Abstract
Infrared automatic target recognition (ATR) technology still is a challenging problem in military applications. In recent years, convolutional neural networks (CNNs) models have already led to breakthrough developments in object detection and target recognition. However, the complex environment and the bad weather caused the poor texture information and the weak background of infrared imaging. It’s difficult to use standard CNNs to perform accurate feature extraction and target classification. To overcome these shortcomings, we propose a novel deep learning framework, composed of the multi-kernel transformation and the Alpha-Beta divergence. The multi-kernel transformation operation is designed between convolutional layers and pooling layers to increase the confidence of feature extraction. The Alpha-Beta divergence is used as a penalty term to re-encode the output neurons of improved CNNs, which can promote the recognition performance of the entire network. Furthermore, comprehensive theoretical analysis and extensive experiments are confirmed that our proposed framework outperforms ResNet, VGG-19, DenseNet, and the different combinations of models in many aspects, such as short time-consuming, high accuracy, and strong robustness. Our approach yields a maximum accuracy score of 98.43% on our dataset. Meanwhile, we use the OKTAL-SE-based synthetic database and the SENSIAC dataset to verify our models. Experimental results demonstrate the maximum average accuracy is 97.16%, it is feasible and effective for infrared target recognition.
Similar content being viewed by others
Data Availability
Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.
References
Chen Z, Shi K, Chen N et al (2019) The experimental study about laser induced dizziness effect of medium-wave infrared seeker which based on image processing. J Vis Commun Image Represent 59:401–406
Chen F, Qi J, Li X (2022) Texture Image Classification Based on Deep Learning and Wireless Sensor Technology, Comput Intell Neurosci
Chen J, Du L, Guo G, et al. (2022) Target-attentional CNN for radar automatic target recognition with HRRP, signal processing 196
Ding B. (2022) Model-driven automatic target recognition of Sar images with part-level reasoning, Optik 252:168561
DivyaS PS, Pati UC (2020) Structure tensor-based SIFT algorithm for SAR image registration. IET Image Process 14(5):929–938
Fang F, Li L, Zhu H, Lim JH (2020) Combining faster R-CNN and model-driven clustering for elongated object detection[J]. IEEE Trans Image Process 29(1):2052–2065
Gan B, Yang H, Zhang W et al (2019) Stacked contractive auto-encoders application in identification of pharmaceuticals. Spectrosc Spectr Anal 39(1):96–102
Huang H (2022) Object extraction of tennis video based on deep learning, Wirel Commun Mobile Comput
Lang Y, Yuan B (2021) Algorithm application based on the infrared image in unmanned ship target image recognition, microprocessors and microsystems 80
Li T, Du L (2019) SAR automatic target recognition based on attribute scattering center model and discriminative dictionary learning. IEEE Sensors J 19(12):4598–4611
Li J, Zhang J, Du X, et al. (2021) Research on correlation of infrared image quality evaluation indexes for target tracking, 7th symposium on novel Photoelectronic detection technology and applications 11763
Luo J, Irisson J, Graham B et al (2018) Automated plankton image analysis using convolutional neural networks. Limnol Oceanogr Methods 16(12):814–827
Naiemi F, Vahid G, Hassan K (2018) An efficient character recognition method using enhanced HOG for spam image detection. Soft Comput 23(22):11759–11774
Qi S, Ning X, Yang G, et al. (2021) Review of multi-view 3D object recognition methods based on deep learning, displays 69
Riu L, Pilorget C, Hamm V, et al. (2022) Calibration and performances of the MicrOmega instrument for the characterization of asteroid Ryugu returned samples, Rev Sci Instruments 93 (5)
Shang M, Yuan Y, Luo X, et al. (2021) An alpha-beta-divergence-generalized recommender for highly accurate predictions of missing user preferences, IEEE Trans Cybern 52(8): 8006–8018
Shen C (2018) A transdisciplinary review of deep learning research and its relevance for water resources scientists. Water Resour Res 54(11):8558–8593
Vijayalakshmi D, Nath MK (2022) A novel multilevel framework based contrast enhancement for uniform and non-uniform background images using a suitable histogram equalization, Digit Signal Process 127
Wang SN, Liu Y, Li L (2022) Sparse weighting for pyramid pooling-based SAR image target recognition, Appl Sci-Basel 12(7)
Wang C, Wang X, Zhang J, et al. (2022) Uncertainty estimation for stereo matching based on evidential deep learning, Pattern Recognition 124
Wang C, Ning X, Sun L, et al. (2022) Learning discriminative features by covering local geometric space for point cloud analysis, IEEE Transactions on Geoscience and Remote Sensing 60
Wang T, Shen F, Deng H, Cai F, Chen S (2022) Smartphone imaging spectrometer for egg/meat freshness monitoring. Anal Methods 14(5):508–517
Wu J, Hu H (2017) Cascade recurrent neural network for image caption generation. Electron Lett 53(25):1642–1643
Wu G, Chen S, Li Y, et al. (2022) Null-pol response pattern in Polarimetric rotation domain: characterization and application, IEEE Geosci Remote Sens Lett 19
Xu X, Zhang X, Zhang T (2022) Lite-YOLOv5: A Lightweight Deep Learning Detector for On-Board Ship Detection in Large-Scene Sentinel-1 SAR Images [J]. Remote Sens:14(4)
Yan H, Zhang X (2020) Adaptive fractional multi-scale edge-preserving decomposition and saliency detection fusion algorithm. ISA Trans 107:160–172
Zeng Z, Sun J, Han Z. et al. (2022) SAR automatic target recognition method based on multi-stream complex-valued networks, IEEE transactions on geoscience and remote sensing 60
Zhang R, Xu L, Yu Z et al (1735-1749) Deep-IRTarget: An automatic target detector in infrared imagery using dual-domain feature extraction and allocation. IEEE Trans Multimed 24:1735–1749
Zhang H, Tian Y, Wang K, Zhang W, Wang FY (2020) Mask SSD: An effective single-stage approach to object instance segmentation[J]. IEEE Trans Image Process 29(1):2078–2093
Zhang M, An J, Yu D, et al. (2022) Convolutional neural network with attention mechanism for SAR automatic target recognition, IEEE geoscience and remote sensing letters 19
Zheng T, Bergin M, Wang G, et al. (2021) Local PM2.5 Hotspot Detector at 300 m Resolution: A Random Forest-Convolutional Neural Network Joint Model Jointly Trained on Satellite Images and Meteorology, Remote Sens, 13(7)
Zhou J, Ren K, Wan M, Cheng B, Gu G, Chen Q (2021) An infrared and visible image fusion method based on VGG-19 network. Optik 248:168084
Funding
This work is supported by National Key Research and Development Program of China (2018YFC1407505), Aeronautical Science Foundation of China (20170142002), Natural Science Foundation of Henan Province (162300410095), Natural Science Foundation of Hainan Province (119MS001), and the scientific research fund of Hainan University (No. kyqd1653).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest/competing interests
The authors declare that they have no conflicts of interest/competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Xu, L., Zhao, F., Xu, P. et al. Infrared target recognition with deep learning algorithms. Multimed Tools Appl 82, 17213–17230 (2023). https://doi.org/10.1007/s11042-022-14142-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-14142-x