Lightweight remote sensing image target detection algorithm without anchor frame
CSTR:
Affiliation:

1.Shijiazhuang Tiedao University;2.School of Management, Shijiazhuang Tiedao University

Fund Project:

the National Natural Science Foundation of China (No. 61702347, No. 62027801), the Natural Science Foundation of Hebei Province (No. F2022210007, No. F2017210161), the Science and Technology Project of Hebei Education Department (No. ZD2022100, No. QN2017132), the Central Guidance on Local Science and Technology Development Fund (No. 226Z0501G).

  • Article
  • | |
  • Metrics
  • |
  • Reference [32]
  • | |
  • Cited by
  • | |
  • Comments
    Abstract:

    The existing remote sensing image object detection algorithms have the problem of large parameter quantities and difficulty in deploying on mobile devices. Therefore, this paper proposes a lightweight remote sensing image object detection algorithm without anchor boxes. Firstly, the DWS-Sandglass lightweight module was designed to reduce the model volume, and then the activation function of the model was improved to ensure the detection accuracy. Then, a parameter free attention module SimAM is introduced to enable the network to focus on more important feature information. Finally, prune the redundant channels of the anchor free box algorithm to reduce the number of model parameters, and fine tune to improve accuracy. The experimental results on the HRSC2016 dataset show that compared with the current mainstream anchor free frame detection algorithms, this algorithm has faster detection speed and smaller model size, making it more suitable for deployment on mobile devices with comparable detection accuracy.

    Reference
    [1] 王李祺,张成,侯宇超,谭秀辉,程蓉,高翔,白艳萍.基于深度学习特征融合的遥感图像场景分类应用[J].南京信息工程大学学报(自然科学版),2023,15(3):346-356.
    [2] WANG Liqi, ZHANG Cheng, HOU Yuchao, TAN Xiuhui, CHENG Rong, GAO Xiang, BAI Yanping. Remote sensing image scene classification based on deep learning feature fusion[J]. Journal of Nanjing University of Information Science & Technology, 2023,15(3):346-356.
    [3] Dalal N, Triggs B. Histograms of oriented gradients for human detection[C].Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. IEEE, 2005, 1: 886-893.
    [4] LIENHART R,MAYDT J.An extended set of haar-like features for rapid object detection[C]. Proceedings of International Conference on Image Processing, 2002.
    [5] IOLA PJONES M.Rapid object detection using a boosted cascade of simple features[C].Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2001.
    [6] 林浩, 李雷孝, 王慧. 支持向量机在智能交通系统中的研究应用综述[J]. 计算机科学与探索, 2020, 14(6): 901-917.
    [7] LIN H, LI L X, WANG H. Survey on research and application of support vector machines in intelligent transportation system[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(6): 901-917.
    [8] [7]韩金辉, 魏艳涛, 彭真明, 等. 红外弱小目标检测方法综述[J]. 红外与激光工程, 2022, 51(04): 438-461.
    [9] Han Jin-hui, Wei Yan-tao, Peng Zhen-ming, et al. Infrared dim and small target detection: A review[J]. Infrared and Laser Engineering, 2022, 51(04): 438-461.
    [10] [8]Li K, Wan G, Cheng G. et al. Object detection in optical remote sensing images: A survey and a new benchmark[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 159:296-307.
    [11] [9]董超, 刘晶红, 徐芳, 等. 光学遥感图像舰船目标快速检测方法[J]. 吉林大学学报(工学版), 2019, 49(04): 1369-1376.
    [12] Dong Chao, Liu Jing-hong, Xu Fang, et al. Fast ship detection in optical remote sensing images[J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(04): 1369-1376.
    [13] [10]Wu C, Wen W, Afzal T, et al. A compact dnn: approaching googlenet-level accuracy of classification and domain adaptation[C]//IEEE Conference on Computer Vision and Pattern Recognition. 2017: 5668-5677.
    [14] [11]Iandola F N, Han S, Moskewicz M W, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and<0. MB model size [EB/OL]. arXiv preprint, (2016-11-04) [2023-03-16]. https://arxiv. org/abs/ 1602.07360.
    [15] [12]Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications [EB/OL]. arXiv preprint, (2017-04-17) [2023-03-16]. https://arxiv.org/abs/ 1704.04861.
    [16] [13]Sandler M, Howard A, Zhu M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]//IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2018: 4510-4520.
    [17] [14]Howard A, Sandler M, Chu G, et al. Searching for mobilenetv3[C]//IEEE/CVF International Conference on Computer Vision. IEEE, 2019: 1314-1324.
    [18] [15]Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 2018: 7132-7141.
    [19] [16]Han K, Wang Y, Tian Q, et al. Ghostnet: More features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 2020: 1580-1589.
    [20] [17]Li H, Kadav A, Durdanovic I, et al. Pruning filters for efficient convnets[J]. arXiv preprint arXiv: 1608.08710, 2016.
    [21] [18]Liu Z, Li J, Shen Z, et al. Learning efficient convolutional networks through network slimming[C]//Proceedings of the IEEE International Conference on Computer Vision. 2017: 2736-2744.
    [22] [19]Yang L, Zhang R, Li L, et al. SimAM: A Simple, parameter-free attention module for convolutional neural networks[C]//International Conference on Machine Learning. PMLR, 2021: 11863-11874.
    [23] [20]刘丽伟, 侯德彪, 侯阿临, 等. 基于SimAM-YOLOv4的自动驾驶目标检测算法[J]. 长春工业大学学报, 2022, 43(03): 244-250.
    [24] Liu Li-wei, Hou De-biao, Hou A-Lin, et al. Automatic driving target detection alorithm based on SimAM-YOLOv4[J]. Journal of Changchun University of Technology, 2022, 43(03): 244-250.
    [25] [21]Yu N, Qiu S, Hu X, et al. Accelerating convolutional neural networks by group-wise 2d- filter pruning[C]//International Joint Conference on Neural Networks. IEEE, 2017: 2502-2509.
    [26] [22]Law H, Deng J. Cornernet: Detecting objects as paired keypoints[C]//European Conference on Computer Vision, 2018: 734-750.
    [27] [23]Duan K, Bai S, Xie L, et al. Centernet: Keypoint triplets for object detection[C]//IEEE/CVF International Conference on Computer Vision, 2019: 6569-6578.
    [28] [24]Ge Z, Liu S, Wang F, et al. Yolox: Exceeding yolo series in 2021 [EB/OL]. arXiv preprint, (2021-07-18) [2023-03-16]. https://arxiv.org/abs/2107.08430.
    [29] [25]Zhang H, Wang Y, Dayoub F, et al. Varifocalnet: An iou-aware dense object detector[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 2021: 8514-8523.
    [30] [26]Yi J, Wu P, Liu B, et al. Oriented object detection in aerial images with box boundary-aware vectors[C]//Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision. IEEE, 2021: 2149-2158.
    [31] [27]Hou L, Lu K, Xue J, et al. Shape-adaptive selection and measurement for oriented object detection[C]//Proceedings of the 36th AAAI Conference on Artificial Intelligence. AAAI, 2022: 923-932.
    [32] [28]Tian Z, Shen C, Chen H, et al. Fcos: Fully convolutional one-stage object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 9627-9636.
    Related
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation
Share
Article Metrics
  • Abstract:266
  • PDF: 0
  • HTML: 0
  • Cited by: 0
History
  • Received:August 29,2023
  • Revised:October 14,2023
  • Adopted:October 16,2023
Article QR Code

Address:No. 219, Ningliu Road, Nanjing, Jiangsu Province

Postcode:210044

Phone:025-58731025