aerial image dehazing algorithm based on improved AOD-Net [J]. Acta Automatica Sinica , 2022 , 48 ( 6 ): 1543 - 1559 . (in Chinese)
申艳 , 张志凡 , 陈政杭 , 等 . 基于跳跃融合连接模块的单幅图像去雨算法 [J]. 北京交通大学学报 , 2025 , 49 ( 6 ): 165 - 173 .
Shen Yan , Zhang Zhifan , Chen Zhenghang , et al . Single image rain removal algorithm based on skip-fusion connection module [J]. Journal of Beijing Jiaotong University , 2025 , 49 ( 6 ): 165 - 173 . (in Chinese)
Valanarasu J M J , Yasarla R , Patel V M . TransWeather: Transformer-based restoration of images degraded by adverse weather conditions [C]∥ Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans : IEEE , 2022 : 2353 - 2363 .
Potlapalli V , Zamir S W , Khan S , et al . PromptIR: Prompting for all-in-one blind image restoration [J]. Advances in Neural Information Processing Systems , 2023 ( 3 ): 215 - 223 .
Xu J , Wu M , Hu X , et al . Towards real-world adverse weather image restoration: Enhancing clearness and semantics with vision-language models [C]∥ 2024 Computer Vision Conference . Cham : Springer , 2025 : 147 - 164 .
Dempster A P . Upper and lower probabilities induced by a multivalued mapping [J]. Annals of Mathematical Statistics , 1967 , 38 ( 2 ): 325 - 339 .
韩德强 , 杨艺 , 韩崇昭 . DS证据理论研究进展及相关问题探讨 [J]. 控制与决策 , 2014 , 29 ( 1 ): 1 - 11 .
Han Deqiang , Yang Yi , Han Chongzhao . Research progress and related issues of DS evidence theory [J]. Control and Decision , 2014 , 29 ( 1 ): 1 - 11 . (in Chinese)
Zhang Z , Han D , Dezert J , et al . A new adaptive switching median filter for impulse noise reduction with pre-detection based on evidential reasoning [J]. Signal Processing , 2018 , 147 : 173 - 189 .
He K , Sun J , Tang X . Single image haze removal using dark channel prior [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2011 , 33 ( 12 ): 2341 - 2353 .
Qin X , Wang Z , Bai Y , et al . FFA-Net: Feature fusion attention network for single image dehazing [C]∥ Proceedings of the AIAA Conference on Artificial Intelligence . Reston : AIAA , 2020 : 11908 - 11915 .
Chen L , Chu X , Zhang X , et al . Simple baselines for image restoration [C]∥ 2022 Computer Vision Conference . Cham : Springer , 2022 : 17 - 33 .
李凯璇 , 刘晓锋 , 陈强 , 等 . YOLOv8-GAIS:一种改进的无人机航拍目标检测算法 [J]. 激光与光电子学进展 , 2025 , 62 ( 12 ): 240295 .
Li Kaixuan , Liu Xiaofeng , Chen Qiang , et al . YOLOv8-GAIS: An improved object detection algorithm for UAV aerial photography [J]. Laser & Optoelectronics Progress , 2025 , 62 ( 12 ): 240295 . (in Chinese)
Zhang K , Zuo W , Zhang L . FFDNet: Toward a fast and flexible solution for CNN-based image denoising [J]. IEEE Transactions on Image Processing , 2018 , 27 ( 9 ): 4608 - 4622.44 .
Song Y , He Z , Qian H , et al . Vision transformers for single image dehazing [J]. IEEE Transactions on Image Processing , 2023 , 32 : 1927 - 1941 .
Zamir S W , Arora A , Khan S , et al . Multi-Stage Progressive Image Restoration [C]∥ Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Reston : IEEE , 2021 : 14821 - 14831 .
吕丹 , 毕笃彦 . 基于结构相似的DCT域图像质量评价 [J]. 吉林大学学报(工学版) , 2011 , 41 ( 6 ): 1771 - 1775 .
Lyu Dan , Bi Duyan . Image quality assessment in DCT domain based on structural similarity [J]. Journal of Jilin University (Engineering and Technology Edition) , 2011 , 41 ( 6 ): 1771 - 1775 . (in Chinese)
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