Research on Low Altitude Object Detection Based on Deep Convolution Neural Network

  • Yongjun Qi
  • Junhua Gu
  • Zepei Tian
  • Dengchao Feng
  • Yingru Su
Conference paper
Part of the Studies in Distributed Intelligence book series (SDI)


The rapid and accurate detection of low altitude objects means a great deal to flight safety in low altitude airspace; however, low altitude object detection is very challenging due to the images’ characteristics such as scale variations, arbitrary orientations, extremely large aspect ratio, and so on. In recent years, deep learning methods, which have demonstrated remarkable success for supervised learning tasks, are widely applied to the field of computer vision and good results have been achieved. Therefore, the deep learning method is applied to low altitude object detection in this paper. We proposed a deep convolution neural network model, which utilizes deep supervision implicitly through the dense layer-wise connections and combines multi-level and multi-scale feature. The model has achieved state-of-the-art performance on two large-scale publicly available datasets for object detection in aerial images.


Low altitude safety Object detection Deep learning 



The authors were supported in part by the National Natural Science Foundation of China under Grant 61702157, in part by NSF of Hebei Province through the Key Program under Grant F2016202144, in part by NSF of North China Institute of Aerospace Engineering through the Key Program under Grant ZD-2013-05, and in part by Self-financing Program of Langfang under Grant 2018013155.


  1. 1.
    D. Feng, A review on visualization of three-dimensional aerial corridor for low altitude safety. Electron. Meas. Technol. 41(9), 2–9 (2018)Google Scholar
  2. 2.
    G.S. Xia, X. Bai, J. Ding et al., DOTA: a large-scale dataset for object detection in aerial images. arXiv, pp. 1–17Google Scholar
  3. 3.
    G. Cheng, P. Zhou, J. Han, RIFD-CNN: rotation-invariant and fisher discriminative convolutional neural networks for object detection. in IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2016, pp. 2884–2893Google Scholar
  4. 4.
    Y. Long, Y. Gong, Z. Xiao, et al., Accurate object localization in remote sensing images based on convolutional neural networks. IEEE Trans. Geosci. Remote Sens. 55(5), 2486–2498 (2017)CrossRefGoogle Scholar
  5. 5.
    G. Wang, X. Wang, B. Fan, et al., Feature extraction by rotation-invariant matrix representation for object detection in aerial image. IEEE Geosci. Remote Sens. Lett. 14(6), 851–855 (2017)MathSciNetCrossRefGoogle Scholar
  6. 6.
    F. Zhang, B. Du, L. Zhang, et al., Weakly supervised learning based on coupled convolutional neural networks for aircraft detection. IEEE Trans. Geosci. Remote Sens. 54(9), 5553–5563 (2016)CrossRefGoogle Scholar
  7. 7.
    J. Deng, W. Dong, R. Socher et al., ImageNet: a large-scale hierarchical image database. in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009, pp. 248–255Google Scholar
  8. 8.
    T. Lin, M. Maire, S. Belongie et al., Microsoft COCO: common objects in context. in European Conference on Computer Vision (ECCV), 2014, pp. 740–755Google Scholar
  9. 9.
    G. Huang, Z. Liu, K.Q. Weinberger, Densely connected convolutional networks. in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2261–2269Google Scholar
  10. 10.
    X. Yuan, D. Li, D. Mohapatra, M. Elhoseny, Automatic removal of complex shadows from indoor videos using transfer learning and dynamic thresholding. Comput. Electr. Eng. 70, 813–825 (2018)CrossRefGoogle Scholar
  11. 11.
    B.S. Murugan, M. Elhoseny, K. Shankar, J. Uthayakumar, Region-based scalable smart system for anomaly detection in pedestrian walkways. Comput. Electr. Eng. 75, 146–160 (2019)CrossRefGoogle Scholar
  12. 12.
    A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks. in International Conference on Neural Information Processing Systems (NIPS), 2012, pp. 1097–1105Google Scholar
  13. 13.
    K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition. in International Conference on Learning Representations (ICLR), 2015, pp. 1–13Google Scholar
  14. 14.
    C. Szegedy, W. Liu, Y. Jia et al., Going deeper with convolutions. in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 1–9Google Scholar
  15. 15.
    K. He, X. Zhang, S. Ren et al., Deep residual learning for image recognition. in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778Google Scholar
  16. 16.
    R. Girshick. Fast R-CNN. in IEEE International Conference on Computer Vision (ICCV), 2015, pp. 1440–1448Google Scholar
  17. 17.
    S. Ren, K. He, R. Girshick, et al., Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Machine Intell. 39(6), 1137–1149 (2017)CrossRefGoogle Scholar
  18. 18.
    T.Y. Lin, P. Dollar, R. Girshick et al., Feature pyramid networks for object detection. in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 936–944Google Scholar
  19. 19.
    J. Redmon, A. Farhadi, YOLO9000: better, faster, stronger. in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6517–6525Google Scholar
  20. 20.
    W. Liu, D. Anguelov, D. Erhan et al., SSD: single shot multibox detector. in European Conference on Computer Vision (ECCV), 2016, pp. 21–37Google Scholar
  21. 21.
    K. Shankar, M. Elhoseny, R. Satheesh Kumar, S.K. Lakshmanaprabu, X. Yuan, Secret image sharing scheme with encrypted shadow images using optimal homomorphic encryption technique. J. Ambient. Intell. Humaniz. Comput. (2018).
  22. 22.
    K. Shankar, M. Elhoseny, S.K. Lakshmanaprabu, M. Ilayaraja, R.M. Vidhyavathi, M. Alkhambashi, Optimal feature level fusion based ANFIS classifier for brain MRI image classification. Concurrency Comput. Pract. Exp. 2018.
  23. 23.
    M. Elhoseny, G.-B. Bian, S.K. Lakshmanaprabu, K. Shankar, A.K. Singh, W. Wu, Effective features to classify ovarian cancer data in internet of medical things. Comput. Netw. 159, 147–156 (2019)CrossRefGoogle Scholar
  24. 24.
    N. Krishnaraj, M. Elhoseny, M. Thenmozhi, Mahmoud M. Selim, K. Shankar. Deep learning model for real-time image compression in Internet of Underwater Things (IoUT). J. Real-Time Image Process. 2019.
  25. 25.
    Y. Zhu, C. Zhang, D. Zhou, et al., Traffic sign detection and recognition using fully convolutional network guided proposals. Neurocomputing 214, 758–766 (2016)CrossRefGoogle Scholar
  26. 26.
    J. Long, E. Shelhamer, T. Darrell, Fully convolutional networks for semantic segmentation. in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3431–3440Google Scholar
  27. 27.
    A. Takeki, T.T. Tu, R. Yoshihashi, et al., Combining deep features for object detection at various scales: finding small birds in landscape images. Trans. Comput. Vis. Appl. 8(1), 5 (2016)CrossRefGoogle Scholar
  28. 28.
    J. Wang, X. Wang, K. Zhang, et al., Small UAV target detection model based on deep neural network. J. Northwest. Polytech. Univ. 36(2), 258–263 (2018)CrossRefGoogle Scholar
  29. 29.
    Q. Lu, Y. Liu, J. Huang, X. Yuan, Q. Hu, License plate detection and recognition using hierarchical feature layers from CNN. Multimed. Tools Appl. 78(11), 15665–15680 (2019)CrossRefGoogle Scholar
  30. 30.
    X. Yuan, L. Xie, M. Abouelenien, A regularized ensemble framework of deep learning for cancer detection from multi-class, imbalanced training data. Pattern Recogn. 77, 160–172 (2018)CrossRefGoogle Scholar
  31. 31.
    X. Yuan, V. Sarma, Automatic urban water-body detection and segmentation from sparse ALSM data via spatially constrained model-driven clustering. IEEE Geosci. Remote Sens. Lett. 8(1), 73–77 (2010)CrossRefGoogle Scholar
  32. 32.
    G. Cheng, J. Han, P. Zhou, et al., Multi-class geospatial object detection and geographic image classification based on collection of part detectors. J. Photogramm. Remote Sens. 98(1), 119–132 (2014)CrossRefGoogle Scholar
  33. 33.
    H. Sun, X. Sun, H. Wang, et al., Automatic target detection in high-resolution remote sensing images using spatial sparse coding bag-of-words model. IEEE Geosci. Remote Sens. Lett. 9(1), 109–113 (2011)MathSciNetCrossRefGoogle Scholar
  34. 34.
    J. Han, P. Zhou, D. Zhang, et al., Efficient, simultaneous detection of multi-class geospatial targets based on visual saliency modeling and discriminative learning of sparse coding. J. Photogramm. Remote Sens. 89(1), 37–48 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Yongjun Qi
    • 1
    • 2
  • Junhua Gu
    • 1
    • 3
  • Zepei Tian
    • 4
  • Dengchao Feng
    • 2
  • Yingru Su
    • 2
  1. 1.State Key Laboratory of Reliability and Intelligence of Electrical EquipmentHebei University of TechnologyTianjinChina
  2. 2.Information Technology CenterNorth China Institute of Aerospace EngineeringLangfangChina
  3. 3.Hebei Province Key Laboratory of Big Data CalculationHebei University of TechnologyTianjinChina
  4. 4.School of Artificial IntelligenceHebei University of TechnologyTianjinChina

Personalised recommendations