Infrared weak small target detection is a critical component of infrared target detection and tracking systems, with extensive applications in maritime rescue and military surveillance. However, the task is challenging due to the complex backgrounds and the small size of the targets. Convolutional neural networks (CNNs) are proficient at capturing local details but struggle with processing global context. In contrast, Transformers excel at handling global information but may not perform well with small targets when used alone. Additionally, multiple convolutional layers can lead to the loss of target information. To address these challenges, this paper presents a Transformer-based multi-scale attention network (MATNet). The model integrates Transformer architecture with CNNs to enhance small target features more effectively. It also incorporates a multi-scale pyramid feature fusion module (FPFC) to merge features across various levels and mitigate the loss of features due to multi-layer pooling. Experimental results demonstrate that MATNet achieves superior performance compared to other methods on public datasets.

Jianchun Zhang, Haiyang Yang, Jiangfeng Sun. Infrared Small Target Detection Based on Transformer-Based Multi-scale Fusion Attention. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 10: 97-104. https://doi.org/10.25236/AJCIS.2024.071014.

[1] S. Huang, Y. Liu, Y. He, T. Zhang, and Z. Peng, “Structure-adaptive clutter suppression for infrared small target detection: Chain-growth filtering,” Remote Sens., vol. 12, no. 1, 2020, Art. no. 47.

[2] Z. Cao, X. Kong, Q. Zhu, S. Cao, and Z. Peng, “Infrared dim target detection via mode-k1k2 extension tensor tubal rank under complex ocean environment,” ISPRS J. Photogrammetry Remote Sens., vol. 181, pp. 167–190, 2021.

[3] X. Kong, C. Yang, S. Cao, C. Li, and Z. Peng, “Infrared small target detection via nonconvex tensor fibered rank approximation,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–21, 2021.

[4] X. Wang, Z. Peng, P. Zhang, and Y. He, “Infrared small target detection via nonnegativity-constrained variational mode decomposition,” IEEE Geosci. Remote Sens. Lett., vol. 14, no. 10, pp. 1700–1704, Oct. 2017.

[5] Y. Liu and Z. Peng, “Infrared small target detection based on resampling-guided image model,” IEEE Geosci. Remote Sens. Lett., vol. 19, pp. 1–5, 2021.

[6] Suyog D Deshpande, Meng Hwa Er, Ronda Venkateswarlu, and Philip Chan, “Max-mean and max-median filters for detection of small targets,” in Signal and Data Processing of Small Targets 1999. SPIE, 1999, vol. 3809, pp. 74–83.

[7] K Zhao and X Kong, “Background noise suppression in small targets infrared images and its method discussion,” Optics and Optoelectronic Technology, vol. 2, no. 2, pp. 9–12, 2004.

[8] Fereshteh Seyed Marvasti, Mohammad Reza Mosavi, and Mahdi Nasiri, “Flying small target detection in ir images based on adaptive toggle operator,” IET Computer Vision, vol. 12, no. 4, pp. 527–534, 2018.

[9] TS Anju and NR Nelwin Raj, “Shearlet transform based image denoising using histogram thresholding,” in ComNet. IEEE, 2016, pp. 162–166.

[10] Xiaoyang Wang, Zhenming Peng, Ping Zhang, and Yanmin He, “Infrared small target detection via nonnegativity-constrained variational mode decomposition,” IEEE GEOSCI REMOTE S, vol. 14, no. 10, pp. 1700–1704, 2017.

[11] Andrea Mazzu, Pietro Morerio, Lucio Marcenaro, and Carlo S Regazzoni, “A cognitive control-inspired approach to object tracking,” IEEE T IMAGE PROCESS, vol. 25, no. 6, pp. 2697–2711, 2016.

[12] Yuwen Chen and Yunhong Xin, “An efficient infrared small target detection method based on visual contrast mechanism,” IEEE GEOSCI REMOTE S, vol. 13, no. 7, pp. 962–966, 2016.

[13] He Deng, Xianping Sun, Maili Liu, Chaohui Ye, and Xin Zhou, “Small infrared target detection based on weighted local difference measure,” IEEE T GEOSCI REMOTE, vol. 54, no. 7, pp. 4204–4214, 2016.

[14] He Deng, Xianping Sun, Maili Liu, Chaohui Ye, and Xin Zhou, “Entropy-based window selection for detecting dim and small infrared targets,” Pattern Recognition, vol. 61, pp. 66–77, 2017.

[15] Jinhui Han, Sibang Liu, Gang Qin, Qian Zhao, Honghui Zhang, and Nana Li, “A local contrast method combined with adaptive background estimation for infrared small target detection,” IEEE GEOSCI REMOTES, vol. 16, no. 9, pp. 1442–1446, 2019.

[16] Chenqiang Gao, Deyu Meng, Yi Yang, Yongtao Wang, Xiaofang Zhou, and Alexander G Hauptmann, “Infrared patch-image model for small target detection in a single image,” IEEE T IMAGE PROCESS, vol. 22, no. 12, pp. 4996–5009, 2013.

[17] Xuan Kong, Chunping Yang, Siying Cao, Chaohai Li, and Zhenming Peng, “Infrared small target detection via nonconvex tensor fibered rank approximation,” IEEE T GEOSCI REMOTE, vol. 60, pp. 1–21, 2021.

[18] Hu Zhu, Shiming Liu, Lizhen Deng, Yansheng Li, and Fu Xiao, “Infrared small target detection via low-rank tensor completion with top-hat regularization,” IEEE T GEOSCI REMOTE, vol. 58, no. 2, pp. 1004–1016, 2019.

[19] Yimian Dai and Yiquan Wu, “Reweighted infrared patch-tensor model with both nonlocal and local priors for single-frame small target detection,” IEEE J-STARS, vol. 10, no. 8, pp. 3752–3767, 2017.

[20] Landan Zhang, Lingbing Peng, Tianfang Zhang, Siying Cao, and Zhenming Peng, “Infrared small target detection via non-convex rank approximation minimization joint l 2, 1 norm,” Remote Sensing, vol. 10, no. 11, pp. 1821, 2018.

[21] Shunshun Zhong, Haibo Zhou, Xingchao Cui, Xiaobing Cao, Fan Zhang, et al., “Infrared small target detection based on local-image construction and maximum correntropy,” Measurement, p. 112662, 2023.

[22] Huan Wang, Luping Zhou, and Lei Wang, “Miss detection vs. false alarm: Adversarial learning for small object segmentation in infrared images,” in ICCV, 2019, pp. 8509–8518.

[23] Yimian Dai, Yiquan Wu, Fei Zhou, and Kobus Barnard, “Asymmetric contextual modulation for infrared small target detection,” in WACV, 2021, pp. 950–959.

[24] Mingjin Zhang, Rui Zhang, Yuxiang Yang, Haichen Bai, Jing Zhang, and Jie Guo, “Isnet: Shape matters for infrared small target detection,” in CVPR, 2022, pp. 877–886.

[25] Gao Chen, Weihua Wang, and Sirui Tan, “Irstformer: A hierarchical vision transformer for infrared small target detection,” Remote Sensing, vol. 14, no. 14, pp. 3258, 2022.

[26] Kewei Wang, Shuaiyuan Du, Chengxin Liu, and Zhiguo Cao, “Interior attention-aware network for infrared small target detection,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–13, 2022.

[27] Mingjin Zhang, Haichen Bai, Jing Zhang, Rui Zhang, Chaoyue Wang, Jie Guo, and Xinbo Gao, “Rkformer: Runge-kutta transformer with random-connection attention for infrared small target detection,” in Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 1730–1738.

[28] Landan Zhang and Zhenming Peng, “Infrared small target detection based on partial sum of the tensor nuclear norm,” Remote Sensing, vol. 11, no. 4, pp. 382, 2019.

[29] Tianfang Zhang, Siying Cao, Tian Pu, and Zhenming Peng, “Agpcnet: Attention-guided pyramid context networks for infrared small target detection,” arXiv preprint arXiv: 2111.03580, 2021.

[30] Boyang Li, Chao Xiao, Longguang Wang, Yingqian Wang, Zaiping Lin, Miao Li, Wei An, and Yulan Guo, “Dense nested attention network for infrared small target detection,” IEEE T IMAGE PROCESS, 2022.

[31] Peiwen Pan, Huan Wang, Chenyi Wang, Chang Nie, “ABC: Attention with Bilinea Correlation for Infrared Small Target Detection,” 2023 IEEE International Conference on Multimedia and Expo.