Abstract
Target detection and identification based on heterogeneous data fusion is significant when performance is restricted by a sensor. Due to UAV with the characteristic of small size, identification is difficult by visual image when it is far away. Hence, we fused the information of radio signal and image for the recognition when it was too far to distinguish the type of UAV. To validate the effectiveness of data fusion, we used the deep learning framework of faster RCNN with different feature extraction network in this study. First, we constructed three datasets with various distance to verify the shortage of object recognition based on visual image. Subsequently, visual image and radio signal fusion identification based on faster RCNN is proposed. Finally, the improvement of performance was confirmed by contrast experiments. The proposed method can enhance the accuracy of identification and has faster inference with similar accuracy compared with deeper feature extraction network, which promotes the practical development of target detection and identification based on deep learning.
Similar content being viewed by others
References
E.F. Nakamura, A.A.F. Loureiro, A.C. Frery, Information fusion for wireless sensor networks: methods, models, and classifications. ACM Comput. Surv. (CSUR) 39(3), 9 (2007)
S. Sun, A survey of multi-view machine learning. Neural Comput. Appl. 23(7–8), 2031–2038 (2013)
C.M. Bishop, Pattern Recognition and Machine Learning (Springer, Berlin, 2006)
R. Kiros, R. Salakhutdinov, R. Zemel, Multimodal neural language models, in International Conference on Machine Learning (2014), pp. 595–603
J. Ngiam, A. Khosla, M. Kim et al., Multimodal Deep Learning (ICML, IN, 2011)
J. Redmon, A. Farhadi, YOLO9000: better, faster, stronger, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017), pp. 7263–7271
A. Asvadi, L. Garrote, C. Premebida et al., Multimodal vehicle detection: fusing 3D-LIDAR and color camera data. Pattern Recognit. Lett. 115, 20–29 (2018)
R. Niu, P. Zulch, M. Distasio, et al., Joint sparsity based heterogeneous data-level fusion for target detection and estimation, in Sensors and Systems for Space Applications X. International Society for Optics and Photonics (2017), p. 10196
Z. Liu, W. Zhang, S. Lin et al., Heterogeneous sensor data fusion by deep multimodal encoding. IEEE J. Sel. Top. Signal Process. 11(3), 479–491 (2017)
S. Ren, K. He, R. Girshick, et al., Faster r-cnn: towards real-time object detection with region proposal networks, in Advances in Neural Information Processing Systems (2015), pp. 91–99
J. Ma, Y. Ma, C. Li, Infrared and visual image fusion methods and applications: a survey. Inf. Fus. 45, 153–178 (2019)
D. Liu, D. Zhou, R. Nie et al., Infrared and visible image fusion based on convolutional neural network model and saliency detection via hybrid l0–l1 layer decomposition. J. Electron. Imag. 27(6), 063036 (2018)
Y. Zhang, L. Zhang, X. Bai et al., Infrared and visual image fusion through infrared feature extraction and visual information preservation. Infra. Phys. Technol. 83, 227–237 (2017)
H. Li, X.J. Wu, J. Kittler, Infrared and visual image fusion using a deep learning framework, in 2018 24th International Conference on Pattern Recognition (ICPR). IEEE (2018), pp. 2705–2710
J. Redmon, S. Divvala, R. Girshick, et al., You only look once: unified, real-time object detection, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 779–788
J. Redmon, A. Farhadi, Yolov3: An Incremental Improvement. arXiv:1804.02767 (2018)
W. Liu, D. Anguelov, D. Erhan, et al., Ssd: single shot multibox detector, in European Conference on Computer Vision (Springer, Cham, 2016), pp. 21–37
R. Girshick. Fast r-cnn, in Proceedings of the IEEE International Conference on Computer Vision (2015), pp. 1440–1448
K. He, G. Gkioxari, P. Dollár, et al., Mask r-cnn, in Proceedings of the IEEE International Conference on Computer Vision (2017), pp. 2961–2969
T.Y. Lin, P. Dollár, R. Girshick, et al., Feature pyramid networks for object detection, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017), pp. 2117–2125
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhang, Y., Zhu, B., Xie, B. et al. Visual image and radio signal fusion identification based on convolutional neural networks. J Opt 50, 237–244 (2021). https://doi.org/10.1007/s12596-020-00672-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12596-020-00672-w