收稿日期:2024-01-02
修回日期:2024-01-19
接受日期:2024-03-15
出版日期:2024-09-15
发布日期:2024-03-29
通讯作者:
刘贞报
E-mail:liuzhenbao@nwpu.edu.cn
基金资助:
Xiao WANG1, Zhenbao LIU1(
), Zhongke SHI2
Received:2024-01-02
Revised:2024-01-19
Accepted:2024-03-15
Online:2024-09-15
Published:2024-03-29
Contact:
Zhenbao LIU
E-mail:liuzhenbao@nwpu.edu.cn
Supported by:摘要:
无人机在检测和跟踪目标过程中受到目标伪装、目标遮挡、移动躲避以及假目标等因素的干扰,而无人机目标附近的阴影区域加剧了这些因素对目标检测和跟踪性能的影响,因此检测无人机目标阴影区域是无人机领域的重要研究任务之一。现有无人机目标阴影检测方法面临训练数据数量有限、数据收集标注困难以及无人机目标中存在大量尺寸较小的细碎阴影区域等问题,针对这些问题,提出一种基于残差混合监督网络的无人机目标阴影检测算法。首先针对无人机目标阴影检测任务的特点设计分辨率注意力网络,在结合底层纹理特征和高层语义特征的过程中,更准确地保留底层纹理特征。然后设计混合监督网络扩充训练数据集,结合普通阴影检测数据集和无人机目标阴影检测数据集训练教师网络,使用无人机阴影检测数据集和教师网络的参数训练学生网络。同时设计残差图像,利用教师网络检测结果和标准结果之间的残差图像扩充训练数据集,使阴影检测网络更加关注细碎阴影区域。最后,在2个公开实验数据集上和已有方法进行对比实验,在各个评价参数上取得了最多41.6%的提升效果,证明所提无人机目标阴影检测算法较好的解决了现有方法存在的问题,具有较高的准确性。
中图分类号:
王潇, 刘贞报, 史忠科. 基于残差混合监督网络的无人机目标阴影检测[J]. 航空学报, 2024, 45(17): 530062.
Xiao WANG, Zhenbao LIU, Zhongke SHI. Shadow detection of UAV target based on residual mixed supervision network[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(17): 530062.
表 1
本文方法和对比方法的评价参数
| 方法 | AISD数据集 | SSAD数据集 | |||||||
|---|---|---|---|---|---|---|---|---|---|
| F1 | OA | IoU | BER | F1 | OA | IoU | BER | ||
| DeepLabV3 | 91.15 | 95.46 | 83.74 | 5.66 | 81.31 | 92.13 | 70.96 | 16.70 | |
| MTMT | 90.68 | 94.46 | 78.26 | 8.48 | 79.02 | 88.47 | 60.71 | 18.96 | |
| DSSDNet | 91.79 | 95.57 | 6.24 | 79.31 | |||||
| GSCA-UNet | 91.69 | 96.29 | 84.88 | 5.51 | |||||
| CADNet | 91.21 | ||||||||
| ESPFNet | 92.04 | ||||||||
| FSDNet | 92.36 | 95.81 | 85.51 | 5.53 | 82.65 | 92.25 | 73.31 | 15.34 | |
| DLA-PSO | 82.70 | 85.26 | |||||||
| CDANet | 92.41 | 83.96 | |||||||
| MRPFANet | 92.61 | 96.11 | 86.24 | 5.42 | 85.21 | 93.38 | 75.84 | 14.99 | |
| 本文方法 | 93.28 | 96.13 | 85.61 | 3.88 | 86.55 | 93.89 | 74.29 | 8.75 | |
| 1 | 石争浩, 仵晨伟, 李成建, 等. 航空遥感图像深度学习目标检测技术研究进展[J]. 中国图象图形学报, 2023, 28(9): 2616-2643. |
| SHI Z H, WU C W, LI C J, et al. Object detection techniques based on deep learning for aerial remote sensing images: A survey[J]. Journal of Image and Graphics, 2023, 28(9): 2616-2643 (in Chinese). | |
| 2 | 刘贞报, 马博迪, 高红岗, 等. 基于形态自适应网络的无人机目标跟踪方法[J]. 航空学报, 2021, 42(4): 524904. |
| LIU Z B, MA B D, GAO H G, et al. Adaptive morphological network based UAV target tracking algorithm[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4): 524904 (in Chinese). | |
| 3 | 江波, 屈若锟, 李彦冬, 等. 基于深度学习的无人机航拍目标检测研究综述[J]. 航空学报, 2021, 42(4): 524519. |
| JIANG B, QU R K, LI Y D, et al. Object detection in UAV imagery based on deep learning: Review[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4): 524519 (in Chinese). | |
| 4 | 刘芳, 韩笑. 基于多尺度深度学习的自适应航拍目标检测[J]. 航空学报, 2022, 43(5): 325270. |
| LIU F, HAN X. Adaptive aerial object detection based on multi-scale deep learning[J]. Acta Aeronautica et Astronautica Sinica, 2022, 43(5): 325270 (in Chinese). | |
| 5 | 施文灶, 毛政元. 基于图割与阴影邻接关系的高分辨率遥感影像建筑物提取方法[J]. 电子学报, 2016, 44(12): 2849-2854. |
| SHI W Z, MAO Z Y. Building extraction from high resolution remotely sensed imagery based on shadows and graph-cut segmentation[J]. Acta Electronica Sinica, 2016, 44(12): 2849-2854 (in Chinese). | |
| 6 | LI Y, WANG H N, FANG Y Q, et al. Learning power Gaussian modeling loss for dense rotated object detection in remote sensing images[J]. Chinese Journal of Aeronautics, 2023, 36(10): 353-365. |
| 7 | GUO R Q, DAI Q Y, HOIEM D. Paired regions for shadow detection and removal[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(12): 2956-2967. |
| 8 | LUO S, LI H F, SHEN H F. Deeply supervised convolutional neural network for shadow detection based on a novel aerial shadow imagery dataset[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 167: 443-457. |
| 9 | LUO S, LI H F, ZHU R Z, et al. ESPFNet: An edge-aware spatial pyramid fusion network for salient shadow detection in aerial remote sensing images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 4633-4646. |
| 10 | LIU D Y, ZHANG J P, WU Y H, et al. A shadow detection algorithm based on multiscale spatial attention mechanism for aerial remote sensing images[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 6003905. |
| 11 | ZHU Q Q, YANG Y, SUN X L, et al. CDANet: contextual detail-aware network for high-spatial-resolution remote-sensing imagery shadow detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5617415. |
| 12 | ZHANG J, SHI X L, ZHENG C Y, et al. MRPFA-net for shadow detection in remote-sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5514011. |
| 13 | 林雨准, 张保明, 郭海涛, 等. 结合多尺度分割和形态学运算的高分辨率遥感影像阴影检测[J]. 中国图象图形学报, 2018, 23(8): 1263-1272. |
| LIN Y Z, ZHANG B M, GUO H T, et al. Shadow detection from high resolution remote sensing imagery based on multi-scale segmentation and morphology operation[J]. Journal of Image and Graphics, 2018, 23(8): 1263-1272 (in Chinese). | |
| 14 | VICENTE T F Y, HOAI M, SAMARAS D. Leave-one-out kernel optimization for shadow detection and removal[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(3): 682-695. |
| 15 | KHAN S H, BENNAMOUN M, SOHEL F, et al. Automatic shadow detection and removal from a single image[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(3): 431-446. |
| 16 | VICENTE T F Y, HOU L, YU C P, et al. Large-scale training of shadow detectors with noisily-annotated shadow examples[C]∥European Conference on Computer Vision. Cham: Springer, 2016: 816-832. |
| 17 | NGUYEN V, VICENTE T F Y, ZHAO M Z, et al. Shadow detection with conditional generative adversarial networks[C]∥ 2017 IEEE International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2017: 4520-4528. |
| 18 | LE H, VICENTE T F Y, NGUYEN V, et al. A+D net: Training a shadow detector with adversarial shadow attenuation[C]∥European Conference on Computer Vision. Cham: Springer, 2018: 680-696. |
| 19 | WANG J F, LI X, YANG J. Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal[C]∥ 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2018: 1788-1797. |
| 20 | HU X W, FU C W, ZHU L, et al. Direction-aware spatial context features for shadow detection and removal[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(11): 2795-2808. |
| 21 | ZHU L, DENG Z J, HU X W, et al. Bidirectional feature pyramid network with recurrent attention residual modules for shadow detection[C]∥European Conference on Computer Vision. Cham: Springer, 2018: 122-137. |
| 22 | ZHENG Q L, QIAO X T, CAO Y, et al. Distraction-aware shadow detection[C]∥ 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2019: 5162-5171. |
| 23 | CHEN Z H, ZHU L, WAN L, et al. A multi-task mean teacher for semi-supervised shadow detection[C]∥ 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2020: 5610-5619. |
| 24 | JIN Y W, XU W B, HU Z W, et al. GSCA-UNet: towards automatic shadow detection in urban aerial imagery with global-spatial-context attention module[J]. Remote Sensing, 2020, 12(17): 2864. |
| 25 | TARVAINEN A, VALPOLA H. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results[C]∥ Proceedings of the 31st International Conference on Neural Information Processing Systems. New York:ACM, 2017:1195–1204. |
| 26 | LIU Z, MAO H Z, WU C Y, et al. A ConvNet for the 2020s[C]∥ 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2022: 11966-11976. |
| 27 | LIU Z, LIN Y T, CAO Y, et al. Swin Transformer: Hierarchical vision transformer using shifted windows[C]∥ 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2021: 9992-10002. |
| 28 | DONG X Y, BAO J M, CHEN D D, et al. CSWin transformer: A general vision transformer backbone with cross-shaped windows[C]∥ 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2022: 12114-12124. |
| 29 | ZHANG Y D, CHEN G, VUKOMANOVIC J, et al. Recurrent Shadow Attention Model (RSAM) for shadow removal in high-resolution urban land-cover mapping[J]. Remote Sensing of Environment, 2020, 247: 111945. |
| 30 | HE Z J, ZHANG Z Z, GUO M Q, et al. Adaptive unsupervised-shadow-detection approach for remote-sensing image based on multichannel features[J]. Remote Sensing, 2022, 14(12): 2756. |
| 31 | YANG Y, GUO M Q, ZHU Q Q. CADNet: Top-down contextual saliency detection network for high spatial resolution remote sensing image shadow detection[C]∥ 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. Piscataway: IEEE Press, 2021: 4075-4078. |
| 32 | HU X W, WANG T Y, FU C W, et al. Revisiting shadow detection: A new benchmark dataset for complex world[J]. IEEE Transactions on Image Processing, 2021, 30: 1925-1934. |
| 33 | RONNEBERGER O, FISCHER P, BROX T. U-net: Convolutional networks for biomedical image segmentation[C]∥International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241. |
| 34 | ZHU J J, SAMUEL K G G, MASOOD S Z, et al. Learning to recognize shadows in monochromatic natural images[C]∥ 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2010: 223-230. |
| [1] | 徐昊 郎荣玲 仇雨薇 范亚. 基于紧耦合TDOA/AOA的鲁棒SOP定位算法[J]. 航空学报, 0, (): 1-0. |
| [2] | 廉云霄 李霓 谢锋 周攀 董长印. 基于时空信息融合的多机协同空战决策方法[J]. 航空学报, 0, (): 1-0. |
| [3] | 黄鑫 邹嘉赫 肖舒怡 李小杭. 防御一类网络隐蔽攻击的自适应控制策略[J]. 航空学报, 0, (): 1-0. |
| [4] | 敖颖 陈浩 李慧铭 肖昆 王祥科. 固定翼无人机集群仿射编队分层控制方法(飞行器安全控制专栏)[J]. 航空学报, 0, (): 1-0. |
| [5] | 李煜 徐新龙 李珂澄 温志涌 李霓 刘小雄. 基于安全约束强化学习的深失速改出控制研究[J]. 航空学报, 0, (): 1-0. |
| [6] | 李煜 陈家鑫 李珂澄 溫志湧 李霓 刘小雄. 不对称机翼损伤飞机特性分析与增量容错控制(先进飞行器安全控制专栏)[J]. 航空学报, 0, (): 1-0. |
| [7] | 崔玉伟 孟宪锋 张思程 李爱军. 基于新型网络分布式架构的飞控系统故障容错方法(飞行器安全控制专栏)[J]. 航空学报, 0, (): 1-0. |
| [8] | 郑锐平 史静平 李天宇 吕永玺. 基于预设时间的固定翼无人机紧密编队控制(先进飞行器安全控制专栏)[J]. 航空学报, 0, (): 1-0. |
| [9] | 赵江, 皮明豪, 田栢苓, 池沛, 王英勋. 面向多目标跟踪的集群无人机自组织共识决策方法[J]. 航空学报, 2025, 46(16): 331635-331635. |
| [10] | 樊薇, 陈赛赛, 熊玉勇, 鲁金忠, 彭志科. 基于RD-S校正的叶端整剖面间隙微波测量方法[J]. 航空学报, 2025, 46(16): 231607-231607. |
| [11] | 宋远, 李锐, 黄智刚. RTK完好性指标分配方法[J]. 航空学报, 2025, 46(16): 331655-331655. |
| [12] | 陈霖, 顾曦文, 陈知颖, 张倬, 孙晓亮. 适应着舰引导大距离跨度的高精度单目视觉位姿测量[J]. 航空学报, 2025, 46(15): 331568-331568. |
| [13] | 黄山, 史静平, 朱奇, 吕永玺, 屈晓波. 翼面损伤飞机预设时间增量反步容错控制[J]. 航空学报, 2025, 46(15): 331503-331503. |
| [14] | 严国乘 王宏伦 王延祥 伦岳斌 朱俊帆. 无人机拖曳式空中回收机翼折叠过程预设性能抗摆动控制[J]. 航空学报, 0, (): 1-0. |
| [15] | 荣尔超 张钰迎 吕熙敏 梁峻宁. 基于神经网络气动预测模型的NMPC的尾座式可垂直起降无人机轨迹跟踪控制器[J]. 航空学报, 0, (): 1-0. |
| 阅读次数 | ||||||
|
全文 |
|
|||||
|
摘要 |
|
|||||
版权所有 © 航空学报编辑部
版权所有 © 2011航空学报杂志社
主管单位:中国科学技术协会 主办单位:中国航空学会 北京航空航天大学

