Précédent|Prochain

Lightweight model for On-Orbit optical object detection

  • role： First author第一作者
  • Affiliation：

    Science & Technology on Integrated Information System Laboratory, Institute of Software Chinese Academy of Sciences, Beijing 100190, China

  • Email：746166746@qq.com
  • Introduction：吕晓宁，研究方向为遥感图像处理。E-mail：746166746@qq.com
LYU Xiaoning1,  
  • role： Corresponding author通信作者
  • Affiliation：

    Science & Technology on Integrated Information System Laboratory, Institute of Software Chinese Academy of Sciences, Beijing 100190, China

  • Email：xiayuli@iscas.ac.cn
  • Introduction：夏玉立，研究方向为遥感图像处理。E-mail： xiayuli@iscas.ac.cn
XIA Yuli1*,  
  • Affiliation：

    Science & Technology on Integrated Information System Laboratory, Institute of Software Chinese Academy of Sciences, Beijing 100190, China

    University of Chinese Academy of Sciences, Beijing 100049, China

ZHAO Junsuo12,  
  • Affiliation：

    Science & Technology on Integrated Information System Laboratory, Institute of Software Chinese Academy of Sciences, Beijing 100190, China

QIAO Peng1

résumé

As an important transport carrier and military target, aircraft detection in remote sensing images is important for aircraft rescue, early warning, and other fields. At present, the widely used neural network model has a complex structure and requires a large number of parameters, which limits the computing and storage resources of aircraft detection satellites. The efficiency and accuracy of satellite in-orbit detection need to be studied, and the computational structure must be optimized. Using neural networks in lightweight operation can reduce the computational costs and compress the overall framework.In this study, on the basis of a deep separable convolution neural network combined with deep separable convolution, the SwishBlcok bottleneck module was established by referring to the construction idea of a reverse residual structure. The characteristics of the network were simultaneously expanded in three aspects as follows: ResBlock_body was replaced with the overall design idea of the main framework of YOLO v4. Simultaneously, the channel attention mechanism of SENet was used for reference and integrated into the network structure. Different weights were given to the extracted feature maps and information. On the premise of maintaining channel separation, a separable convolution structure was used to improve the SPP structure and PANet structure; in this manner, both the number of model parameters and the memory dependence could be reduced. Moreover, the convolution layer and the batch normalization layer were merged to further accelerate forward reasoning. Drawing on the focal loss function, the loss function of object detection was improved to solve the imbalance between foreground and background data samples.The quality of algorithm restoration necessitates verification. In this study, objective evaluation indices were used to measure the algorithm from multiple angles. The public RSOD dataset and an internally produced dataset were used to compare the high-performance network models for algorithm verification. In terms of the rationality of the various improvements in the network model, verification experiments were conducted to measure the quality and processing speed of the algorithm. Then, the trained model was deployed on an embedded platform to verify the detection speed of the improved YOLO v4 algorithm model for on-orbit object recognition. The number of parameters of the proposed scheme was reduced by sevenfold compared with that of the original method, and the number of FLOPs was reduced by approximately 30 at a recognition accuracy of 94.09%. Subsequently, the experimental results were compared with the findings for the YOLO series, SSD, MobileNet, CenterNet, and other cutting-edge network models. The proposed algorithm outperformed the other methods.The proposed on-orbit object detection model can overcome the limitations of computing and storage resources, which traditionally cannot support high-precision complex models. The experimental results from ground and embedded platforms also prove that the proposed on-orbit object detection algorithm can effectively detect remote sensing targets based on detection performance. Future research may expand the scale of remote sensing datasets and improve the universality of model application scenarios

mots-clés

remote sensing;convolution neural network;Yolov4;Optical Remote Object detection;Reverse residual structure

References

  1. 1.
    Biswas D, Su H B, Wang C Y, Stevanovic A and Wang W M. 2019. An automatic traffic density estimation using single shot detection (SSD) and MobileNet-SSD. Physics and Chemistry of the Earth, Parts A/B/C, 110: 176-184
  2. 2.
    Bochkovskiy A, Wang C Y and Liao H Y M. 2020. YOLOv4: optimal speed and accuracy of object detection. arXiv: 2004. 10934
  3. 3.
    Chen Y H, Krishna T, Emer J S and Sze V. 2017. Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE Journal of Solid-State Circuits, 52(1): 127-138
  4. 4.
    Demirel H and Anbarjafari G. 2010. Satellite image resolution enhancement using complex wavelet transform. IEEE Geoscience and Remote Sensing Letters, 7(1): 123-126
  5. 5.
    Dong Y F, Zhang C T, Wang P and Feng Z. 2020. Airplane detection of optical remote sensing images based on deep learning. Laser and Optoelectronics Progress, 57(4): 041007
  6. 6.
    Girshick R. 2015. Fast R-CNN//2015 IEEE International Conference on Computer Vision. Santiago, Chile: IEEE: 1440-1448
  7. 7.
    Han X F, Jiang T, Zhao Z F and Lei Z T. 2020. Research on remote sensing image target recognition based on deep convolution neural network. International Journal of Pattern Recognition and Artificial Intelligence, 34(5): 2054015
  8. 8.
    Law H and Deng J. 2020. CornerNet: detecting objects as paired keypoints. International Journal of Computer Vision, 128(3): 642-656
  9. 9.
    Lin T Y, Goyal P, Girshick R, He K M and Dollár P. 2020. Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2): 318-327
  10. 10.
    Liu G, Sun X, Fu K and Wang H Q. 2013. Aircraft recognition in high-resolution satellite images using coarse-to-fine shape prior. IEEE Geoscience and Remote Sensing Letters, 10(3): 573-577
  11. 11.
    Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY and Berg AC. 2016. SSD: single shot MultiBox detector//14th European Conference on Computer Vision. Amsterdam, The Netherlands: Springer: 21-37
  12. 12.
    Redmon J and Farhadi A. 2018. YOLOv3: an Incremental Improvement. arXiv: 1804. 02767
  13. 13.
    Ren S Q, He K M, Girshick R and Sun J. 2017. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6): 137-1149
  14. 14.
    Roy A G, Navab N and Wachinger C. 2018. Concurrent spatial and channel ‘squeeze and excitation’ in fully convolutional networks//21st International Conference on Medical Image Computing and Computer-Assisted Intervention. Granada, Spain: Springer: 421-429
  15. 15.
    Tan M X, Pang R M and Le Q V. 2020. EfficientDet: scalable and efficient object detection//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, USA: IEEE: 10778-10787
  16. 16.
    Tang J X, Deng C W, Huang G B and Zhao B J. 2015. Compressed-domain ship detection on spaceborne optical image using deep neural network and extreme learning machine. IEEE Transactions on Geoscience and Remote Sensing, 53(3): 1174-1185
  17. 17.
    Wang C, Zhang L Q, Yan T P, Jiang T, Jia Y J and Lai Z H. 2021. Research on the state detection of the secondary panel of the switchgear based on the YOLOv5 network model. Journal of Physics: Conference Series, 1994(1): 012030
  18. 18.
    Yu J Y, Huang D, Wang L Y, Guo J and Wang Y H. 2016. A real-time on-board ship targets detection method for optical remote sensing satellite//2016 IEEE 13th International Conference on Signal Processing (ICSP). Chengdu, China: IEEE: 204-208
  19. 19.
    Zhou X Y, Zhuo J C and Krähenbühl P. 2019. Bottom-up object detection by grouping extreme and center points//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 850-859

Lire l'article complet

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website