Occluded Vehicle Target Detection Method Based On Conditional Generative Adversarial Siamese Network

Zengyong Xu

doi:10.6180/jase.202306_26(6).0010

Occluded Vehicle Target Detection Method Based On Conditional Generative Adversarial Siamese Network

Electro-Mechanical Engineering

Zengyong Xu This email address is being protected from spambots. You need JavaScript enabled to view it.¹

¹School of Automotive Studies, Henan College of Transportation, Zhengzhou 450000 China

Received: July 13, 2022
Accepted: August 12, 2022
Publication Date: September 15, 2022

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202306_26(6).0010

ABSTRACT

In vehicle target detection process, due to the existence of occlusion, the feature of the vehicle target to be detected will be missing. So the detection accuracy will be reduced. Therefore, we propose a conditional generative adversarial siamese network for vehicle detection. The occluded vehicle network is divided into two parts: occluded feature generator and discriminator. Firstly, the random occlusion is generated for the data set as the input of the model. Then, the pooling feature of the occluded vehicle is restored by the generator, and the pooling feature of the restored occluded image is distinguished from the pooling feature of the unoccluded image by the discriminator. The siamese network is used to extract features from reconstructed images, which further improves the representation ability of the model. Finally, the experiment results show that the proposed model can accurately detect the occluded vehicles compared with other state-of-the-art methods.

Keywords: Vehicle detection; Conditional generative adversarial siamese network; Occluded feature generator; Pooling feature

REFERENCES

[1] Z. Huang, W. Li, X.-G. Xia, X. Wu, Z. Cai, and R. Tao, (2021) “A novel nonlocal-aware pyramid and multiscale multitask refinement detector for object detection in remote sensing images" IEEE Transactions on Geoscience and Remote Sensing 60: 1–20.
[2] Z. Gao, G. Yang, E. Li, Z. Liang, and R. Guo, (2021) “Efficient parallel branch network with multi-scale feature fusion for real-time overhead power line segmentation" IEEE Sensors Journal 21(10): 12220–12227.
[3] Z. Qu, X. Shang, S.-F. Xia, T.-M. Yi, and D.-Y. Zhou, (2022) “A method of single-shot target detection with multi-scale feature fusion and feature enhancement" IET Image Processing 16(6): 1752–1763.
[4] M. Zhang, S. Xu,W. Song, Q. He, and Q.Wei, (2021) “Lightweight underwater object detection based on yolo v4 and multi-scale attentional feature fusion" Remote Sensing 13(22): 4706.
[5] D. Giveki, (2021) “Robust moving object detection based on fusing Atanassov’s Intuitionistic 3D Fuzzy Histon Roughness Index and texture features" International Journal of Approximate Reasoning 135: 1–20.
[6] Y. Liu, X.-Y. Zhang, J.-W. Bian, L. Zhang, and M.-M. Cheng, (2021) “SAMNet: Stereoscopically attentive multi-scale network for lightweight salient object detection" IEEE Transactions on Image Processing 30: 3804–3814.
[7] Q. Guo, W. Feng, C. Zhou, R. Huang, L. Wan, and S. Wang. “Learning dynamic siamese network for visual object tracking”. In: Proceedings of the IEEE international conference on computer vision. 2017, 1763–1771.
[8] U. Shaham and R. R. Lederman, (2018) “Learning by coincidence: Siamese networks and common variable learning" Pattern Recognition 74: 52–63.
[9] J. Song, J. Zhang, Y. Liu, and Y. Yu, (2021) “Conditional generative adversarial siamese networks for object tracking" Control and Decision 36(5): 1110–1118.
[10] S. An, S. Lin, J. Qiao, and C. Li, (2021) “Object detection via learning occluded features based on generative adversarial networks" Control and Decision 36(5): 1199–1205.
[11] R. Girshick, J. Donahue, T. Darrell, and J. Malik. “Rich feature hierarchies for accurate object detection and semantic segmentation”. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2014, 580–587.
[12] K. He, X. Zhang, S. Ren, and J. Sun, (2015) “Spatial pyramid pooling in deep convolutional networks for visual recognition" IEEE transactions on pattern analysis and machine intelligence 37(9): 1904–1916.
[13] S. Zheng, S. Jayasumana, B. Romera Paredes, V. Vineet, Z. Su, D. Du, C. Huang, and P. Torr, (2015) “Proceedings of the IEEE international conference on computer vision":
[14] R. Faster, (2015) “Towards real-time object detection with region proposal networks" Advances in neural information processing systems 9199(10.5555): 2969239–2969250.
[15] C. Zhang and D. He, (2020) “A deep multiscale fusion method via low-rank sparse decomposition for object saliency detection based on urban data in optical remote sensing images"Wireless Communications and Mobile Computing 2020:
[16] S. Yin and H. Li, (2020) “Hot region selection based on selective search and modified fuzzy C-means in remote sensing images" IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 13: 5862–5871.
[17] C.-H. He, S.-C. Lai, and K.-M. Lam. “Improving object detection with relation graph inference”. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2019, 2537–2541.
[18] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi. “You only look once: Unified, real-time object detection”. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, 779–788.
[19] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg. “Ssd: Single shot multibox detector”. In: European conference on computer vision. Springer. 2016, 21–37.
[20] K. Kumar Singh and Y. Jae Lee. “Hide-and-seek: Forcing a network to be meticulous for weaklysupervised object and action localization”. In: Proceedings of the IEEE International Conference on Computer Vision. 2017, 3524–3533.
[21] A. Krizhevsky, I. Sutskever, and G. E. Hinton, (2012) “Imagenet classification with deep convolutional neural networks" Advances in neural information processing systems 25:
[22] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna. “Rethinking the inception architecture for computer vision”. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, 2818–2826.
[23] L. Fu, W.-b. Gu, W. Li, L. Chen, Y.-b. Ai, and H.-l. Wang, (2021) “Bidirectional parallel multi-branch convolution feature pyramid network for target detection in aerial images of swarm UAVs" Defence Technology 17(4): 1531–1541.
[24] J. M. D’Souza, V. V. Velpula, and K. Guruprasad, (2021) “Effectiveness of a Camera as a UAV Mounted Search Sensor for Target Detection: An Experimental Investigation" International Journal of Control, Automation and Systems 19(7): 2557–2568.
[25] Y. Xu, C. Yang, B. Sun, X. Yan, and M. Chen, (2021) “A novel multi-scale fusion framework for detail-preserving low-light image enhancement" Information Sciences 548: 378–397.
[26] G. Qi, Y. Zhang, K. Wang, N. Mazur, Y. Liu, and D. Malaviya, (2022) “Small Object Detection Method Based on Adaptive Spatial Parallel Convolution and Fast Multi-Scale Fusion" Remote Sensing 14(2): 420.
[27] T.-H. Lim and H. Choo, (2021) “Prediction of Target Detection Probability Based on Air-to-Air Long-Range Scenarios in Anomalous Atmospheric Environments" Remote Sensing 13(19): 3943.
[28] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D.Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, (2014) “Generative adversarial nets" Advances in neural information processing systems 27:
[29] X. Cheng, C. Song, Y. Gu, and B. Chen, (2020) “Learning attention for object tracking with adversarial learning network" EURASIP Journal on Image and Video Processing 2020(1): 1–21.
[30] O. Besson, F. Vincent, and S. Matteoli, (2021) “Adaptive target detection in hyperspectral imaging from two sets of training samples with different means" Signal Processing 181: 107909.
[31] X. Wu, A.-Q. Lin, Y. Li, H. Wu, L.-Y. Cen, H. Liu, and D.-X. Song, (2021) “Simulating spatiotemporal land use change in middle and high latitude regions using multiscale fusion and cellular automata: The case of Northeast China" Ecological Indicators 133: 108449.
[32] K.-H. Shih, C.-T. Chiu, and Y.-Y. Pu. “Real-time object detection via pruning and a concatenated multi-feature assisted region proposal network”. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2019, 1398–1402.
[33] X.Wang, A. Shrivastava, and A. Gupta. “A-fast-rcnn: Hard positive generation via adversary for object detection”. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017, 2606–2615.
[34] J. Liu, L. Wang, and H. Zhou, (2021) “The application of human–computer interaction technology fused with artificial intelligence in sports moving target detection education for college athlete" Frontiers in Psychology: 2848.
[35] S. Yin, Y. Zhang, and S. Karim, (2019) “Region search based on hybrid convolutional neural network in optical remote sensing images" International Journal of Distributed Sensor Networks 15(5): 1550147719852036.